Framework for Forgery Detection in Content Based Image Retrieval System

Nowadays Image retrieval is becomes more challenged thing in many of the fields like medical diagnosis, crime prevention, military services, architectural and engineering design, geographical information, trademark matching, etc. So there is the necessitates of effectively retrieving relevant images when needed. Thus, content-based image retrieval systems (CBIR) have become very popular for browsing, searching and retrieving images from a large database of digital images. So in order to improve the retrieval accuracy, this paper will focus on to use content-based image retrieval systems with kmeans as the clustering algorithm and B+ tree for speeding up the retrieval process. For representing the images, we extract their feature vectors of images using Daubechies’ wavelets. Then we introduced the Zernike moments in the retrieved images with the reference image by that we find out the variations of the images. After that by comparing the images using Zernike moments and find out the forgery between the images.