Transfer Between Pose and Illumination Training in Face Recognition

This source preferred by Changhong Liu

This data was imported from PubMed:

Authors: Liu, C.H., Bhuiyan, M.A.-A., Ward, J. and Sui, J.

Journal: J Exp Psychol Hum Percept Perform

Volume: 35

Issue: 4

Pages: 939-947

ISSN: 0096-1523

DOI: 10.1037/a0013710

The relationship between pose and illumination learning in face recognition was examined in a yes-no recognition paradigm. The authors assessed whether pose training can transfer to a new illumination or vice versa. Results show that an extensive level of pose training through a face-name association task was able to generalize to a new illumination (Experiments 1 and 3), but an equal level of illumination training failed to generalize to a new pose (Experiment 2). The transfer of pose training was likely to depend on a relatively extensive level of training because the same faces with reduced level of exposure (Experiment 4) were unable to reproduce the transfer effect. The findings suggest that generalization of pose training may be extended to different types of image variation, whereas generalization of illumination training may be confined within the trained type of variation.

This data was imported from Scopus:

Authors: Liu, C.H., Bhuiyan, M.A.A., Ward, J. and Sui, J.

Journal: Journal of Experimental Psychology: Human Perception and Performance

Volume: 35

Issue: 4

Pages: 939-947

ISSN: 0096-1523

DOI: 10.1037/a0013710

The relationship between pose and illumination learning in face recognition was examined in a yes-no recognition paradigm. The authors assessed whether pose training can transfer to a new illumination or vice versa. Results show that an extensive level of pose training through a face-name association task was able to generalize to a new illumination (Experiments 1 and 3), but an equal level of illumination training failed to generalize to a new pose (Experiment 2). The transfer of pose training was likely to depend on a relatively extensive level of training because the same faces with reduced level of exposure (Experiment 4) were unable to reproduce the transfer effect. The findings suggest that generalization of pose training may be extended to different types of image variation, whereas generalization of illumination training may be confined within the trained type of variation. © 2009 American Psychological Association.

This data was imported from Web of Science (Lite):

Authors: Liu, C.H., Bhuiyan, M.A.-A., Ward, J. and Sui, J.

Journal: JOURNAL OF EXPERIMENTAL PSYCHOLOGY-HUMAN PERCEPTION AND PERFORMANCE

Volume: 35

Issue: 4

Pages: 939-947

eISSN: 1939-1277

ISSN: 0096-1523

DOI: 10.1037/a0013710

This data was imported from Europe PubMed Central:

Authors: Liu, C.H., Bhuiyan, M.A., Ward, J. and Sui, J.

Journal: Journal of experimental psychology. Human perception and performance

Volume: 35

Issue: 4

Pages: 939-947

eISSN: 1939-1277

ISSN: 0096-1523

The relationship between pose and illumination learning in face recognition was examined in a yes-no recognition paradigm. The authors assessed whether pose training can transfer to a new illumination or vice versa. Results show that an extensive level of pose training through a face-name association task was able to generalize to a new illumination (Experiments 1 and 3), but an equal level of illumination training failed to generalize to a new pose (Experiment 2). The transfer of pose training was likely to depend on a relatively extensive level of training because the same faces with reduced level of exposure (Experiment 4) were unable to reproduce the transfer effect. The findings suggest that generalization of pose training may be extended to different types of image variation, whereas generalization of illumination training may be confined within the trained type of variation.

The data on this page was last updated at 04:53 on December 15, 2018.