నైరూప్య

Review of Logo Matching & Recognition System Based On Context Dependency

Ku. Prachi Jivan Dikey

In this paper we present a framework for logo retrieval in images and videos. The wide range application of visual data from Companies, Institution, Individuals and Social system like Flickr, YouTube is for diffusion and sharing of images and Video. There are several issues in processing visual data from an image which was corrupted by noise or subjected to any transformation and also its accuracy in matching Logos are some of the emerging research issues currently. To overcome these problem we have proposed a new class of similarities based on Context Dependent algorithm which enhances the performance in terms of accuracy in logo matching and computation time. Through this paper, the design of Logo matching and recognition which is important for brand advertising and surveillance applications is proposed. It discovers either improper or non-authorized use of logos. Reference logos and test images are seen as constellations of local features (interest points, regions, etc.) and matched by minimizing an energy function mixing: 1) a fidelity term that measures the quality of feature matching 2) a neighborhood criterion that captures feature co-occurrence/geometry 3) a regularization term that controls the smoothness of the matching solution. Context is a collection of interest points and Context Dependent Similarity Matrix is created to find interest point correspondences between two images in order to tackle logo detection.