Image and video spatial super-resolution via bandlet-based sparsity regularization and structure tensor
A new framework for single image and video super-resolution is proposed in this paper. The main idea is to employ the geometric details of the image in a way that minimizes the possible artifacts caused by the super-resolution process. To this end, we benefit from the bandlet transform which capture...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Mosleh, Ali [verfasserIn] |
|---|
| Format: |
E-Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2015transfer abstract |
|---|
| Schlagwörter: |
|---|
| Umfang: |
10 |
|---|
| Übergeordnetes Werk: |
Enthalten in: Effectiveness of continuous and pulsed ultrasound for the management of knee osteoarthritis: a systematic review and network meta-analysis - Zeng, C. ELSEVIER, 2014, theory, techniques & applications, Amsterdam [u.a.] |
|---|---|
| Übergeordnetes Werk: |
volume:30 ; year:2015 ; pages:137-146 ; extent:10 |
| Links: |
|---|
| DOI / URN: |
10.1016/j.image.2014.10.010 |
|---|
| Katalog-ID: |
ELV039816540 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | ELV039816540 | ||
| 003 | DE-627 | ||
| 005 | 20230625225959.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 180603s2015 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.image.2014.10.010 |2 doi | |
| 028 | 5 | 2 | |a GBVA2015014000016.pica |
| 035 | |a (DE-627)ELV039816540 | ||
| 035 | |a (ELSEVIER)S0923-5965(14)00150-7 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | |a 004 |a 000 | |
| 082 | 0 | 4 | |a 004 |q DE-600 |
| 082 | 0 | 4 | |a 000 |q DE-600 |
| 082 | 0 | 4 | |a 610 |q VZ |
| 082 | 0 | 4 | |a 660 |a 620 |q VZ |
| 084 | |a 52.56 |2 bkl | ||
| 100 | 1 | |a Mosleh, Ali |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Image and video spatial super-resolution via bandlet-based sparsity regularization and structure tensor |
| 264 | 1 | |c 2015transfer abstract | |
| 300 | |a 10 | ||
| 336 | |a nicht spezifiziert |b zzz |2 rdacontent | ||
| 337 | |a nicht spezifiziert |b z |2 rdamedia | ||
| 338 | |a nicht spezifiziert |b zu |2 rdacarrier | ||
| 520 | |a A new framework for single image and video super-resolution is proposed in this paper. The main idea is to employ the geometric details of the image in a way that minimizes the possible artifacts caused by the super-resolution process. To this end, we benefit from the bandlet transform which captures the image surface geometry quite effectively. The proposed single image super-resolution method is a two-stage scheme. In the first step, edges and high frequency details of the image are interpolated in the enlarged image. This interpolation uses a structure tensor, which is modified according to the geometry layer revealed by the image bandlets. In the second stage, the edge interpolated image is fed to an inpainting scheme to estimate the pixel values for the new spatial locations within the enlarged image. These locations are treated as missing pixels and then a precise regularization in the bandlet domain is performed to fill-in the missing pixels. In a bid to avoid flickering artifacts after frame-by-frame spatially super-resolving videos, a pixel intensity refinement stage is added to the procedure which takes into account the motion flows of the frames. Due to the use of geometric details that bandlet transform captures and the edge interpolation stage, the method results in high quality, high resolution images with no over-smoothing or blurring effect while in case of video sequences it also preserves temporal consistency. Our experimental results demonstrate the effectiveness of the proposed super-resolution technique for both still images and videos. | ||
| 520 | |a A new framework for single image and video super-resolution is proposed in this paper. The main idea is to employ the geometric details of the image in a way that minimizes the possible artifacts caused by the super-resolution process. To this end, we benefit from the bandlet transform which captures the image surface geometry quite effectively. The proposed single image super-resolution method is a two-stage scheme. In the first step, edges and high frequency details of the image are interpolated in the enlarged image. This interpolation uses a structure tensor, which is modified according to the geometry layer revealed by the image bandlets. In the second stage, the edge interpolated image is fed to an inpainting scheme to estimate the pixel values for the new spatial locations within the enlarged image. These locations are treated as missing pixels and then a precise regularization in the bandlet domain is performed to fill-in the missing pixels. In a bid to avoid flickering artifacts after frame-by-frame spatially super-resolving videos, a pixel intensity refinement stage is added to the procedure which takes into account the motion flows of the frames. Due to the use of geometric details that bandlet transform captures and the edge interpolation stage, the method results in high quality, high resolution images with no over-smoothing or blurring effect while in case of video sequences it also preserves temporal consistency. Our experimental results demonstrate the effectiveness of the proposed super-resolution technique for both still images and videos. | ||
| 650 | 7 | |a Super-resolution |2 Elsevier | |
| 650 | 7 | |a Inpainting |2 Elsevier | |
| 650 | 7 | |a Video |2 Elsevier | |
| 650 | 7 | |a Structure tensor |2 Elsevier | |
| 650 | 7 | |a Bandlets |2 Elsevier | |
| 700 | 1 | |a Bouguila, Nizar |4 oth | |
| 700 | 1 | |a Hamza, A. Ben |4 oth | |
| 773 | 0 | 8 | |i Enthalten in |n Elsevier |a Zeng, C. ELSEVIER |t Effectiveness of continuous and pulsed ultrasound for the management of knee osteoarthritis: a systematic review and network meta-analysis |d 2014 |d theory, techniques & applications |g Amsterdam [u.a.] |w (DE-627)ELV017872103 |
| 773 | 1 | 8 | |g volume:30 |g year:2015 |g pages:137-146 |g extent:10 |
| 856 | 4 | 0 | |u https://doi.org/10.1016/j.image.2014.10.010 |3 Volltext |
| 912 | |a GBV_USEFLAG_U | ||
| 912 | |a GBV_ELV | ||
| 912 | |a SYSFLAG_U | ||
| 912 | |a SSG-OLC-PHA | ||
| 912 | |a GBV_ILN_21 | ||
| 912 | |a GBV_ILN_22 | ||
| 912 | |a GBV_ILN_70 | ||
| 912 | |a GBV_ILN_2002 | ||
| 912 | |a GBV_ILN_2005 | ||
| 912 | |a GBV_ILN_2014 | ||
| 912 | |a GBV_ILN_2015 | ||
| 936 | b | k | |a 52.56 |j Regenerative Energieformen |j alternative Energieformen |q VZ |
| 951 | |a AR | ||
| 952 | |d 30 |j 2015 |h 137-146 |g 10 | ||
