Re-INDEXING AND IDENTIFYING NEAR-DUPLICATE IMAGES USING OPTIMIZING TECHNIQUE

S.Thaiyalnayaki; J.Sasikala

Volume : V, Issue : XII, December - 2016

Re-INDEXING AND IDENTIFYING NEAR-DUPLICATE IMAGES USING OPTIMIZING TECHNIQUE

S. Thaiyalnayaki, J. Sasikala

Abstract :

� Image tracking technique is being applied more oadly in fields like robotics, human-computer interaction, security surveillance and other areas in recent years [7-9], it has attracted more and more researchers. As the most important segment of image tracking, the image matching becomes one hot topic in the current field of computer vision. The image matching is that the key point could be recognised between two ro more images by some matching algorithm. The images can use in matching often in different time, different perspectives, different scale. Near duplicates can be a similar copy or differ a little in their visual content. Duplicate images introduce many problems of redundancy and copyright infringement in large set of image collections. This paper proposes a methodology for identifying and then indexing the near duplicate images on web and Re-indexing the near duplicate images. First step is to get the search image from the user and enhance the search image and then Features are extracted from search image as well as using SURF (Speeded up Robust Features) that is to extract the local invariant features of search image. After this calculate the similarity among the features extracted images using same SURF algorithm and then indexing Near duplicate images based on user�s search image using Locality Sensitive Hashing (LSH). And finally optimizing result by Re-indexing the near duplicate images. We demonstrate that our identifying and indexing approach is highly effective for collections of up to a few hundred thousand images.