Analysis of Real-Time Face-Verification Methods for Surveillance Applications

In the last decade, face-recognition and -verification methods based on deep learning have increasingly used deeper and more complex architectures to obtain state-of-the-art (SOTA) accuracy. Hence, these architectures are limited to powerful devices that can handle heavy computational resources. Con...
Ausführliche Beschreibung

Gespeichert in:

Autor*in:	Filiberto Perez-Montes [verfasserIn] Jesus Olivares-Mercado [verfasserIn] Gabriel Sanchez-Perez [verfasserIn] Gibran Benitez-Garcia [verfasserIn] Lidia Prudente-Tixteco [verfasserIn] Osvaldo Lopez-Garcia [verfasserIn]

Format:	E-Artikel
Sprache:	Englisch

Erschienen:	2023

Schlagwörter:	face verification lightweight face recognition video surveillance MobileFaceNet EfficientNet GhostNet

Übergeordnetes Werk:	In: Journal of Imaging - MDPI AG, 2016, 9(2023), 2, p 21
Übergeordnetes Werk:	volume:9 ; year:2023 ; number:2, p 21

Links:	Link aufrufen Link aufrufen Link aufrufen Journal toc

DOI / URN:	10.3390/jimaging9020021

Katalog-ID:	DOAJ08024372X

Internformat


LEADER	01000caa a22002652 4500
001	DOAJ08024372X
003	DE-627
005	20240413062753.0
007	cr uuu---uuuuu
008	230310s2023 xx \|\|\|\|\|o 00\| \|\|eng c
024	7		\|a 10.3390/jimaging9020021 \|2 doi
035			\|a (DE-627)DOAJ08024372X
035			\|a (DE-599)DOAJ359c091212754b2c94abab98aee5e1a5
040			\|a DE-627 \|b ger \|c DE-627 \|e rakwb
041			\|a eng
050		0	\|a TR1-1050
050		0	\|a R858-859.7
050		0	\|a QA75.5-76.95
100	0		\|a Filiberto Perez-Montes \|e verfasserin \|4 aut
245	1	0	\|a Analysis of Real-Time Face-Verification Methods for Surveillance Applications
264		1	\|c 2023
336			\|a Text \|b txt \|2 rdacontent
337			\|a Computermedien \|b c \|2 rdamedia
338			\|a Online-Ressource \|b cr \|2 rdacarrier
520			\|a In the last decade, face-recognition and -verification methods based on deep learning have increasingly used deeper and more complex architectures to obtain state-of-the-art (SOTA) accuracy. Hence, these architectures are limited to powerful devices that can handle heavy computational resources. Conversely, lightweight and efficient methods have recently been proposed to achieve real-time performance on limited devices and embedded systems. However, real-time face-verification methods struggle with problems usually solved by their heavy counterparts—for example, illumination changes, occlusions, face rotation, and distance to the subject. These challenges are strongly related to surveillance applications that deal with low-resolution face images under unconstrained conditions. Therefore, this paper compares three SOTA real-time face-verification methods for coping with specific problems in surveillance applications. To this end, we created an evaluation subset from two available datasets consisting of 3000 face images