Psychophysically inspired Bayesian occlusion model to recognize occluded faces

Ibrahim Venkat; Ahamad Tajudin Khader; K G Subramanian; Philippe De Wilde

doi:10.1007/978-3-642-23672-3_51

Psychophysically inspired Bayesian occlusion model to recognize occluded faces

Ibrahim Venkat^*, Ahamad Tajudin Khader, K G Subramanian, Philippe De Wilde

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

4 Citations (Scopus)

Abstract

Face recognition systems robust to major occlusions have wide applications ranging from consumer products with biometric features to surveillance and law enforcement applications. In unconstrained scenarios, faces are often subject to occlusions, apart from common variations such as pose, illumination, scale, orientation and so on. In this paper we propose a novel Bayesian oriented occlusion model inspired by psychophysical mechanisms to recognize faces prone to occlusions amidst other common variations. We have discovered and modeled similarity maps that exist in facial domains by means of Bayesian Networks. The proposed model is capable of efficiently learning and exploiting these maps from the facial domain. Hence it can tackle the occlusion uncertainty reasonably well. Improved recognition rates over state of the art techniques have been observed.

Original language	English
Title of host publication	Computer Analysis of Images and Patterns
Subtitle of host publication	14th International Conference, CAIP 2011, Seville, Spain, August 29-31, 2011, Proceedings, Part I
Editors	Pedro Real, Daniel Diaz-Pernil, Helena Molina-Abril, Ainhoa Berciano, Walter Kropatsch
Publisher	Springer
Pages	420-426
Number of pages	7
ISBN (Electronic)	978-3-642-23672-3
ISBN (Print)	978-3-642-23671-6
DOIs	https://doi.org/10.1007/978-3-642-23672-3_51
Publication status	Published - 2011
Event	14th International Conference on Computer Analysis of Images and Patterns - Seville, Spain Duration: 29 Aug 2011 → 31 Aug 2011

Publication series

Name	Lecture Notes in Computer Science
Volume	6854
ISSN (Print)	0302-9743

Conference

Conference	14th International Conference on Computer Analysis of Images and Patterns
Abbreviated title	CAIP 2011
Country/Territory	Spain
City	Seville
Period	29/08/11 → 31/08/11

Keywords

Face Recognition
Occlusion Models
Similarity Measures
Bayesian Networks
Parameter Estimation
SIMILARITY

Access to Document

10.1007/978-3-642-23672-3_51

Cite this

Venkat, I., Khader, A. T., Subramanian, K. G., & De Wilde, P. (2011). Psychophysically inspired Bayesian occlusion model to recognize occluded faces. In P. Real, D. Diaz-Pernil, H. Molina-Abril, A. Berciano, & W. Kropatsch (Eds.), Computer Analysis of Images and Patterns: 14th International Conference, CAIP 2011, Seville, Spain, August 29-31, 2011, Proceedings, Part I (pp. 420-426). (Lecture Notes in Computer Science; Vol. 6854). Springer. https://doi.org/10.1007/978-3-642-23672-3_51

Venkat, Ibrahim ; Khader, Ahamad Tajudin ; Subramanian, K G et al. / Psychophysically inspired Bayesian occlusion model to recognize occluded faces. Computer Analysis of Images and Patterns: 14th International Conference, CAIP 2011, Seville, Spain, August 29-31, 2011, Proceedings, Part I. editor / Pedro Real ; Daniel Diaz-Pernil ; Helena Molina-Abril ; Ainhoa Berciano ; Walter Kropatsch. Springer, 2011. pp. 420-426 (Lecture Notes in Computer Science).

@inproceedings{f48bea2d0b73485aa6f8139ff2935be4,

title = "Psychophysically inspired Bayesian occlusion model to recognize occluded faces",

abstract = "Face recognition systems robust to major occlusions have wide applications ranging from consumer products with biometric features to surveillance and law enforcement applications. In unconstrained scenarios, faces are often subject to occlusions, apart from common variations such as pose, illumination, scale, orientation and so on. In this paper we propose a novel Bayesian oriented occlusion model inspired by psychophysical mechanisms to recognize faces prone to occlusions amidst other common variations. We have discovered and modeled similarity maps that exist in facial domains by means of Bayesian Networks. The proposed model is capable of efficiently learning and exploiting these maps from the facial domain. Hence it can tackle the occlusion uncertainty reasonably well. Improved recognition rates over state of the art techniques have been observed.",

keywords = "Face Recognition, Occlusion Models, Similarity Measures, Bayesian Networks, Parameter Estimation, SIMILARITY",

author = "Ibrahim Venkat and Khader, {Ahamad Tajudin} and Subramanian, {K G} and {De Wilde}, Philippe",

year = "2011",

doi = "10.1007/978-3-642-23672-3_51",

language = "English",

isbn = "978-3-642-23671-6",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "420--426",

editor = "Pedro Real and Daniel Diaz-Pernil and Molina-Abril, {Helena } and Berciano, {Ainhoa } and Walter Kropatsch",

booktitle = "Computer Analysis of Images and Patterns",

note = "14th International Conference on Computer Analysis of Images and Patterns, CAIP 2011 ; Conference date: 29-08-2011 Through 31-08-2011",

