Eye Detection Using Composite Cross-Correlation

Abstract

This study presents a new eye detection method depending on composite template matching for facial images. The objective of this study is to utilize template match method to detect the eyes from given images and to improve this method to obtain higher rate of detection. The idea of our method is to integrate cross correlations of various eye templates. Thus, the correct values of single template matching based eye detection dominated the final output. It also contributed to the re-correct the detection in the event of failure of all single templates. The study also presents a method to obtain candidate eye pixels which contribute to abbreviate the time required to implement up to 91%. The formula of composite cross correlation has been generalized taking into account the differences between the sizes, shifts and irregular single templates. The experiments applied on PICS database reported 98.76% as eye detection rate

Eye Detection based on Viola & Jones Detector, Skin Color, and Eye Template

“…Template-matching methods [16,17]: Among the eye detection methods based on template matching, there is the method proposed by F. Rehab et al, [17] uses a deformable template (the template size and the rotation angle are adjusted to find the search area that best fits the reference template) and a matching algorithm based on the normalized cross-correlation coefficient (NCC) and particle swarm optimization (PSO). [18][19][20]: The method of eye detection presented by Jiatao Song et al, [18] starts with: Extracting the edge binary images from the grayscale image based on a multi-resolution wavelet transformation, extracting regions and eye segments from the binary image, and the location of the eye using light points and intensity information.…”

“…To overcome these problems, various techniques have been developed in recent years and can be divided into four categories [14,15]: Template -matching methods, feature-based methods, appearance-based methods, and hybrid methods. In template-matching methods [16,17], an eye template is constructed and then compared with the different regions of the image to determine those that are the eyes. These methods are easy and quick, but they cannot be treated with eye variations in the scale, expression, rotation and lighting.…”

Localizing Uterus Region from Low-Resolution Ultrasonography Device Using Template Matching Method

“…Different experiments were conducted to analyse the behaviour of these methods and to define which method performs better in artificially generated images. Nanaa [6] proposed a new eye detection method depending on composite template matching for facial images. The objective of this study was to utilize template matching method to detect the eyes from given images and to improve this method to obtain higher rate of detection.…”