Face recognition across time lapse: On learning feature subspaces

Klare, Brendan; Jain, Anil K.

doi:10.1109/ijcb.2011.6117547

Cited by 37 publications

(28 citation statements)

References 22 publications

(31 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furl et als [16] and O'Toole et als [17] conducted studies to investigate the impact of cross training and matching on White and Asian races. Similar training biases were investigated by Klare and Jain [18], who showed that aging-invariant face recognition algorithms suffer from decreased performance in non-aging scenarios.…”

Section: Prior Studies and Related Workmentioning

confidence: 88%

Face Recognition Performance: Role of Demographic Information

Klare

Burge

Klontz

et al. 2012

IEEE Trans.Inform.Forensic Secur.

Self Cite

404

252

View full text Add to dashboard Cite

Abstract-This paper studies the influence of demographics on the performance of face recognition algorithms. The recognition accuracies of six different face recognition algorithms (three commercial, two non-trainable, and one trainable) are computed on a large scale gallery that is partitioned so that each partition consists entirely of specific demographic cohorts. Eight total cohorts are isolated based on gender (male and female), race/ethnicity (Black, White, and Hispanic), and age group (18 to 30, 30 to 50, and 50 to 70 years old). Experimental results demonstrate that both commercial and the non-trainable algorithms consistently have lower matching accuracies on the same cohorts (females, Blacks, and age group 18 to 30). Additional experiments investigate the impact of the demographic distribution in the training set on the performance of a trainable face recognition algorithm. We show that the matching accuracy for race/ethnicity and age cohorts can be improved by training exclusively on that specific cohort. Operationally, this leads to a scenario, called dynamic face matcher selection, where multiple face recognition algorithms (each trained on different demographic cohorts), are available for a biometric system operator to select based on the demographic information extracted from a probe image. This procedure should lead to improved face recognition accuracy in many intelligence and law enforcement face recognition scenarios.

show abstract

Section: Prior Studies and Related Workmentioning

confidence: 88%

Face Recognition Performance: Role of Demographic Information

Klare

Burge

Klontz

et al. 2012

IEEE Trans.Inform.Forensic Secur.

Self Cite

404

252

View full text Add to dashboard Cite

show abstract

“…This observation suggests learning an age gap specific model for robust face recognition [10,16]. However, other demographic factors, e.g.…”

Section: Introductionmentioning

confidence: 99%

How Does Aging Affect Facial Components?

Otto

Huang

Jain

2012

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. There is growing interest in achieving age invariant face recognition due to its wide applications in law enforcement. The challenge lies in that face aging is quite a complicated process, which involves both intrinsic and extrinsic factors. Face aging also influences individual facial components (such as the mouth, eyes, and nose) differently. We propose a component based method for age invariant face recognition. Facial components are automatically localized based on landmarks detected using an Active Shape Model. Multi-scale local binary pattern and scale-invariant feature transform features are then extracted from each component, followed by random subspace linear discriminant analysis for classification. With a component based representation, we study how aging influences individual facial components on two large aging databases (MORPH Album2 and PCSO). Per component performance analysis shows that the nose is the most stable component during face aging. Age invariant recognition exploiting demographics shows that face aging has more influence on females than males. Overall, recognition performance on the two databases shows that the proposed component based approach is more robust to large time lapses than FaceVACS, a leading commercial face matcher.

show abstract

“…The parameters used for both the alignment and the MLBP descriptors have been optimized in a number of previous studies by our research group. Our prior research has relied on such holistic representations, and these parameters represent our best practices [49]. It is also important to note that we are not able to improve the accuracy of this holistic representation by increasing the size (or IPD) of the face image.…”

Section: Resultsmentioning

confidence: 99%

“…While they outperform the nose and mouth, they only do marginally better. However, in cognitive science and automated face recognition literature, the eyes and/or eyebrows have generally been regarded as the most useful component for recognition, while the nose and mouth are regarded as being less informative [18], [22], [29], [49].…”

Section: ) Component Representations -Pcso Databasementioning

confidence: 99%

Component-Based Representation in Automated Face Recognition

Bonnen

Klare

Jain

2013

IEEE Trans.Inform.Forensic Secur.

Self Cite

View full text Add to dashboard Cite

Abstract-This paper presents a framework for componentbased face alignment and representation that demonstrates improvements in matching performance over the more common holistic approach to face alignment and representation. This work is motivated by recent evidence from the cognitive science community demonstrating the efficacy of component-based facial representations. The component-based framework presented in this paper consists of the following major steps: (i) landmark extraction using Active Shape Models (ASM), (ii) alignment and cropping of components using Procrustes Analysis, (iii) representation of components with Multi-Scale Local Binary Patterns (MLBP), (iv) per-component measurement of facial similarity, and (v) fusion of per-component similarities. We demonstrate on three public datasets and an operational dataset consisting of face images of 8,000 subjects, that the proposed componentbased representation provides higher recognition accuracies over holistic-based representations. Additionally, we show that the proposed component-based representations: (i) are more robust to changes in facial pose, and (ii) improve recognition accuracy on occluded face images in forensic scenarios.

show abstract

Face recognition across time lapse: On learning feature subspaces

Cited by 37 publications

References 22 publications

Face Recognition Performance: Role of Demographic Information

Face Recognition Performance: Role of Demographic Information

How Does Aging Affect Facial Components?

Component-Based Representation in Automated Face Recognition

Contact Info

Product

Resources

About