presenting face rotation and low-resolution problems. We defined five groups of face rotation with five levels of resolutions that can appear in common surveillance scenarios. With our evaluation subset, we methodically evaluated the face-verification accuracy of MobileFaceNet, EfficientNet-B0, and GhostNet. Furthermore, we also evaluated them with conventional datasets, such as Cross-Pose LFW and QMUL-SurvFace. When examining the experimental results of the three mentioned datasets, we found that EfficientNet-B0 could deal with both surveillance problems, but MobileFaceNet was better at handling extreme face rotation over 80 degrees.
650		4	\|a face verification
650		4	\|a lightweight face recognition
650		4	\|a video surveillance
650		4	\|a MobileFaceNet
650		4	\|a EfficientNet
650		4	\|a GhostNet
653		0	\|a Photography
653		0	\|a Computer applications to medicine. Medical informatics
653		0	\|a Electronic computers. Computer science
700	0		\|a Jesus Olivares-Mercado \|e verfasserin \|4 aut
700	0		\|a Gabriel Sanchez-Perez \|e verfasserin \|4 aut
700	0		\|a Gibran Benitez-Garcia \|e verfasserin \|4 aut
700	0		\|a Lidia Prudente-Tixteco \|e verfasserin \|4 aut
700	0		\|a Osvaldo Lopez-Garcia \|e verfasserin \|4 aut
773	0	8	\|i In \|t Journal of Imaging \|d MDPI AG, 2016 \|g 9(2023), 2, p 21 \|w (DE-627)827607911 \|w (DE-600)2824270-1 \|x 2313433X \|7 nnns
773	1	8	\|g volume:9 \|g year:2023 \|g number:2, p 21
856	4	0	\|u https://doi.org/10.3390/jimaging9020021 \|z kostenfrei
856	4	0	\|u https://doaj.org/article/359c091212754b2c94abab98aee5e1a5 \|z kostenfrei
856	4	0	\|u https://www.mdpi.com/2313-433X/9/2/21 \|z kostenfrei
856	4	2	\|u https://doaj.org/toc/2313-433X \|y Journal toc \|z kostenfrei
912			\|a GBV_USEFLAG_A
912			\|a SYSFLAG_A
912			\|a GBV_DOAJ
912			\|a GBV_ILN_11
912			\|a GBV_ILN_20
912			\|a GBV_ILN_22
912			\|a GBV_ILN_23
912			\|a GBV_ILN_24
912			\|a GBV_ILN_39
912			\|a GBV_ILN_40
912			\|a GBV_ILN_60
912			\|a GBV_ILN_62
912			\|a GBV_ILN_63
912			\|a GBV_ILN_65
912			\|a GBV_ILN_69
912			\|a GBV_ILN_70
912			\|a GBV_ILN_73
912			\|a GBV_ILN_95
912			\|a GBV_ILN_105
912			\|a GBV_ILN_110
912			\|a GBV_ILN_151
912			\|a GBV_ILN_161
912			\|a GBV_ILN_170
912			\|a GBV_ILN_213
912			\|a GBV_ILN_230
912			\|a GBV_ILN_285
912			\|a GBV_ILN_293
912			\|a GBV_ILN_370
912			\|a GBV_ILN_602
912			\|a GBV_ILN_2014
912			\|a GBV_ILN_4012
912			\|a GBV_ILN_4037
912			\|a GBV_ILN_4112
912			\|a GBV_ILN_4125
912			\|a GBV_ILN_4126
912			\|a GBV_ILN_4249
912			\|a GBV_ILN_4305
912			\|a GBV_ILN_4306
912			\|a GBV_ILN_4307
912			\|a GBV_ILN_4313
912			\|a GBV_ILN_4322
912			\|a GBV_ILN_4323
912			\|a GBV_ILN_4324
912			\|a GBV_ILN_4325
912			\|a GBV_ILN_4326
912			\|a GBV_ILN_4335
912			\|a GBV_ILN_4338
912			\|a GBV_ILN_4367
912			\|a GBV_ILN_4700
951			\|a AR
952			\|d 9 \|j 2023 \|e 2, p 21

