Mean Integral and General Projection Functions

525 Words2 Pages

Projection functions are specific types of geometric feature-based approaches that are used in finding intensity variation in an image and extracting the feature vectors. Geng et al. [23] used the variance projection function for iris localization. Despite the wide application of VPF and MIPF (Mean Integral Projection Function), both have their limitations. MIPF will fail when vertical and horizontal summations of the elements in searching area are unchanged, while VPF will fail in case of the same variance and different mean of the elements. Therefore, the landmarks that have relatively high contrast cannot be properly extracted. To overcome these problems, a new projection function which we called General Projection Function (GPF) is proposed by Bastanfard and Dehshibi []. They apply GPF on Iranian Face Database to locate the position of the facial feature points such as the iris, nose, center of lips and chin. In order to increase the accuracy of feature localization in case of occlusions such as glass and scarf Dehshibi et al [] propose a new projection function called Combined P...

Open Document