High Impact Factor : 4.396 icon | Submit Manuscript Online icon |

Improved Face Annotation in Personal Photo Shared on OSN using Collaborative Face Reorganization


Jyoti H. Jadhav , Dr. D. Y. Patil School of Engineering, Pune; Pankaj Agarkar, Dr. D. Y. Patil School of Engineering, Pune


Collaboration, face annotation, face reorganization, online social network, social context


User share and access the large volume of information on social networking sites like Facebook, Flicker. Face annotation for effective management of personal photos in online social networks (OSNs) is currently of considerable practical interest. The existing OSNs only support manual face annotation, a task that can be considered time-consuming and labor-intensive. We propose a collaborative face recognition (FR) framework, to improving the accuracy of face annotation. The accuracy of face annotation is improved by effectively making use of multiple FR engines available in an OSN. The collaborative FR framework consists of two major parts: selection of FR engines and merging (or fusion) of multiple FR results. In selection of FR engines it determines a set of personalized FR engines that are suitable for recognizing query face images belonging to a particular member of the OSN. For this purpose, it uses both social network context in an OSN and social context in personal photo collections. There are two solutions for merging FR results, traditional techniques for combining multiple classifier results. Experiments were conducted using 547 991 personal photos collected from an existing OSN. The results demonstrate that the proposed collaborative FR method is able to significantly improve the accuracy of face annotation, compared to conventional FR approaches that only make use of a single FR engine. Also the collaborative FR framework has a low computational cost and comes with a design that is suited for deployment in a decentralized OSN

Other Details

Paper ID: IJSRDV4I50360
Published in: Volume : 4, Issue : 5
Publication Date: 01/08/2016
Page(s): 583-588

Article Preview

Download Article