MODIFIED INTEGRAL PROJECTION METHOD FOR EYE DETECTION USING DYNAMIC TIME WARPING

Face and facial pattern detection is an active research area that is useful for many practical applications. In this paper, we present an innovative technique for eye detection using Augmented Dynamic Time Warping (ADTW) algorithm. Dynamic Time Warping (DTW) is a reliable algorithm that can perform similarity matching between two sequences but it requires supplimnetry techniques to be effective and efficient when used as a pattern detection tool. Therefore, for template matching in a facial pattern detection, the DTW is augmented with proposed image processing strategy along with a proper weighting scheme to increase its efficiency and accuracy. Our proposed ADTW overcomes some of the shortcomings associated with the traditional dynamic time warping and hence improves the alignment of the warping path of the sequences. The results of the implementation of the ADTW to detect eyes in facial images of subject with and without glasses show a marked improvement in detection accuracy when compared with that of the traditional DTW.