| 953 | |2 045F |a 004 | ||
| author_variant |
a m am |
|---|---|
| matchkey_str |
moslehalibouguilanizarhamzaaben:2015----:mgadiesailuersltovaadebsdpriyeuai |
| hierarchy_sort_str |
2015transfer abstract |
| bklnumber |
52.56 |
| publishDate |
2015 |
| allfields |
10.1016/j.image.2014.10.010 doi GBVA2015014000016.pica (DE-627)ELV039816540 (ELSEVIER)S0923-5965(14)00150-7 DE-627 ger DE-627 rakwb eng 004 000 004 DE-600 000 DE-600 610 VZ 660 620 VZ 52.56 bkl Mosleh, Ali verfasserin aut Image and video spatial super-resolution via bandlet-based sparsity regularization and structure tensor 2015transfer abstract 10 nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier A new framework for single image and video super-resolution is proposed in this paper. The main idea is to employ the geometric details of the image in a way that minimizes the possible artifacts caused by the super-resolution process. To this end, we benefit from the bandlet transform which captures the image surface geometry quite effectively. The proposed single image super-resolution method is a two-stage scheme. In the first step, edges and high frequency details of the image are interpolated in the enlarged image. This interpolation uses a structure tensor, which is modified according to the geometry layer revealed by the image bandlets. In the second stage, the edge interpolated image is fed to an inpainting scheme to estimate the pixel values for the new spatial locations within the enlarged image. These locations are treated as missing pixels and then a precise regularization in the bandlet domain is performed to fill-in the missing pixels. In a bid to avoid flickering artifacts after frame-by-frame spatially super-resolving videos, a pixel intensity refinement stage is added to the procedure which takes into account the motion flows of the frames. Due to the use of geometric details that bandlet transform captures and the edge interpolation stage, the method results in high quality, high resolution images with no over-smoothing or blurring effect while in case of video sequences it also preserves temporal consistency. Our experimental results demonstrate the effectiveness of the proposed super-resolution technique for both still images and videos. A new framework for single image and video super-resolution is proposed in this paper. The main idea is to employ the geometric details of the image in a way that minimizes the possible artifacts caused by the super-resolution process. To this end, we benefit from the bandlet transform which captures the image surface geometry quite effectively. The proposed single image super-resolution method is a two-stage scheme. In the first step, edges and high frequency details of the image are interpolated in the enlarged image. This interpolation uses a structure tensor, which is modified according to the geometry layer revealed by the image bandlets. In the second stage, the edge interpolated image is fed to an inpainting scheme to estimate the pixel values for the new spatial locations within the enlarged image. These locations are treated as missing pixels and then a precise regularization in the bandlet domain is performed to fill-in the missing pixels. In a bid to avoid flickering artifacts after frame-by-frame spatially super-resolving videos, a pixel intensity refinement stage is added to the procedure which takes into account the motion flows of the frames. Due to the use of geometric details that bandlet transform captures and the edge interpolation stage, the method results in high quality, high resolution images with no over-smoothing or blurring effect while in case of video sequences it also preserves temporal consistency. Our experimental results demonstrate the effectiveness of the proposed super-resolution technique for both still images and videos. Super-resolution Elsevier Inpainting Elsevier Video Elsevier Structure tensor Elsevier Bandlets Elsevier Bouguila, Nizar oth Hamza, A. Ben oth Enthalten in Elsevier Zeng, C. ELSEVIER Effectiveness of continuous and pulsed ultrasound for the management of knee osteoarthritis: a systematic review and network meta-analysis 2014 theory, techniques & applications Amsterdam [u.a.] (DE-627)ELV017872103 volume:30 year:2015 pages:137-146 extent:10 https://doi.org/10.1016/j.image.2014.10.010 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA GBV_ILN_21 GBV_ILN_22 GBV_ILN_70 GBV_ILN_2002 GBV_ILN_2005 GBV_ILN_2014 GBV_ILN_2015 52.56 Regenerative Energieformen alternative Energieformen VZ AR 30 2015 137-146 10 045F 004 |
| spelling |
10.1016/j.image.2014.10.010 doi GBVA2015014000016.pica (DE-627)ELV039816540 (ELSEVIER)S0923-5965(14)00150-7 DE-627 ger DE-627 rakwb eng 004 000 004 DE-600 000 DE-600 610 VZ 660 620 VZ 52.56 bkl Mosleh, Ali verfasserin aut Image and video spatial super-resolution via bandlet-based sparsity regularization and structure tensor 2015transfer abstract 10 nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier A new framework for single image and video super-resolution is proposed in this paper. The main idea is to employ the geometric details of the image in a way that minimizes the possible artifacts caused by the super-resolution process. To this end, we benefit from the bandlet transform which captures the image surface geometry quite effectively. The proposed single image super-resolution method is a two-stage scheme. In the first step, edges and high frequency details of the image are interpolated in the enlarged image. This interpolation uses a structure tensor, which is modified according to the geometry layer revealed by the image bandlets. In the second stage, the edge interpolated image is fed to an inpainting scheme to estimate the pixel values for the new spatial locations within the enlarged image. These locations are treated as missing pixels and then a precise regularization in the bandlet domain is performed to fill-in the missing pixels. In a bid to avoid flickering artifacts after frame-by-frame spatially super-resolving videos, a pixel intensity refinement stage is added to the procedure which takes into account the motion flows of the frames. Due to the use of geometric details that bandlet transform captures and the edge interpolation stage, the method results in high quality, high resolution images with no over-smoothing or blurring effect while in case of video sequences it also preserves temporal consistency. Our experimental results demonstrate the effectiveness of the proposed super-resolution