Efficient Method of Visual Feature Extraction for Facial Image Detection and Retrieval

Abstract

Due to the significant increase in the already huge collection of digital images that we have today, it has become imperative to find efficient methods for the archival and retrieval of these images. In this research, a content based-human facial image detection and retrieval model is proposed for retrieving facial images of humans based on their visual content from an image database. The research proposes a technique of face segmentation based on which a new method of features extraction from the human face is devised. The capability and effectiveness of the color space models (RGB, HSV, and HSI) on facial image retrieval technique are also investigated. Eigenfaces features are used as a domain specific visual content to extract the characteristic feature images of the human facial images, while the color histogram of the facial image is used as a general visual content. Viola-Jones face detection method is employed to obtain the location, extent and dimensions of each face. Moreover, for the measurement of distance and classification purposes, Euclidean distance is utilized. The sample image database consists of 1500 local facial images of one hundred and fifty participants from the University of Malaya (UM), Kuala Lumpur, and some of their friends and families outside the UM. Several experiments based on precision and recall approach were conducted to evaluate the proposed methods. The retrieval result of the facial image given by the proposed method showed excellent improvement comparing to those achieved when using the traditional method of visual features extraction.