Indexfelder

author_variant	f p m fpm j o m jom g s p gsp g b g gbg l p t lpt o l g olg
matchkey_str	article:2313433X:2023----::nlssfelieaeeiiainehdfruvi
hierarchy_sort_str	2023
callnumber-subject-code	TR
publishDate	2023
allfields	10.3390/jimaging9020021 doi (DE-627)DOAJ08024372X (DE-599)DOAJ359c091212754b2c94abab98aee5e1a5 DE-627 ger DE-627 rakwb eng TR1-1050 R858-859.7 QA75.5-76.95 Filiberto Perez-Montes verfasserin aut Analysis of Real-Time Face-Verification Methods for Surveillance Applications 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier In the last decade, face-recognition and -verification methods based on deep learning have increasingly used deeper and more complex architectures to obtain state-of-the-art (SOTA) accuracy. Hence, these architectures are limited to powerful devices that can handle heavy computational resources. Conversely, lightweight and efficient methods have recently been proposed to achieve real-time performance on limited devices and embedded systems. However, real-time face-verification methods struggle with problems usually solved by their heavy counterparts—for example, illumination changes, occlusions, face rotation, and distance to the subject. These challenges are strongly related to surveillance applications that deal with low-resolution face images under unconstrained conditions. Therefore, this paper compares three SOTA real-time face-verification methods for coping with specific problems in surveillance applications. To this end, we created an evaluation subset from two available datasets consisting of 3000 face images presenting face rotation and low-resolution problems. We defined five groups of face rotation with five levels of resolutions that can appear in common surveillance scenarios. With our evaluation subset, we methodically evaluated the face-verification accuracy of MobileFaceNet, EfficientNet-B0, and GhostNet. Furthermore, we also evaluated them with conventional datasets, such as Cross-Pose LFW and QMUL-SurvFace. When examining the experimental results of the three mentioned datasets, we found that EfficientNet-B0 could deal with both surveillance problems, but MobileFaceNet was better at handling extreme face rotation over 80 degrees. face verification lightweight face recognition video surveillance MobileFaceNet EfficientNet GhostNet Photography Computer applications to medicine. Medical informatics Electronic computers. Computer science Jesus Olivares-Mercado verfasserin aut Gabriel Sanchez-Perez verfasserin aut Gibran Benitez-Garcia verfasserin aut Lidia Prudente-Tixteco verfasserin aut Osvaldo Lopez-Garcia verfasserin aut In Journal of Imaging MDPI AG, 2016 9(2023), 2, p 21 (DE-627)827607911 (DE-600)2824270-1 2313433X nnns volume:9 year:2023 number:2, p 21 https://doi.org/10.3390/jimaging9020021 kostenfrei https://doaj.org/article/359c091212754b2c94abab98aee5e1a5 kostenfrei https://www.mdpi.com/2313-433X/9/2/21 kostenfrei https://doaj.org/toc/2313-433X Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 9 2023 2, p 21
spelling	10.3390/jimaging9020021 doi (DE-627)DOAJ08024372X (DE-599)DOAJ359c091212754b2c94abab98aee5e1a5 DE-627 ger DE-627 rakwb eng TR1-1050 R858-859.7 QA75.5-76.95 Filiberto Perez-Montes verfasserin aut Analysis of Real-Time Face-Verification Methods for Surveillance Applications 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier In the last decade, face-recognition and -verification methods based on deep learning have increasingly used deeper and more complex architectures to obtain state-of-the-art (SOTA) accuracy. Hence, these architectures are limited to powerful devices that can handle heavy computational resources. Conversely, lightweight and efficient methods have recently been proposed to achieve real-time performance on limited devices and embedded systems. However, real-time face-verification methods struggle with problems usually solved by their heavy counterparts—for example, illumination changes, occlusions, face rotation, and distance to the subject. These challenges are strongly related to surveillance applications that deal with low-resolution face images under unconstrained conditions. Therefore, this paper compares three SOTA real-time face-verification methods for coping with specific problems in surveillance applications. To this end, we created an evaluation subset from two available datasets consisting of 3000 face images presenting face rotation and low-resolution problems. We defined five groups of face rotation with five levels of resolutions that can appear in common surveillance scenarios. With our evaluation subset, we methodically evaluated the face-verification accuracy of MobileFaceNet, EfficientNet-B0, and GhostNet. Furthermore, we also evaluated them with conventional datasets, such as Cross-Pose LFW and QMUL-SurvFace. When examining the experimental results of the three mentioned datasets, we found that EfficientNet-B0 could deal with both surveillance problems, but MobileFaceNet was better at handling extreme face rotation over 80 degrees. face verification lightweight face recognition video surveillance MobileFaceNet EfficientNet GhostNet Photography Computer applications to medicine. Medical informatics Electronic computers. Computer science Jesus Olivares-Mercado verfasserin aut Gabriel Sanchez-Perez verfasserin aut Gibran Benitez-Garcia verfasserin aut Lidia Prudente-Tixteco verfasserin aut Osvaldo Lopez-Garcia verfasserin aut In Journal of Imaging MDPI AG, 2016 9(2023), 2, p 21 (DE-627)827607911 (DE-600)2824270-1 2313433X nnns volume:9 year:2023 number:2, p 21 https://doi.org/10.3390/jimaging9020021 kostenfrei https://doaj.org/article/359c091212754b2c94abab98aee5e1a5 kostenfrei https://www.mdpi.com/2313-433X/9/2/21 kostenfrei https://doaj.org/toc/2313-433X Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 9 2023 2, p 21