technique for both still images and videos. A new framework for single image and video super-resolution is proposed in this paper. The main idea is to employ the geometric details of the image in a way that minimizes the possible artifacts caused by the super-resolution process. To this end, we benefit from the bandlet transform which captures the image surface geometry quite effectively. The proposed single image super-resolution method is a two-stage scheme. In the first step, edges and high frequency details of the image are interpolated in the enlarged image. This interpolation uses a structure tensor, which is modified according to the geometry layer revealed by the image bandlets. In the second stage, the edge interpolated image is fed to an inpainting scheme to estimate the pixel values for the new spatial locations within the enlarged image. These locations are treated as missing pixels and then a precise regularization in the bandlet domain is performed to fill-in the missing pixels. In a bid to avoid flickering artifacts after frame-by-frame spatially super-resolving videos, a pixel intensity refinement stage is added to the procedure which takes into account the motion flows of the frames. Due to the use of geometric details that bandlet transform captures and the edge interpolation stage, the method results in high quality, high resolution images with no over-smoothing or blurring effect while in case of video sequences it also preserves temporal consistency. Our experimental results demonstrate the effectiveness of the proposed super-resolution technique for both still images and videos. Super-resolution Elsevier Inpainting Elsevier Video Elsevier Structure tensor Elsevier Bandlets Elsevier Bouguila, Nizar oth Hamza, A. Ben oth Enthalten in Elsevier Zeng, C. ELSEVIER Effectiveness of continuous and pulsed ultrasound for the management of knee osteoarthritis: a systematic review and network meta-analysis 2014 theory, techniques & applications Amsterdam [u.a.] (DE-627)ELV017872103 volume:30 year:2015 pages:137-146 extent:10 https://doi.org/10.1016/j.image.2014.10.010 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA GBV_ILN_21 GBV_ILN_22 GBV_ILN_70 GBV_ILN_2002 GBV_ILN_2005 GBV_ILN_2014 GBV_ILN_2015 52.56 Regenerative Energieformen alternative Energieformen VZ AR 30 2015 137-146 10 045F 004 |
| allfields_unstemmed |
10.1016/j.image.2014.10.010 doi GBVA2015014000016.pica (DE-627)ELV039816540 (ELSEVIER)S0923-5965(14)00150-7 DE-627 ger DE-627 rakwb eng 004 000 004 DE-600 000 DE-600 610 VZ 660 620 VZ 52.56 bkl Mosleh, Ali verfasserin aut Image and video spatial super-resolution via bandlet-based sparsity regularization and structure tensor 2015transfer abstract 10 nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier A new framework for single image and video super-resolution is proposed in this paper. The main idea is to employ the geometric details of the image in a way that minimizes the possible artifacts caused by the super-resolution process. To this end, we benefit from the bandlet transform which captures the image surface geometry quite effectively. The proposed single image super-resolution method is a two-stage scheme. In the first step, edges and high frequency details of the image are interpolated in the enlarged image. This interpolation uses a structure tensor, which is modified according to the geometry layer revealed by the image bandlets. In the second stage, the edge interpolated image is fed to an inpainting scheme to estimate the pixel values for the new spatial locations within the enlarged image. These locations are treated as missing pixels and then a precise regularization in the bandlet domain is performed to fill-in the missing pixels. In a bid to avoid flickering artifacts after frame-by-frame spatially super-resolving videos, a pixel intensity refinement stage is added to the procedure which takes into account the motion flows of the frames. Due to the use of geometric details that bandlet transform captures and the edge interpolation stage, the method results in high quality, high resolution images with no over-smoothing or blurring effect while in case of video sequences it also preserves temporal consistency. Our experimental results demonstrate the effectiveness of the proposed super-resolution technique for both still images and videos. A new framework for single image and video super-resolution is proposed in this paper. The main idea is to employ the geometric details of the image in a way that minimizes the possible artifacts caused by the super-resolution process. To this end, we benefit from the bandlet transform which captures the image surface geometry quite effectively. The proposed single image super-resolution method is a two-stage scheme. In the first step, edges and high frequency details of the image are interpolated in the enlarged image. This interpolation uses a structure tensor, which is modified according to the geometry layer revealed by the image bandlets. In the second stage, the edge interpolated image is fed to an inpainting scheme to estimate the pixel values for the new spatial locations within the enlarged image. These locations are treated as missing pixels and then a precise regularization in the bandlet domain is performed to fill-in the missing pixels. In a bid to avoid flickering artifacts after frame-by-frame spatially super-resolving videos, a pixel intensity refinement stage is added to the procedure which takes into account the motion flows of the frames. Due to the use of geometric details that bandlet transform captures and the edge interpolation stage, the method results in high quality, high resolution images with no over-smoothing or blurring effect while in case of video sequences it also preserves temporal consistency. Our experimental results demonstrate the effectiveness of the proposed super-resolution technique for both still images and videos. Super-resolution Elsevier Inpainting Elsevier Video Elsevier Structure tensor Elsevier Bandlets Elsevier Bouguila, Nizar oth Hamza, A. Ben oth Enthalten in Elsevier Zeng, C. ELSEVIER Effectiveness of continuous and pulsed ultrasound for the management of knee osteoarthritis: a systematic review and network meta-analysis 2014 theory, techniques & applications Amsterdam [u.a.] (DE-627)ELV017872103 volume:30 year:2015 pages:137-146 extent:10 https://doi.org/10.1016/j.image.2014.10.010 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA GBV_ILN_21 GBV_ILN_22 GBV_ILN_70 GBV_ILN_2002 GBV_ILN_2005 GBV_ILN_2014 GBV_ILN_2015 52.56 Regenerative Energieformen alternative Energieformen VZ AR 30 2015 137-146 10 045F 004 |