}

Venkat, I, Khader, AT, Subramanian, KG & De Wilde, P 2011, Psychophysically inspired Bayesian occlusion model to recognize occluded faces. in P Real, D Diaz-Pernil, H Molina-Abril, A Berciano & W Kropatsch (eds), Computer Analysis of Images and Patterns: 14th International Conference, CAIP 2011, Seville, Spain, August 29-31, 2011, Proceedings, Part I. Lecture Notes in Computer Science, vol. 6854, Springer, pp. 420-426, 14th International Conference on Computer Analysis of Images and Patterns, Seville, Spain, 29/08/11. https://doi.org/10.1007/978-3-642-23672-3_51

Psychophysically inspired Bayesian occlusion model to recognize occluded faces. / Venkat, Ibrahim; Khader, Ahamad Tajudin; Subramanian, K G et al.
Computer Analysis of Images and Patterns: 14th International Conference, CAIP 2011, Seville, Spain, August 29-31, 2011, Proceedings, Part I. ed. / Pedro Real; Daniel Diaz-Pernil; Helena Molina-Abril; Ainhoa Berciano; Walter Kropatsch. Springer, 2011. p. 420-426 (Lecture Notes in Computer Science; Vol. 6854).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Psychophysically inspired Bayesian occlusion model to recognize occluded faces

AU - Venkat, Ibrahim

AU - Khader, Ahamad Tajudin

AU - Subramanian, K G

AU - De Wilde, Philippe

PY - 2011

Y1 - 2011

N2 - Face recognition systems robust to major occlusions have wide applications ranging from consumer products with biometric features to surveillance and law enforcement applications. In unconstrained scenarios, faces are often subject to occlusions, apart from common variations such as pose, illumination, scale, orientation and so on. In this paper we propose a novel Bayesian oriented occlusion model inspired by psychophysical mechanisms to recognize faces prone to occlusions amidst other common variations. We have discovered and modeled similarity maps that exist in facial domains by means of Bayesian Networks. The proposed model is capable of efficiently learning and exploiting these maps from the facial domain. Hence it can tackle the occlusion uncertainty reasonably well. Improved recognition rates over state of the art techniques have been observed.

AB - Face recognition systems robust to major occlusions have wide applications ranging from consumer products with biometric features to surveillance and law enforcement applications. In unconstrained scenarios, faces are often subject to occlusions, apart from common variations such as pose, illumination, scale, orientation and so on. In this paper we propose a novel Bayesian oriented occlusion model inspired by psychophysical mechanisms to recognize faces prone to occlusions amidst other common variations. We have discovered and modeled similarity maps that exist in facial domains by means of Bayesian Networks. The proposed model is capable of efficiently learning and exploiting these maps from the facial domain. Hence it can tackle the occlusion uncertainty reasonably well. Improved recognition rates over state of the art techniques have been observed.

KW - Face Recognition

KW - Occlusion Models

KW - Similarity Measures

KW - Bayesian Networks

KW - Parameter Estimation

KW - SIMILARITY

U2 - 10.1007/978-3-642-23672-3_51

DO - 10.1007/978-3-642-23672-3_51

M3 - Conference contribution

SN - 978-3-642-23671-6

T3 - Lecture Notes in Computer Science

SP - 420

EP - 426

BT - Computer Analysis of Images and Patterns

A2 - Real, Pedro

A2 - Diaz-Pernil, Daniel

A2 - Molina-Abril, Helena

A2 - Berciano, Ainhoa

A2 - Kropatsch, Walter

PB - Springer

T2 - 14th International Conference on Computer Analysis of Images and Patterns

Y2 - 29 August 2011 through 31 August 2011

ER -

Venkat I, Khader AT, Subramanian KG, De Wilde P. Psychophysically inspired Bayesian occlusion model to recognize occluded faces. In Real P, Diaz-Pernil D, Molina-Abril H, Berciano A, Kropatsch W, editors, Computer Analysis of Images and Patterns: 14th International Conference, CAIP 2011, Seville, Spain, August 29-31, 2011, Proceedings, Part I. Springer. 2011. p. 420-426. (Lecture Notes in Computer Science). doi: 10.1007/978-3-642-23672-3_51

Psychophysically inspired Bayesian occlusion model to recognize occluded faces

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this