Paper Details

In today’s growing and competitive world we need more and exactly sure security for our applications. Manyof them including face verification use face image retrieval method. It’s a challenging technique since all the faces willbe similar due to its similar geometrical configuration of face structure. Thus, with the exponentially increasing images,large-scale content-based face image retrieval is an enabling technology for many emerging applications.In our project,we aim to improve content-based face retrieval by constructing semantic codewords for efficient large-scale faceretrieval and for that we utilize automatically detected human attributes that contain semantic cues of the face photos. Incontent based image retrieval we can only retrieve the image using low level features. But in our project we have useattribute-enhanced sparse coding and attribute embedded inverted indexing to retrieve the image using high levelfeatures (hair style, gender, race) and to improve the face retrieval in the offline and online stages.The results show thatthe proposed methods can achieve up to 42 to 43% relative improvement compared to the existing methods.

Prof.P.Gaikwad, Shreekant Sanap, Rohit Jadhav, Sanket Kaware, Pratik Mhasawade, “ADVANCED TECHNIQUE TO RETRIEVE FACE IMAGE BY USING ATTRIBUTE-ENHANCED SPARSE CODEWORDS& INVERTED INDEXING”, International Journal of Advance Engineering and Research Development (IJAERD), Vol. 2, Issue 3, pp. 149-153, March 2015.