000082890 001__ 82890
000082890 005__ 20180317093234.0
000082890 037__ $$aREP_WORK
000082890 245__ $$aRobust Features for Frontal Face Authentication in Difficult Image Conditions
000082890 269__ $$a2003
000082890 260__ $$bIDIAP$$c2003
000082890 336__ $$aReports
000082890 520__ $$aIn this report we extend the recently proposed {DCT}-mod2 feature extraction technique (which utilizes polynomial coefficients derived from {2D} {DCT} coefficients obtained from horizontally & vertically neighbouring blocks) via the use of various windows and diagonally neighbouring blocks. We also evaluate enhanced {PCA}, where traditional {PCA} feature extraction is combined with {DCT}-mod2. Results using test images corrupted by a linear and a non-linear illumination change, white Gaussian noise and compression artefacts, show that use of diagonally neighbouring blocks and windowing is detrimental to robustness against illumination changes while being useful for increasing robustness against white noise and compression artefacts. We also show that the enhanced {PCA} technique retains all the positive aspects of traditional {PCA} (that is robustness against white noise and compression artefacts) while also being robust to illumination direction changes; moreover, enhanced {PCA} outperforms {PCA} with histogram equalisation pre-processing.
000082890 6531_ $$alearning
000082890 700__ $$aSanderson, Conrad
000082890 700__ $$0243961$$aBengio, Samy$$g140142
000082890 8564_ $$uhttp://publications.idiap.ch/downloads/reports/2003/rr03-05.pdf$$zURL
000082890 8564_ $$s157778$$uhttps://infoscience.epfl.ch/record/82890/files/rr03-05.pdf$$zn/a
000082890 909CO $$ooai:infoscience.tind.io:82890$$preport$$pSTI
000082890 909C0 $$0252189$$pLIDIAP$$xU10381
000082890 937__ $$aEPFL-REPORT-82890
000082890 970__ $$asanders-rr-03-05/LIDIAP
000082890 973__ $$aEPFL$$sPUBLISHED
000082890 980__ $$aREPORT