allfields_unstemmed	10.3390/jimaging9020021 doi (DE-627)DOAJ08024372X (DE-599)DOAJ359c091212754b2c94abab98aee5e1a5 DE-627 ger DE-627 rakwb eng TR1-1050 R858-859.7 QA75.5-76.95 Filiberto Perez-Montes verfasserin aut Analysis of Real-Time Face-Verification Methods for Surveillance Applications 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier In the last decade, face-recognition and -verification methods based on deep learning have increasingly used deeper and more complex architectures to obtain state-of-the-art (SOTA) accuracy. Hence, these architectures are limited to powerful devices that can handle heavy computational resources. Conversely, lightweight and efficient methods have recently been proposed to achieve real-time performance on limited devices and embedded systems. However, real-time face-verification methods struggle with problems usually solved by their heavy counterparts—for example, illumination changes, occlusions, face rotation, and distance to the subject. These challenges are strongly related to surveillance applications that deal with low-resolution face images under unconstrained conditions. Therefore, this paper compares three SOTA real-time face-verification methods for coping with specific problems in surveillance applications. To this end, we created an evaluation subset from two available datasets consisting of 3000 face images presenting face rotation and low-resolution problems. We defined five groups of face rotation with five levels of resolutions that can appear in common surveillance scenarios. With our evaluation subset, we methodically evaluated the face-verification accuracy of MobileFaceNet, EfficientNet-B0, and GhostNet. Furthermore, we also evaluated them with conventional datasets, such as Cross-Pose LFW and QMUL-SurvFace. When examining the experimental results of the three mentioned datasets, we found that EfficientNet-B0 could deal with both surveillance problems, but MobileFaceNet was better at handling extreme face rotation over 80 degrees. face verification lightweight face recognition video surveillance MobileFaceNet EfficientNet GhostNet Photography Computer applications to medicine. Medical informatics Electronic computers. Computer science Jesus Olivares-Mercado verfasserin aut Gabriel Sanchez-Perez verfasserin aut Gibran Benitez-Garcia verfasserin aut Lidia Prudente-Tixteco verfasserin aut Osvaldo Lopez-Garcia verfasserin aut In Journal of Imaging MDPI AG, 2016 9(2023), 2, p 21 (DE-627)827607911 (DE-600)2824270-1 2313433X nnns volume:9 year:2023 number:2, p 21 https://doi.org/10.3390/jimaging9020021 kostenfrei https://doaj.org/article/359c091212754b2c94abab98aee5e1a5 kostenfrei https://www.mdpi.com/2313-433X/9/2/21 kostenfrei https://doaj.org/toc/2313-433X Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 9 2023 2, p 21
allfieldsGer	10.3390/jimaging9020021 doi (DE-627)DOAJ08024372X (DE-599)DOAJ359c091212754b2c94abab98aee5e1a5 DE-627 ger DE-627 rakwb eng TR1-1050 R858-859.7 QA75.5-76.95 Filiberto Perez-Montes verfasserin aut Analysis of Real-Time Face-Verification Methods for Surveillance Applications 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier In the last decade, face-recognition and -verification methods based on deep learning have increasingly used deeper and more complex architectures to obtain state-of-the-art (SOTA) accuracy. Hence, these architectures are limited to powerful devices that can handle heavy computational resources. Conversely, lightweight and efficient methods have recently been proposed to achieve real-time performance on limited devices and embedded systems. However, real-time face-verification methods struggle with problems usually solved by their heavy counterparts—for example, illumination changes, occlusions, face rotation, and distance to the subject. These challenges are strongly related to surveillance applications that deal with low-resolution face images under unconstrained conditions. Therefore, this paper compares three SOTA real-time face-verification methods for coping with specific problems in surveillance applications. To this end, we created an evaluation subset from two available datasets consisting of 3000 face images presenting face rotation and low-resolution problems. We defined five groups of face rotation with five levels of resolutions that can appear in common surveillance scenarios. With our evaluation subset, we methodically evaluated the face-verification accuracy of MobileFaceNet, EfficientNet-B0, and GhostNet. Furthermore, we also evaluated them with conventional datasets, such as Cross-Pose LFW and QMUL-SurvFace. When examining the experimental results of the three mentioned datasets, we found that EfficientNet-B0 could deal with both surveillance problems, but MobileFaceNet was better at handling extreme face rotation over 80 degrees. face verification lightweight face recognition video surveillance MobileFaceNet EfficientNet GhostNet Photography Computer applications to medicine. Medical informatics Electronic computers. Computer science Jesus Olivares-Mercado verfasserin aut Gabriel Sanchez-Perez verfasserin aut Gibran Benitez-Garcia verfasserin aut Lidia Prudente-Tixteco verfasserin aut Osvaldo Lopez-Garcia verfasserin aut In Journal of Imaging MDPI AG, 2016 9(2023), 2, p 21 (DE-627)827607911 (DE-600)2824270-1 2313433X nnns volume:9 year:2023 number:2, p 21 https://doi.org/10.3390/jimaging9020021 kostenfrei https://doaj.org/article/359c091212754b2c94abab98aee5e1a5 kostenfrei https://www.mdpi.com/2313-433X/9/2/21 kostenfrei https://doaj.org/toc/2313-433X Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 9 2023 2, p 21