| allfieldsGer |
10.1016/j.image.2014.10.010 doi GBVA2015014000016.pica (DE-627)ELV039816540 (ELSEVIER)S0923-5965(14)00150-7 DE-627 ger DE-627 rakwb eng 004 000 004 DE-600 000 DE-600 610 VZ 660 620 VZ 52.56 bkl Mosleh, Ali verfasserin aut Image and video spatial super-resolution via bandlet-based sparsity regularization and structure tensor 2015transfer abstract 10 nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier A new framework for single image and video super-resolution is proposed in this paper. The main idea is to employ the geometric details of the image in a way that minimizes the possible artifacts caused by the super-resolution process. To this end, we benefit from the bandlet transform which captures the image surface geometry quite effectively. The proposed single image super-resolution method is a two-stage scheme. In the first step, edges and high frequency details of the image are interpolated in the enlarged image. This interpolation uses a structure tensor, which is modified according to the geometry layer revealed by the image bandlets. In the second stage, the edge interpolated image is fed to an inpainting scheme to estimate the pixel values for the new spatial locations within the enlarged image. These locations are treated as missing pixels and then a precise regularization in the bandlet domain is performed to fill-in the missing pixels. In a bid to avoid flickering artifacts after frame-by-frame spatially super-resolving videos, a pixel intensity refinement stage is added to the procedure which takes into account the motion flows of the frames. Due to the use of geometric details that bandlet transform captures and the edge interpolation stage, the method results in high quality, high resolution images with no over-smoothing or blurring effect while in case of video sequences it also preserves temporal consistency. Our experimental results demonstrate the effectiveness of the proposed super-resolution technique for both still images and videos. A new framework for single image and video super-resolution is proposed in this paper. The main idea is to employ the geometric details of the image in a way that minimizes the possible artifacts caused by the super-resolution process. To this end, we benefit from the bandlet transform which captures the image surface geometry quite effectively. The proposed single image super-resolution method is a two-stage scheme. In the first step, edges and high frequency details of the image are interpolated in the enlarged image. This interpolation uses a structure tensor, which is modified according to the geometry layer revealed by the image bandlets. In the second stage, the edge interpolated image is fed to an inpainting scheme to estimate the pixel values for the new spatial locations within the enlarged image. These locations are treated as missing pixels and then a precise regularization in the bandlet domain is performed to fill-in the missing pixels. In a bid to avoid flickering artifacts after frame-by-frame spatially super-resolving videos, a pixel intensity refinement stage is added to the procedure which takes into account the motion flows of the frames. Due to the use of geometric details that bandlet transform captures and the edge interpolation stage, the method results in high quality, high resolution images with no over-smoothing or blurring effect while in case of video sequences it also preserves temporal consistency. Our experimental results demonstrate the effectiveness of the proposed super-resolution technique for both still images and videos. Super-resolution Elsevier Inpainting Elsevier Video Elsevier Structure tensor Elsevier Bandlets Elsevier Bouguila, Nizar oth Hamza, A. Ben oth Enthalten in Elsevier Zeng, C. ELSEVIER Effectiveness of continuous and pulsed ultrasound for the management of knee osteoarthritis: a systematic review and network meta-analysis 2014 theory, techniques & applications Amsterdam [u.a.] (DE-627)ELV017872103 volume:30 year:2015 pages:137-146 extent:10 https://doi.org/10.1016/j.image.2014.10.010 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA GBV_ILN_21 GBV_ILN_22 GBV_ILN_70 GBV_ILN_2002 GBV_ILN_2005 GBV_ILN_2014 GBV_ILN_2015 52.56 Regenerative Energieformen alternative Energieformen VZ AR 30 2015 137-146 10 045F 004 |
| allfieldsSound |
10.1016/j.image.2014.10.010 doi GBVA2015014000016.pica (DE-627)ELV039816540 (ELSEVIER)S0923-5965(14)00150-7 DE-627 ger DE-627 rakwb eng 004 000 004 DE-600 000 DE-600 610 VZ 660 620 VZ 52.56 bkl Mosleh, Ali verfasserin aut Image and video spatial super-resolution via bandlet-based sparsity regularization and structure tensor 2015transfer abstract 10 nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier A new framework for single image and video super-resolution is proposed in this paper. The main idea is to employ the geometric details of the image in a way that minimizes the possible artifacts caused by the super-resolution process. To this end, we benefit from the bandlet transform which captures the image surface geometry quite effectively. The proposed single image super-resolution method is a two-stage scheme. In the first step, edges and high frequency details of the image are interpolated in the enlarged image. This interpolation uses a structure tensor, which is modified according to the geometry layer revealed by the image bandlets. In the second stage, the edge interpolated image is fed to an inpainting scheme to estimate the pixel values for the new spatial locations within the enlarged image. These locations are treated as missing pixels and then a precise regularization in the bandlet domain is performed to fill-in the missing pixels. In a bid to avoid flickering artifacts after frame-by-frame spatially super-resolving videos, a pixel intensity refinement stage is added to the procedure which takes into account the motion flows of the frames. Due to the use of geometric details that bandlet transform captures and the edge interpolation stage, the method results in high quality, high resolution images with no over-smoothing or blurring effect while in case of video sequences it also preserves temporal consistency. Our experimental results demonstrate the effectiveness of the proposed super-resolution technique for both still images and videos. A new framework for single image and video super-resolution