Face recognition with occlusion using Dynamic Image-to-Class Warping (DICW)

Xingjie Wei, Chang Tsun Li, Yongjian Hu

Research output: Book chapter/Published conference paperConference paper

16 Citations (Scopus)

Abstract

A novel approach Dynamic Image-to-Class Warping (DICW) is proposed to deal with partially occluded face recognition in this work. An image is partitioned into sub-patches, which are then concatenated in the raster scan order to form a sequence. A face consists of forehead, eyes, nose, mouth and chin in a natural order and this order does not change despite occlusion or small rotation. Thus, in this work, a face is represented by the aforementioned sequence which contains the order of facial features. Taking the order information into account, DICW computes the distance between a query face and an enrolled person by finding the optimal alignment between the query sequence and all sequences of that person along both time dimension and within-class dimension. Extensive experiments on public face databases with various types of occlusion have verified the effectiveness of the proposed method. In addition, our method, which considers the inherent structure of the face, performs with greater consistency than current methods when the number of enrolled images per person is limited. Our method does not require any training process and has a low computational cost, which makes it applicable for real-world FR applications.
Original languageEnglish
Title of host publicationProceedings of the 2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition
Subtitle of host publicationFG 2013
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages1-6
Number of pages6
ISBN (Print)9781467355452
DOIs
Publication statusPublished - 2013
EventIEEE International Conference on Automatic Face and Gesture Recognition - Majesty Plaza Hotel, Shanghai, China
Duration: 22 Apr 201326 Apr 2013
Conference number: 10th
http://fg2013.cse.sc.edu/ (Conference website)

Conference

ConferenceIEEE International Conference on Automatic Face and Gesture Recognition
CountryChina
CityShanghai
Period22/04/1326/04/13
Internet address

Fingerprint

Face recognition
Costs
Experiments

Cite this

Wei, X., Li, C. T., & Hu, Y. (2013). Face recognition with occlusion using Dynamic Image-to-Class Warping (DICW). In Proceedings of the 2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition: FG 2013 (pp. 1-6). [6553747] IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/FG.2013.6553747
Wei, Xingjie ; Li, Chang Tsun ; Hu, Yongjian. / Face recognition with occlusion using Dynamic Image-to-Class Warping (DICW). Proceedings of the 2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition: FG 2013. IEEE, Institute of Electrical and Electronics Engineers, 2013. pp. 1-6
@inproceedings{f8fbc74bd94849a5a0b5f3b50279cfa3,
title = "Face recognition with occlusion using Dynamic Image-to-Class Warping (DICW)",
abstract = "A novel approach Dynamic Image-to-Class Warping (DICW) is proposed to deal with partially occluded face recognition in this work. An image is partitioned into sub-patches, which are then concatenated in the raster scan order to form a sequence. A face consists of forehead, eyes, nose, mouth and chin in a natural order and this order does not change despite occlusion or small rotation. Thus, in this work, a face is represented by the aforementioned sequence which contains the order of facial features. Taking the order information into account, DICW computes the distance between a query face and an enrolled person by finding the optimal alignment between the query sequence and all sequences of that person along both time dimension and within-class dimension. Extensive experiments on public face databases with various types of occlusion have verified the effectiveness of the proposed method. In addition, our method, which considers the inherent structure of the face, performs with greater consistency than current methods when the number of enrolled images per person is limited. Our method does not require any training process and has a low computational cost, which makes it applicable for real-world FR applications.",
author = "Xingjie Wei and Li, {Chang Tsun} and Yongjian Hu",
year = "2013",
doi = "10.1109/FG.2013.6553747",
language = "English",
isbn = "9781467355452",
pages = "1--6",
booktitle = "Proceedings of the 2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States",

}

Wei, X, Li, CT & Hu, Y 2013, Face recognition with occlusion using Dynamic Image-to-Class Warping (DICW). in Proceedings of the 2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition: FG 2013., 6553747, IEEE, Institute of Electrical and Electronics Engineers, pp. 1-6, IEEE International Conference on Automatic Face and Gesture Recognition, Shanghai, China, 22/04/13. https://doi.org/10.1109/FG.2013.6553747

Face recognition with occlusion using Dynamic Image-to-Class Warping (DICW). / Wei, Xingjie; Li, Chang Tsun; Hu, Yongjian.

Proceedings of the 2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition: FG 2013. IEEE, Institute of Electrical and Electronics Engineers, 2013. p. 1-6 6553747.

Research output: Book chapter/Published conference paperConference paper

TY - GEN

T1 - Face recognition with occlusion using Dynamic Image-to-Class Warping (DICW)

AU - Wei, Xingjie

AU - Li, Chang Tsun

AU - Hu, Yongjian

PY - 2013

Y1 - 2013

N2 - A novel approach Dynamic Image-to-Class Warping (DICW) is proposed to deal with partially occluded face recognition in this work. An image is partitioned into sub-patches, which are then concatenated in the raster scan order to form a sequence. A face consists of forehead, eyes, nose, mouth and chin in a natural order and this order does not change despite occlusion or small rotation. Thus, in this work, a face is represented by the aforementioned sequence which contains the order of facial features. Taking the order information into account, DICW computes the distance between a query face and an enrolled person by finding the optimal alignment between the query sequence and all sequences of that person along both time dimension and within-class dimension. Extensive experiments on public face databases with various types of occlusion have verified the effectiveness of the proposed method. In addition, our method, which considers the inherent structure of the face, performs with greater consistency than current methods when the number of enrolled images per person is limited. Our method does not require any training process and has a low computational cost, which makes it applicable for real-world FR applications.

AB - A novel approach Dynamic Image-to-Class Warping (DICW) is proposed to deal with partially occluded face recognition in this work. An image is partitioned into sub-patches, which are then concatenated in the raster scan order to form a sequence. A face consists of forehead, eyes, nose, mouth and chin in a natural order and this order does not change despite occlusion or small rotation. Thus, in this work, a face is represented by the aforementioned sequence which contains the order of facial features. Taking the order information into account, DICW computes the distance between a query face and an enrolled person by finding the optimal alignment between the query sequence and all sequences of that person along both time dimension and within-class dimension. Extensive experiments on public face databases with various types of occlusion have verified the effectiveness of the proposed method. In addition, our method, which considers the inherent structure of the face, performs with greater consistency than current methods when the number of enrolled images per person is limited. Our method does not require any training process and has a low computational cost, which makes it applicable for real-world FR applications.

UR - http://www.scopus.com/inward/record.url?scp=84881504140&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84881504140&partnerID=8YFLogxK

U2 - 10.1109/FG.2013.6553747

DO - 10.1109/FG.2013.6553747

M3 - Conference paper

AN - SCOPUS:84881504140

SN - 9781467355452

SP - 1

EP - 6

BT - Proceedings of the 2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition

PB - IEEE, Institute of Electrical and Electronics Engineers

ER -

Wei X, Li CT, Hu Y. Face recognition with occlusion using Dynamic Image-to-Class Warping (DICW). In Proceedings of the 2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition: FG 2013. IEEE, Institute of Electrical and Electronics Engineers. 2013. p. 1-6. 6553747 https://doi.org/10.1109/FG.2013.6553747