A novel illumination normalization method based on local relation map

Lian, Zhichao; Er, Meng Joo; Li, Juekun

doi:10.1109/iciea.2012.6360731

Cited by 1 publication

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides ASR, GRF, WF, LN, and NLM mentioned above, the famous LBP [37], [38], its improved versions [39], [40], the recently proposed LRM [41], and OLHE [43] also adopt the local operation. They all describe the relations between neighboring pixels for illumination insensitive representation.…”

Section: Discussionmentioning

confidence: 99%

Analysis of Noteworthy Issues in Illumination Processing for Face Recognition

Yao

Nagahashi

2015

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYFace recognition under variable illumination conditions is a challenging task. Numbers of approaches have been developed for solving the illumination problem. In this paper, we summarize and analyze some noteworthy issues in illumination processing for face recognition by reviewing various representative approaches. These issues include a principle that associates various approaches with a commonly used reflectance model and the shared considerations like contribution of basic processing methods, processing domain, feature scale, and a common problem. We also address a more essential question-what to actually normalize. Through the discussion on these issues, we also provide suggestions on potential directions for future research. In addition, we conduct evaluation experiments on 1) contribution of fundamental illumination correction to illumination insensitive face recognition and 2) comparative performance of various approaches. Experimental results show that the approaches with fundamental illumination correction methods are more insensitive to extreme illumination than without them. Tan and Triggs' method (TT) using L 1 norm achieves the best results among nine tested approaches.

show abstract