is proposed in this paper. The main idea is to employ the geometric details of the image in a way that minimizes the possible artifacts caused by the super-resolution process. To this end, we benefit from the bandlet transform which captures the image surface geometry quite effectively. The proposed single image super-resolution method is a two-stage scheme. In the first step, edges and high frequency details of the image are interpolated in the enlarged image. This interpolation uses a structure tensor, which is modified according to the geometry layer revealed by the image bandlets. In the second stage, the edge interpolated image is fed to an inpainting scheme to estimate the pixel values for the new spatial locations within the enlarged image. These locations are treated as missing pixels and then a precise regularization in the bandlet domain is performed to fill-in the missing pixels. In a bid to avoid flickering artifacts after frame-by-frame spatially super-resolving videos, a pixel intensity refinement stage is added to the procedure which takes into account the motion flows of the frames. Due to the use of geometric details that bandlet transform captures and the edge interpolation stage, the method results in high quality, high resolution images with no over-smoothing or blurring effect while in case of video sequences it also preserves temporal consistency. Our experimental results demonstrate the effectiveness of the proposed super-resolution technique for both still images and videos. Super-resolution Elsevier Inpainting Elsevier Video Elsevier Structure tensor Elsevier Bandlets Elsevier Bouguila, Nizar oth Hamza, A. Ben oth Enthalten in Elsevier Zeng, C. ELSEVIER Effectiveness of continuous and pulsed ultrasound for the management of knee osteoarthritis: a systematic review and network meta-analysis 2014 theory, techniques & applications Amsterdam [u.a.] (DE-627)ELV017872103 volume:30 year:2015 pages:137-146 extent:10 https://doi.org/10.1016/j.image.2014.10.010 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA GBV_ILN_21 GBV_ILN_22 GBV_ILN_70 GBV_ILN_2002 GBV_ILN_2005 GBV_ILN_2014 GBV_ILN_2015 52.56 Regenerative Energieformen alternative Energieformen VZ AR 30 2015 137-146 10 045F 004 |
| language |
English |
| source |
Enthalten in Effectiveness of continuous and pulsed ultrasound for the management of knee osteoarthritis: a systematic review and network meta-analysis Amsterdam [u.a.] volume:30 year:2015 pages:137-146 extent:10 |
| sourceStr |
Enthalten in Effectiveness of continuous and pulsed ultrasound for the management of knee osteoarthritis: a systematic review and network meta-analysis Amsterdam [u.a.] volume:30 year:2015 pages:137-146 extent:10 |
| format_phy_str_mv |
Article |
| bklname |
Regenerative Energieformen alternative Energieformen |
| institution |
findex.gbv.de |
| topic_facet |
Super-resolution Inpainting Video Structure tensor Bandlets |
| dewey-raw |
004 |
| isfreeaccess_bool |
false |
| container_title |
Effectiveness of continuous and pulsed ultrasound for the management of knee osteoarthritis: a systematic review and network meta-analysis |
| authorswithroles_txt_mv |
Mosleh, Ali @@aut@@ Bouguila, Nizar @@oth@@ Hamza, A. Ben @@oth@@ |
| publishDateDaySort_date |
2015-01-01T00:00:00Z |
| hierarchy_top_id |
ELV017872103 |
| dewey-sort |
14 |
| id |
ELV039816540 |
| language_de |
englisch |
| fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">ELV039816540</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230625225959.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">180603s2015 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.image.2014.10.010</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">GBVA2015014000016.pica</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV039816540</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0923-5965(14)00150-7</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2=" "><subfield code="a">004</subfield><subfield code="a">000</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">004</subfield><subfield code="q">DE-600</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">000</subfield><subfield code="q">DE-600</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">610</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">660</subfield><subfield code="a">620</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">52.56</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Mosleh, Ali</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Image and video spatial super-resolution via bandlet-based sparsity regularization and structure tensor</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2015transfer abstract</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">10</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">z</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zu</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">A new framework for single image and video super-resolution is proposed in this paper. The main idea is to employ the geometric details of the image in a way that minimizes the possible artifacts caused by the super-resolution process. To this end, we benefit from the bandlet transform which captures the image surface geometry quite effectively. The proposed single image super-resolution method is a two-stage scheme. In the first step, edges and high frequency details of the image are interpolated in the enlarged image. This interpolation uses a structure tensor, which is modified according to the geometry layer revealed by the image bandlets. In the second stage, the edge interpolated image is fed to an inpainting scheme to estimate the pixel values for the new spatial locations within the enlarged image. These locations are treated as missing pixels and then a precise regularization in the bandlet domain is performed to fill-in the missing pixels. In a bid to avoid flickering artifacts after frame-by-frame spatially super-resolving videos, a pixel intensity refinement stage is added to the procedure which takes into account the motion flows of the frames. Due to the use of geometric details that bandlet transform captures and the edge interpolation stage, the method results in high quality, high resolution images with no over-smoothing or blurring effect while in case of video sequences it also preserves temporal consistency. Our experimental results demonstrate the effectiveness of the proposed super-resolution technique for both still images and videos.