Making People's Life Much Easier by Effective Face Image Retrieval from the Popular Online Social Network such as Facebook

Abstract

The primary objective of this paper is to make people's life much easier by retrieving images containing faces of the same person appearing in the query image, from the popular online social network like Facebook (web-scale image database) containing millions of face images effectively and accurately. In this work face image of a person will be used as a query image to retrieve images of the same person with various poses, expressions, and illumination. Such face retrieval system has many applications, including name-based face image search, face tagging in images and videos, copyright enforcement, labeling faces in photos from the popular online social network such as Facebook etc. Also, this paper proposes a method for Automatic Image Registration in which pair of images with differences in rotation, translation, and spectral content is registered for remote sensing applications using multisensors. This work identifies that an image edge feature extraction using perceptional organization methods based on the rules of human perception are allowed us to reduce noise and over segmentation problem in image feature extraction. Generic edge tokens are perceptually significant edge features which are descriptive in the representation and therefore can be manipulated qualitatively in supporting perceptional grouping. This paper provided a new technique that can speed up registration (by reducing data) and improve accuracy by selecting a subimage for the registration process based on its ability to provide accurate results and determined a faster method for implementing multi-resolution image registration. The proposed work not only reduces the computation cost of future work, but it also greatly reduces the complexity and confusion caused by over-segmentation.