Unconstrained face identification with multi-scale block-based correlation

Jack Gaston, Ming Ji, Danny Crookes

Research output: Chapter in Book/Report/Conference proceedingConference contribution

127 Downloads (Pure)


Many approaches to unconstrained face identification exploit small patches which are unaffected by distortions outside of their locality. However, small patches have limited discriminative ability, making accurate patch matching difficult. We propose a novel blockbased approach to exploit the greater discriminative information in larger areas, while maintaining robustness to local variations. A testing block contains several neighbouring testing patches. We identify all the matching training patches in a block jointly, using normalized cross correlation (NCC), as a means of reducing the uncertainty of each matching patch with the addition of the neighbouring patch information. We further propose a multi-scale extension in which we carry out block-based matching at several block sizes, where a larger block contains more neighbouring testing patches, to combine complementary information across scales for further robustness. For evaluation, we use two unconstrained datasets, cropped Labelled Faces in the Wild (LFWCrop) and Unconstrained Facial Images (UFI). Our new approach is able to significantly improve identi- fication accuracy over existing patch-based methods, in the presence of uncontrolled pose, expression and lighting variations. 
Original languageEnglish
Title of host publicationProceedings of the 2017 IEEE International Conference on Acoustics, Speech and Signal Processing
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages5
ISBN (Electronic)ISSN: 2379-190X
ISBN (Print)978-1-5090-4117-6
Publication statusPublished - 09 Mar 2017
Event The 42nd IEEE International Conference on Acoustics, Speech and Signal Processing: ICASSP2017 - New Orleans, United States
Duration: 05 Mar 201709 Mar 2017


Conference The 42nd IEEE International Conference on Acoustics, Speech and Signal Processing
CountryUnited States
CityNew Orleans
Internet address

Fingerprint Dive into the research topics of 'Unconstrained face identification with multi-scale block-based correlation'. Together they form a unique fingerprint.

Cite this