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">A new framework for single image and video super-resolution is proposed in this paper. The main idea is to employ the geometric details of the image in a way that minimizes the possible artifacts caused by the super-resolution process. To this end, we benefit from the bandlet transform which captures the image surface geometry quite effectively. The proposed single image super-resolution method is a two-stage scheme. In the first step, edges and high frequency details of the image are interpolated in the enlarged image. This interpolation uses a structure tensor, which is modified according to the geometry layer revealed by the image bandlets. In the second stage, the edge interpolated image is fed to an inpainting scheme to estimate the pixel values for the new spatial locations within the enlarged image. These locations are treated as missing pixels and then a precise regularization in the bandlet domain is performed to fill-in the missing pixels. In a bid to avoid flickering artifacts after frame-by-frame spatially super-resolving videos, a pixel intensity refinement stage is added to the procedure which takes into account the motion flows of the frames. Due to the use of geometric details that bandlet transform captures and the edge interpolation stage, the method results in high quality, high resolution images with no over-smoothing or blurring effect while in case of video sequences it also preserves temporal consistency. Our experimental results demonstrate the effectiveness of the proposed super-resolution technique for both still images and videos.</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Super-resolution</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Inpainting</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Video</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Structure tensor</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Bandlets</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Bouguila, Nizar</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Hamza, A. Ben</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="n">Elsevier</subfield><subfield code="a">Zeng, C. ELSEVIER</subfield><subfield code="t">Effectiveness of continuous and pulsed ultrasound for the management of knee osteoarthritis: a systematic review and network meta-analysis</subfield><subfield code="d">2014</subfield><subfield code="d">theory, techniques & applications</subfield><subfield code="g">Amsterdam [u.a.]</subfield><subfield code="w">(DE-627)ELV017872103</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:30</subfield><subfield code="g">year:2015</subfield><subfield code="g">pages:137-146</subfield><subfield code="g">extent:10</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1016/j.image.2014.10.010</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-PHA</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_21</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2002</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2005</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2015</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">52.56</subfield><subfield code="j">Regenerative Energieformen</subfield><subfield code="j">alternative Energieformen</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">30</subfield><subfield code="j">2015</subfield><subfield code="h">137-146</subfield><subfield code="g">10</subfield></datafield><datafield tag="953" ind1=" " ind2=" "><subfield code="2">045F</subfield><subfield code="a">004</subfield></datafield></record></collection>
|
| author |
Mosleh, Ali |
| spellingShingle |
Mosleh, Ali ddc 004 ddc 000 ddc 610 ddc 660 bkl 52.56 Elsevier Super-resolution Elsevier Inpainting Elsevier Video Elsevier Structure tensor Elsevier Bandlets Image and video spatial super-resolution via bandlet-based sparsity regularization and structure tensor |
| authorStr |
Mosleh, Ali |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)ELV017872103 |
| format |
electronic Article |
| dewey-ones |
004 - Data processing & computer science 000 - Computer science, information & general works 610 - Medicine & health 660 - Chemical engineering 620 - Engineering & allied operations |
| delete_txt_mv |
keep |
| author_role |
aut |
| collection |
elsevier |
| remote_str |
true |
| illustrated |
Not Illustrated |
| topic_title |
004 000 004 DE-600 000 DE-600 610 VZ 660 620 VZ 52.56 bkl Image and video spatial super-resolution via bandlet-based sparsity regularization and structure tensor Super-resolution Elsevier Inpainting Elsevier Video Elsevier Structure tensor Elsevier Bandlets Elsevier |
| topic |
ddc 004 ddc 000 ddc 610 ddc 660 bkl 52.56 Elsevier Super-resolution Elsevier Inpainting Elsevier Video Elsevier Structure tensor Elsevier Bandlets |
| topic_unstemmed |
ddc 004 ddc 000 ddc 610 ddc 660 bkl 52.56 Elsevier Super-resolution Elsevier Inpainting Elsevier Video Elsevier Structure tensor Elsevier Bandlets |
| topic_browse |
ddc 004 ddc 000 ddc 610 ddc 660 bkl 52.56 Elsevier Super-resolution Elsevier Inpainting Elsevier Video Elsevier Structure tensor Elsevier Bandlets |
| format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
zu |
| author2_variant |
n b nb a b h ab abh |
| hierarchy_parent_title |
Effectiveness of continuous and pulsed ultrasound for the management of knee osteoarthritis: a systematic review and network meta-analysis |
| hierarchy_parent_id |
ELV017872103 |
| dewey-tens |
000 - Computer science, knowledge & systems 610 - Medicine & health 660 - Chemical engineering 620 - Engineering |
| hierarchy_top_title |
Effectiveness of continuous and pulsed ultrasound for the management of knee osteoarthritis: a systematic review and network meta-analysis |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)ELV017872103 |
| title |
Image and video spatial super-resolution via bandlet-based sparsity regularization and structure tensor |
| ctrlnum |
(DE-627)ELV039816540 (ELSEVIER)S0923-5965(14)00150-7 |
| title_full |
Image and video spatial super-resolution via bandlet-based sparsity regularization and structure tensor |
| author_sort |
Mosleh, Ali |
| journal |
Effectiveness of continuous and pulsed ultrasound for the management of knee osteoarthritis: a systematic review and network meta-analysis |
| journalStr |
Effectiveness of continuous and pulsed ultrasound for the management of knee osteoarthritis: a systematic review and network meta-analysis |
| lang_code |
eng |
