Face Verification Subject to Varying (Age, Ethnicity, and Gender) Demographics Using Deep Learning

Khiyari, Hachim El; Wechsler, Harry

doi:10.4172/2155-6180.1000323

Cited by 38 publications

(30 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The results also show that it is easier to recognize older subjects rather than younger subjects. Similar results were found in the case of singletons [9] [18]. Here we show that those findings apply to sets as well.…”

Section: Discussionsupporting

confidence: 78%

See 1 more Smart Citation

Age Invariant Face Recognition Using Convolutional Neural Networks and Set Distances

Khiyari¹,

Wechsler²

2017

JIS

Self Cite

View full text Add to dashboard Cite

Biometric security systems based on facial characteristics face a challenging task due to variability in the intrapersonal facial appearance of subjects traced to factors such as pose, illumination, expression and aging. This paper innovates as it proposes a deep learning and set-based approach to face recognition subject to aging. The images for each subject taken at various times are treated as a single set, which is then compared to sets of images belonging to other subjects. Facial features are extracted using a convolutional neural network characteristic of deep learning. Our experimental results show that set-based recognition performs better than the singleton-based approach for both face identification and face verification. We also find that by using set-based recognition, it is easier to recognize older subjects from younger ones rather than younger subjects from older ones.

show abstract

Section: Discussionsupporting

confidence: 78%

“…CNNs have been found recently most successful for both object classification [11] and automatic rather than handcrafted feature extraction [9].…”

Section: Convolutional Neural Network and Transfer Learningmentioning

confidence: 99%

Age Invariant Face Recognition Using Convolutional Neural Networks and Set Distances

Khiyari¹,

Wechsler²

2017

JIS

Self Cite

View full text Add to dashboard Cite

show abstract

“…A crucial point in reasoning about differentials is that the vast majority of biometric systems are configured with a fixed threshold against which all comparisons are made (i.e., the threshold is not tailored to cameras, environmental conditions or, particularly, demographics). Most academic studies ignore this point (even in demographics e.g., [13]) by reporting false negative rates at fixed false positive rates rather than at fixed thresholds, thereby hiding excursions in false positive rates and misstating false negative rates. This report includes documentation of demographic differentials about typical operating thresholds.…”

Section: Fixed Threshold Operationmentioning

confidence: 99%

“…Figure 17 summarizes the false non-match rates for the 52 most accurate algorithms comparing mugshot photos. It does this for each of four race categories and two sexes 13 . Figure 18 takes the same approach but for 20 countries of birth and two age groups (over/under 45).…”

Section: Metricsmentioning

confidence: 99%

Face recognition vendor test part 3:

Grother¹,

Ngan²,

Hanaoka³

2019

230

113

View full text Add to dashboard Cite

This is the third in a series of reports on ongoing face recognition vendor tests (FRVT) executed by the National Institute of Standards and Technology (NIST). The first two reports cover, respectively, the performance of one-to-one face recognition algorithms used for verification of asserted identities, and performance of one-to-many face recognition algorithms used for identification of individuals in photo data bases. This document extends those evaluations to document accuracy variations across demographic groups. MOTIVATION The recent expansion in the availability, capability, and use of face recognition has been accompanied by assertions that demographic dependencies could lead to accuracy variations and potential bias. A report from Georgetown University [14] work noted that prior studies [22], articulated sources of bias, described the potential impacts particularly in a policing context, and discussed policy and regulatory implications. Additionally, this work is motivated by studies of demographic effects in more recent face recognition [9, 16, 23] and gender estimation algorithms [5, 36]. AIMS AND SCOPE NIST has conducted tests to quantify demographic differences in contemporary face recognition algorithms. This report provides details about the recognition process, notes where demographic effects could occur, details specific performance metrics and analyses, gives empirical results, and recommends research into the mitigation of performance deficiencies. NIST intends this report to inform discussion and decisions about the accuracy, utility, and limitations of face recognition technologies. Its intended audience includes policy makers, face recognition algorithm developers, systems integrators, and managers of face recognition systems concerned with mitigation of risks implied by demographic differentials.

show abstract

“…Згорткові нейронні мережі (Convolutional Neural Networks, CNN) є сучасним напрямком у вирішенні різних проблем аналізу зображень, таких як аналіз, класифікація, розпізнавання тощо. Було запропоновано багато різних архітектур CNN [1,2,3], але більш розповсюдженим є використання попередньо відомих та навчених реалізацій мереж типу VGG [4,5]. Глибокі архітектури нейронних мереж і CNN з десятків шарів вимагають налаштувань багатьох параметрів, а також значну кількість часу для навчання, тому кількість робіт про компактні (дрібні) архітектури нейронних мереж невпинно зростає [6,[7][8][9] останнім часом.…”

Section: вступunclassified

Ensemble of shallow convolutional neural networks for classification of gender in video stream

Gorokhovatskyi¹,

Peredrii²

2019

A.I.S.

View full text Add to dashboard Cite

Face Verification Subject to Varying (Age, Ethnicity, and Gender) Demographics Using Deep Learning

Cited by 38 publications

References 0 publications

Age Invariant Face Recognition Using Convolutional Neural Networks and Set Distances

Age Invariant Face Recognition Using Convolutional Neural Networks and Set Distances

Face recognition vendor test part 3:

Ensemble of shallow convolutional neural networks for classification of gender in video stream

Contact Info

Product

Resources

About