allfieldsSound	10.3390/jimaging9020021 doi (DE-627)DOAJ08024372X (DE-599)DOAJ359c091212754b2c94abab98aee5e1a5 DE-627 ger DE-627 rakwb eng TR1-1050 R858-859.7 QA75.5-76.95 Filiberto Perez-Montes verfasserin aut Analysis of Real-Time Face-Verification Methods for Surveillance Applications 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier In the last decade, face-recognition and -verification methods based on deep learning have increasingly used deeper and more complex architectures to obtain state-of-the-art (SOTA) accuracy. Hence, these architectures are limited to powerful devices that can handle heavy computational resources. Conversely, lightweight and efficient methods have recently been proposed to achieve real-time performance on limited devices and embedded systems. However, real-time face-verification methods struggle with problems usually solved by their heavy counterparts—for example, illumination changes, occlusions, face rotation, and distance to the subject. These challenges are strongly related to surveillance applications that deal with low-resolution face images under unconstrained conditions. Therefore, this paper compares three SOTA real-time face-verification methods for coping with specific problems in surveillance applications. To this end, we created an evaluation subset from two available datasets consisting of 3000 face images presenting face rotation and low-resolution problems. We defined five groups of face rotation with five levels of resolutions that can appear in common surveillance scenarios. With our evaluation subset, we methodically evaluated the face-verification accuracy of MobileFaceNet, EfficientNet-B0, and GhostNet. Furthermore, we also evaluated them with conventional datasets, such as Cross-Pose LFW and QMUL-SurvFace. When examining the experimental results of the three mentioned datasets, we found that EfficientNet-B0 could deal with both surveillance problems, but MobileFaceNet was better at handling extreme face rotation over 80 degrees. face verification lightweight face recognition video surveillance MobileFaceNet EfficientNet GhostNet Photography Computer applications to medicine. Medical informatics Electronic computers. Computer science Jesus Olivares-Mercado verfasserin aut Gabriel Sanchez-Perez verfasserin aut Gibran Benitez-Garcia verfasserin aut Lidia Prudente-Tixteco verfasserin aut Osvaldo Lopez-Garcia verfasserin aut In Journal of Imaging MDPI AG, 2016 9(2023), 2, p 21 (DE-627)827607911 (DE-600)2824270-1 2313433X nnns volume:9 year:2023 number:2, p 21 https://doi.org/10.3390/jimaging9020021 kostenfrei https://doaj.org/article/359c091212754b2c94abab98aee5e1a5 kostenfrei https://www.mdpi.com/2313-433X/9/2/21 kostenfrei https://doaj.org/toc/2313-433X Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 9 2023 2, p 21
language	English
source	In Journal of Imaging 9(2023), 2, p 21 volume:9 year:2023 number:2, p 21
sourceStr	In Journal of Imaging 9(2023), 2, p 21 volume:9 year:2023 number:2, p 21
format_phy_str_mv	Article
institution	findex.gbv.de
topic_facet	face verification lightweight face recognition video surveillance MobileFaceNet EfficientNet GhostNet Photography Computer applications to medicine. Medical informatics Electronic computers. Computer science
isfreeaccess_bool	true
container_title	Journal of Imaging
authorswithroles_txt_mv	Filiberto Perez-Montes @@aut@@ Jesus Olivares-Mercado @@aut@@ Gabriel Sanchez-Perez @@aut@@ Gibran Benitez-Garcia @@aut@@ Lidia Prudente-Tixteco @@aut@@ Osvaldo Lopez-Garcia @@aut@@
publishDateDaySort_date	2023-01-01T00:00:00Z
hierarchy_top_id	827607911
id	DOAJ08024372X
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">DOAJ08024372X</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20240413062753.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230310s2023 xx \|\|\|\|\|o 00\| \|\|eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.3390/jimaging9020021</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ08024372X</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJ359c091212754b2c94abab98aee5e1a5</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="050" ind1=" " ind2="0"><subfield code="a">TR1-1050</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">R858-859.7</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">QA75.5-76.95</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Filiberto Perez-Montes</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Analysis of Real-Time Face-Verification Methods for Surveillance Applications</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2023</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">In the last decade, face-recognition and -verification methods based on deep learning have increasingly used deeper and more complex architectures to obtain state-of-the-art (SOTA) accuracy. Hence, these architectures are limited to powerful devices that can handle heavy computational resources. Conversely, lightweight and efficient methods have recently been proposed to achieve real-time performance on limited devices and embedded systems. However, real-time face-verification methods struggle with problems usually solved by their heavy counterparts—for example, illumination changes, occlusions, face rotation, and distance to the subject. These challenges are strongly related to surveillance applications that deal with low-resolution face images under unconstrained conditions. Therefore, this paper compares three SOTA real-time face-verification methods for coping with specific problems in surveillance applications. To this end, we created an evaluation subset from two available datasets consisting of 3000 face images presenting face rotation and low-resolution problems. We defined five groups of face rotation with five levels of resolutions that can appear in common surveillance scenarios. With our evaluation subset, we methodically evaluated the face-verification accuracy of MobileFaceNet, EfficientNet-B0, and GhostNet. Furthermore, we also evaluated them with conventional datasets, such as Cross-Pose LFW and QMUL-SurvFace. When examining the experimental results of the three mentioned datasets, we found that EfficientNet-B0 could deal with both surveillance problems, but MobileFaceNet was better at handling extreme face rotation over 80 degrees.