| isOA_bool |
false |
| dewey-hundreds |
000 - Computer science, information & general works 600 - Technology |
| recordtype |
marc |
| publishDateSort |
2015 |
| contenttype_str_mv |
zzz |
| container_start_page |
137 |
| author_browse |
Mosleh, Ali |
| container_volume |
30 |
| physical |
10 |
| class |
004 000 004 DE-600 000 DE-600 610 VZ 660 620 VZ 52.56 bkl |
| format_se |
Elektronische Aufsätze |
| author-letter |
Mosleh, Ali |
| doi_str_mv |
10.1016/j.image.2014.10.010 |
| dewey-full |
004 000 610 660 620 |
| title_sort |
image and video spatial super-resolution via bandlet-based sparsity regularization and structure tensor |
| title_auth |
Image and video spatial super-resolution via bandlet-based sparsity regularization and structure tensor |
| abstract |
A new framework for single image and video super-resolution is proposed in this paper. The main idea is to employ the geometric details of the image in a way that minimizes the possible artifacts caused by the super-resolution process. To this end, we benefit from the bandlet transform which captures the image surface geometry quite effectively. The proposed single image super-resolution method is a two-stage scheme. In the first step, edges and high frequency details of the image are interpolated in the enlarged image. This interpolation uses a structure tensor, which is modified according to the geometry layer revealed by the image bandlets. In the second stage, the edge interpolated image is fed to an inpainting scheme to estimate the pixel values for the new spatial locations within the enlarged image. These locations are treated as missing pixels and then a precise regularization in the bandlet domain is performed to fill-in the missing pixels. In a bid to avoid flickering artifacts after frame-by-frame spatially super-resolving videos, a pixel intensity refinement stage is added to the procedure which takes into account the motion flows of the frames. Due to the use of geometric details that bandlet transform captures and the edge interpolation stage, the method results in high quality, high resolution images with no over-smoothing or blurring effect while in case of video sequences it also preserves temporal consistency. Our experimental results demonstrate the effectiveness of the proposed super-resolution technique for both still images and videos. |
| abstractGer |
A new framework for single image and video super-resolution is proposed in this paper. The main idea is to employ the geometric details of the image in a way that minimizes the possible artifacts caused by the super-resolution process. To this end, we benefit from the bandlet transform which captures the image surface geometry quite effectively. The proposed single image super-resolution method is a two-stage scheme. In the first step, edges and high frequency details of the image are interpolated in the enlarged image. This interpolation uses a structure tensor, which is modified according to the geometry layer revealed by the image bandlets. In the second stage, the edge interpolated image is fed to an inpainting scheme to estimate the pixel values for the new spatial locations within the enlarged image. These locations are treated as missing pixels and then a precise regularization in the bandlet domain is performed to fill-in the missing pixels. In a bid to avoid flickering artifacts after frame-by-frame spatially super-resolving videos, a pixel intensity refinement stage is added to the procedure which takes into account the motion flows of the frames. Due to the use of geometric details that bandlet transform captures and the edge interpolation stage, the method results in high quality, high resolution images with no over-smoothing or blurring effect while in case of video sequences it also preserves temporal consistency. Our experimental results demonstrate the effectiveness of the proposed super-resolution technique for both still images and videos. |
| abstract_unstemmed |
A new framework for single image and video super-resolution is proposed in this paper. The main idea is to employ the geometric details of the image in a way that minimizes the possible artifacts caused by the super-resolution process. To this end, we benefit from the bandlet transform which captures the image surface geometry quite effectively. The proposed single image super-resolution method is a two-stage scheme. In the first step, edges and high frequency details of the image are interpolated in the enlarged image. This interpolation uses a structure tensor, which is modified according to the geometry layer revealed by the image bandlets. In the second stage, the edge interpolated image is fed to an inpainting scheme to estimate the pixel values for the new spatial locations within the enlarged image. These locations are treated as missing pixels and then a precise regularization in the bandlet domain is performed to fill-in the missing pixels. In a bid to avoid flickering artifacts after frame-by-frame spatially super-resolving videos, a pixel intensity refinement stage is added to the procedure which takes into account the motion flows of the frames. Due to the use of geometric details that bandlet transform captures and the edge interpolation stage, the method results in high quality, high resolution images with no over-smoothing or blurring effect while in case of video sequences it also preserves temporal consistency. Our experimental results demonstrate the effectiveness of the proposed super-resolution technique for both still images and videos. |
| collection_details |
GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA GBV_ILN_21 GBV_ILN_22 GBV_ILN_70 GBV_ILN_2002 GBV_ILN_2005 GBV_ILN_2014 GBV_ILN_2015 |
| title_short |
Image and video spatial super-resolution via bandlet-based sparsity regularization and structure tensor |
| url |
https://doi.org/10.1016/j.image.2014.10.010 |
| remote_bool |
true |
| author2 |
Bouguila, Nizar Hamza, A. Ben |
| author2Str |
Bouguila, Nizar Hamza, A. Ben |
| ppnlink |
ELV017872103 |
| mediatype_str_mv |
z |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| author2_role |
oth oth |
| doi_str |
10.1016/j.image.2014.10.010 |
| up_date |
2024-07-06T21:34:08.537Z |
| _version_ |
1803867021417381888 |
| fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">ELV039816540</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230625225959.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">180603s2015 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.image.2014.10.010</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">GBVA2015014000016.pica</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV039816540</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0923-5965(14)00150-7</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2=" "><subfield code="a">004</subfield><subfield code="a">000</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">004</subfield><subfield code="q">DE-600</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">000</subfield><subfield code="q">DE-600</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">610</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">660</subfield><subfield code="a">620</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">52.56</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Mosleh, Ali</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Image and video spatial super-resolution via bandlet-based sparsity regularization and structure tensor</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2015transfer abstract</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">10</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">z</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zu</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">A new framework for single image and video super-resolution is proposed in this paper. The main idea is to employ the geometric details of the image in a way that minimizes the possible artifacts caused by the super-resolution process. To this end, we benefit from the bandlet transform which captures the image surface geometry quite effectively. The proposed single image super-resolution method is a two-stage scheme. In the first step, edges and high frequency details of the image are interpolated in the enlarged image. This interpolation uses a structure tensor, which is modified according to the geometry layer revealed by the image bandlets. In the second stage, the edge interpolated image is fed to an inpainting scheme to estimate the pixel values for the new spatial locations within the enlarged image. These locations are treated as missing pixels and then a precise regularization in the bandlet domain is performed to fill-in the missing pixels. In a bid to avoid flickering artifacts after frame-by-frame spatially super-resolving videos, a pixel intensity refinement stage is added to the procedure which takes into account the motion flows of the frames. Due to the use of geometric details that bandlet transform captures and the edge interpolation stage, the method results in high quality, high resolution images with no over-smoothing or blurring effect while in case of video sequences it also preserves temporal consistency. Our experimental results demonstrate the effectiveness of the proposed super-resolution technique for both still images and videos.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">A new framework for single image and video super-resolution is proposed in this paper. The main idea is to employ the geometric details of the image in a way that minimizes the possible artifacts caused by the super-resolution process. To this end, we benefit from the bandlet transform which captures the image surface geometry quite effectively. The proposed single image super-resolution method is a two-stage scheme. In the first step, edges and high frequency details of the image are interpolated in the enlarged image. This interpolation uses a structure tensor, which is modified according to the geometry layer revealed by the image bandlets. In the second stage, the edge interpolated image is fed to an inpainting scheme to estimate the pixel values for the new spatial locations within the enlarged image. These locations are treated as missing pixels and then a precise regularization in the bandlet domain is performed to fill-in the missing pixels. In a bid to avoid flickering artifacts after frame-by-frame spatially super-resolving videos, a pixel intensity refinement stage is added to the procedure which takes into account the motion flows of the frames. Due to the use of geometric details that bandlet transform captures and the edge interpolation stage, the method results in high quality, high resolution images with no over-smoothing or blurring effect while in case of video sequences it also preserves temporal consistency. Our experimental results demonstrate the effectiveness of the proposed super-resolution technique for both still images and videos.</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Super-resolution</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Inpainting</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Video</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Structure tensor</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Bandlets</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Bouguila, Nizar</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Hamza, A. Ben</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="n">Elsevier</subfield><subfield code="a">Zeng, C. ELSEVIER</subfield><subfield code="t">Effectiveness of continuous and pulsed ultrasound for the management of knee osteoarthritis: a systematic review and network meta-analysis</subfield><subfield code="d">2014</subfield><subfield code="d">theory, techniques & applications</subfield><subfield code="g">Amsterdam [u.a.]</subfield><subfield code="w">(DE-627)ELV017872103</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:30</subfield><subfield code="g">year:2015</subfield><subfield code="g">pages:137-146</subfield><subfield code="g">extent:10</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1016/j.image.2014.10.010</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-PHA</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_21</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2002</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2005</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2015</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">52.56</subfield><subfield code="j">Regenerative Energieformen</subfield><subfield code="j">alternative Energieformen</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">30</subfield><subfield code="j">2015</subfield><subfield code="h">137-146</subfield><subfield code="g">10</subfield></datafield><datafield tag="953" ind1=" " ind2=" "><subfield code="2">045F</subfield><subfield code="a">004</subfield></datafield></record></collection>
|
| score |
7.4019346 |