ResearchBib Share Your Research, Maximize Your Social Impacts
Sign for Notice Everyday Sign up >> Login

A Survey on Efficient Facial Feature Extraction Technique for Image Annotation

Journal: International Journal of Emerging Trends & Technology in Computer Science (IJETTCS) (Vol.5, No. 1)

Publication Date:

Authors : ; ;

Page : 024-027

Keywords : ;

Source : Downloadexternal Find it from : Google Scholarexternal

Abstract

Abstract With the rapid growth of web photo sharing portals and social networks, massive amounts of images and photos have been uploaded and shared on the Internet. With the great success of social networks and social web sites recently, web users have been highly motivated to share their images with their friends that allow other users to tag and comment on image collections. Nowadays large amount of photos which are shared by users are facial images of human those are available on Internet freely. From all of the facial images some of the images are tagged properly. But many of them are not tagged. This has motivated the study of face annotation automatically. Finding who on personal photos is one of the most promising applications in image annotation. So for that purpose, facial feature extraction techniques are used. In this paper we talk about GIST for feature extraction to improve accuracy of extracted features. Keywords: Face Annotation, feature extraction, label refinement, weak label.

Last modified: 2016-03-08 16:16:56