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">face verification</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">lightweight face recognition</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">video surveillance</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">MobileFaceNet</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">EfficientNet</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">GhostNet</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Photography</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Computer applications to medicine. Medical informatics</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Electronic computers. Computer science</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Jesus Olivares-Mercado</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Gabriel Sanchez-Perez</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Gibran Benitez-Garcia</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Lidia Prudente-Tixteco</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Osvaldo Lopez-Garcia</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">In</subfield><subfield code="t">Journal of Imaging</subfield><subfield code="d">MDPI AG, 2016</subfield><subfield code="g">9(2023), 2, p 21</subfield><subfield code="w">(DE-627)827607911</subfield><subfield code="w">(DE-600)2824270-1</subfield><subfield code="x">2313433X</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:9</subfield><subfield code="g">year:2023</subfield><subfield code="g">number:2, p 21</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.3390/jimaging9020021</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/359c091212754b2c94abab98aee5e1a5</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://www.mdpi.com/2313-433X/9/2/21</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/2313-433X</subfield><subfield code="y">Journal toc</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_DOAJ</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_11</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</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_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_39</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</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_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_170</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_213</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</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_4012</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4249</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4306</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4307</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4326</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4335</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4367</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">9</subfield><subfield code="j">2023</subfield><subfield code="e">2, p 21</subfield></datafield></record></collection>
callnumber-first	T - Technology
author	Filiberto Perez-Montes
spellingShingle	Filiberto Perez-Montes misc TR1-1050 misc R858-859.7 misc QA75.5-76.95 misc face verification misc lightweight face recognition misc video surveillance misc MobileFaceNet misc EfficientNet misc GhostNet misc Photography misc Computer applications to medicine. Medical informatics misc Electronic computers. Computer science Analysis of Real-Time Face-Verification Methods for Surveillance Applications
authorStr	Filiberto Perez-Montes
ppnlink_with_tag_str_mv	@@773@@(DE-627)827607911
format	electronic Article
delete_txt_mv	keep
author_role	aut aut aut aut aut aut
collection	DOAJ
remote_str	true
callnumber-label	TR1-1050
illustrated	Not Illustrated
issn	2313433X
topic_title	TR1-1050 R858-859.7 QA75.5-76.95 Analysis of Real-Time Face-Verification Methods for Surveillance Applications face verification lightweight face recognition video surveillance MobileFaceNet EfficientNet GhostNet
topic	misc TR1-1050 misc R858-859.7 misc QA75.5-76.95 misc face verification misc lightweight face recognition misc video surveillance misc MobileFaceNet misc EfficientNet misc GhostNet misc Photography misc Computer applications to medicine. Medical informatics misc Electronic computers. Computer science
topic_unstemmed	misc TR1-1050 misc R858-859.7 misc QA75.5-76.95 misc face verification misc lightweight face recognition misc video surveillance misc MobileFaceNet misc EfficientNet misc GhostNet misc Photography misc Computer applications to medicine. Medical informatics misc Electronic computers. Computer science
topic_browse	misc TR1-1050 misc R858-859.7 misc QA75.5-76.95 misc face verification misc lightweight face recognition misc video surveillance misc MobileFaceNet misc EfficientNet misc GhostNet misc Photography misc Computer applications to medicine. Medical informatics misc Electronic computers. Computer science
format_facet	Elektronische Aufsätze Aufsätze Elektronische Ressource
format_main_str_mv	Text Zeitschrift/Artikel
carriertype_str_mv	cr
hierarchy_parent_title	Journal of Imaging
hierarchy_parent_id	827607911
hierarchy_top_title	Journal of Imaging
isfreeaccess_txt	true
familylinks_str_mv	(DE-627)827607911 (DE-600)2824270-1
title	Analysis of Real-Time Face-Verification Methods for Surveillance Applications
ctrlnum	(DE-627)DOAJ08024372X (DE-599)DOAJ359c091212754b2c94abab98aee5e1a5
title_full	Analysis of Real-Time Face-Verification Methods for Surveillance Applications
author_sort	Filiberto Perez-Montes
journal	Journal of Imaging
journalStr	Journal of Imaging
callnumber-first-code	T
lang_code	eng
isOA_bool	true
recordtype	marc
publishDateSort	2023
contenttype_str_mv	txt
author_browse	Filiberto Perez-Montes Jesus Olivares-Mercado Gabriel Sanchez-Perez Gibran Benitez-Garcia Lidia Prudente-Tixteco Osvaldo Lopez-Garcia
container_volume	9
class	TR1-1050 R858-859.7 QA75.5-76.95
format_se	Elektronische Aufsätze
author-letter	Filiberto Perez-Montes
doi_str_mv	10.3390/jimaging9020021
author2-role	verfasserin
title_sort	analysis of real-time face-verification methods for surveillance applications
callnumber	TR1-1050
title_auth	Analysis of Real-Time Face-Verification Methods for Surveillance Applications
abstract	In the last decade, face-recognition and -verification methods based on deep learning have increasingly used deeper and more complex architectures to obtain state-of-the-art (SOTA) accuracy. Hence, these architectures are limited to powerful devices that can handle heavy computational resources. Conversely, lightweight and efficient methods have recently been proposed to achieve real-time performance on limited devices and embedded systems. However, real-time face-verification methods struggle with problems usually solved by their heavy counterparts—for example, illumination changes, occlusions, face rotation, and distance to the subject. These challenges are strongly related to surveillance applications that deal with low-resolution face images under unconstrained conditions. Therefore, this paper compares three SOTA real-time face-verification methods for coping with specific problems in surveillance applications. To this end, we created an evaluation subset from two available datasets consisting of 3000 face images presenting face rotation and low-resolution problems. We defined five groups of face rotation with five levels of resolutions that can appear in common surveillance scenarios. With our evaluation subset, we methodically evaluated the face-verification accuracy of MobileFaceNet, EfficientNet-B0, and GhostNet. Furthermore, we also evaluated them with conventional datasets, such as Cross-Pose LFW and QMUL-SurvFace. When examining the experimental results of the three mentioned datasets, we found that EfficientNet-B0 could deal with both surveillance problems, but MobileFaceNet was better at handling extreme face rotation over 80 degrees.
abstractGer	In the last decade, face-recognition and -verification methods based on deep learning have increasingly used deeper and more complex architectures to obtain state-of-the-art (SOTA) accuracy. Hence, these architectures are limited to powerful devices that can handle heavy computational resources. Conversely, lightweight and efficient methods have recently been proposed to achieve real-time performance on limited devices and embedded systems. However, real-time face-verification methods struggle with problems usually solved by their heavy counterparts—for example, illumination changes, occlusions, face rotation, and distance to the subject. These challenges are strongly related to surveillance applications that deal with low-resolution face images under unconstrained conditions. Therefore, this paper compares three SOTA real-time face-verification methods for coping with specific problems in surveillance applications. To this end, we created an evaluation subset from two available datasets consisting of 3000 face images presenting face rotation and low-resolution problems. We defined five groups of face rotation with five levels of resolutions that can appear in common surveillance scenarios. With our evaluation subset, we methodically evaluated the face-verification accuracy of MobileFaceNet, EfficientNet-B0, and GhostNet. Furthermore, we also evaluated them with conventional datasets, such as Cross-Pose LFW and QMUL-SurvFace. When examining the experimental results of the three mentioned datasets, we found that EfficientNet-B0 could deal with both surveillance problems, but MobileFaceNet was better at handling extreme face rotation over 80 degrees.
abstract_unstemmed	In the last decade, face-recognition and -verification methods based on deep learning have increasingly used deeper and more complex architectures to obtain state-of-the-art (SOTA) accuracy. Hence, these architectures are limited to powerful devices that can handle heavy computational resources. Conversely, lightweight and efficient methods have recently been proposed to achieve real-time performance on limited devices and embedded systems. However, real-time face-verification methods struggle with problems usually solved by their heavy counterparts—for example, illumination changes, occlusions, face rotation, and distance to the subject. These challenges are strongly related to surveillance applications that deal with low-resolution face images under unconstrained conditions. Therefore, this paper compares three SOTA real-time face-verification methods for coping with specific problems in surveillance applications. To this end, we created an evaluation subset from two available datasets consisting of 3000 face images presenting face rotation and low-resolution problems. We defined five groups of face rotation with five levels of resolutions that can appear in common surveillance scenarios. With our evaluation subset, we methodically evaluated the face-verification accuracy of MobileFaceNet, EfficientNet-B0, and GhostNet. Furthermore, we also evaluated them with conventional datasets, such as Cross-Pose LFW and QMUL-SurvFace. When examining the experimental results of the three mentioned datasets, we found that EfficientNet-B0 could deal with both surveillance problems, but MobileFaceNet was better at handling extreme face rotation over 80 degrees.
collection_details	GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700
container_issue	2, p 21
title_short	Analysis of Real-Time Face-Verification Methods for Surveillance Applications
url	https://doi.org/10.3390/jimaging9020021 https://doaj.org/article/359c091212754b2c94abab98aee5e1a5 https://www.mdpi.com/2313-433X/9/2/21 https://doaj.org/toc/2313-433X
remote_bool	true
author2	Jesus Olivares-Mercado Gabriel Sanchez-Perez Gibran Benitez-Garcia Lidia Prudente-Tixteco Osvaldo Lopez-Garcia
author2Str	Jesus Olivares-Mercado Gabriel Sanchez-Perez Gibran Benitez-Garcia Lidia Prudente-Tixteco Osvaldo Lopez-Garcia
ppnlink	827607911
callnumber-subject	TR - Photography
mediatype_str_mv	c
isOA_txt	true
hochschulschrift_bool	false
doi_str	10.3390/jimaging9020021
callnumber-a	TR1-1050
up_date	2024-07-03T13:35:28.934Z
_version_	1803565115835940864
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">DOAJ08024372X</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20240413062753.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230310s2023 xx \|\|\|\|\|o 00\| \|\|eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.3390/jimaging9020021</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ08024372X</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJ359c091212754b2c94abab98aee5e1a5</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="050" ind1=" " ind2="0"><subfield code="a">TR1-1050</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">R858-859.7</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">QA75.5-76.95</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Filiberto Perez-Montes</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Analysis of Real-Time Face-Verification Methods for Surveillance Applications</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2023</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">In the last decade, face-recognition and -verification methods based on deep learning have increasingly used deeper and more complex architectures to obtain state-of-the-art (SOTA) accuracy. Hence, these architectures are limited to powerful devices that can handle heavy computational resources. Conversely, lightweight and efficient methods have recently been proposed to achieve real-time performance on limited devices and embedded systems. However, real-time face-verification methods struggle with problems usually solved by their heavy counterparts—for example, illumination changes, occlusions, face rotation, and distance to the subject. These challenges are strongly related to surveillance applications that deal with low-resolution face images under unconstrained conditions. Therefore, this paper compares three SOTA real-time face-verification methods for coping with specific problems in surveillance applications. To this end, we created an evaluation subset from two available datasets consisting of 3000 face images presenting face rotation and low-resolution problems. We defined five groups of face rotation with five levels of resolutions that can appear in common surveillance scenarios. With our evaluation subset, we methodically evaluated the face-verification accuracy of MobileFaceNet, EfficientNet-B0, and GhostNet. Furthermore, we also evaluated them with conventional datasets, such as Cross-Pose LFW and QMUL-SurvFace. When examining the experimental results of the three mentioned datasets, we found that EfficientNet-B0 could deal with both surveillance problems, but MobileFaceNet was better at handling extreme face rotation over 80 degrees.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">face verification</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">lightweight face recognition</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">video surveillance</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">MobileFaceNet</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">EfficientNet</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">GhostNet</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Photography</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Computer applications to medicine. Medical informatics</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Electronic computers. Computer science</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Jesus Olivares-Mercado</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Gabriel Sanchez-Perez</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Gibran Benitez-Garcia</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Lidia Prudente-Tixteco</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Osvaldo Lopez-Garcia</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">In</subfield><subfield code="t">Journal of Imaging</subfield><subfield code="d">MDPI AG, 2016</subfield><subfield code="g">9(2023), 2, p 21</subfield><subfield code="w">(DE-627)827607911</subfield><subfield code="w">(DE-600)2824270-1</subfield><subfield code="x">2313433X</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:9</subfield><subfield code="g">year:2023</subfield><subfield code="g">number:2, p 21</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.3390/jimaging9020021</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/359c091212754b2c94abab98aee5e1a5</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://www.mdpi.com/2313-433X/9/2/21</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/2313-433X</subfield><subfield code="y">Journal toc</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_DOAJ</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_11</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</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_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_39</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</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_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_170</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_213</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</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_4012</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4249</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4306</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4307</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4326</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4335</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4367</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">9</subfield><subfield code="j">2023</subfield><subfield code="e">2, p 21</subfield></datafield></record></collection>
score	7.4014435

Nicht das Richtige dabei?

Schreiben Sie uns!

Analysis of Real-Time Face-Verification Methods for Surveillance Applications

Nicht das Richtige dabei?

Zugang & Verfügbarkeit

Vorhandene Bände

Nicht das Richtige dabei?