Advanced Trends in Logo Matching and Recognition

Abstract

1,2 Department of Electronics and Telecommunication,Dr D Y Patil Institute of Engineering and Technologgy,Pimpri, Pune Abstract—Graphic logos are a special class of visual objects extremely important to determine the identity of something or someone. The main aim of this project is to present a highly effective and scalable framework for matching and recognizing logos from real environment. Given a query image and a large logo database and the goal is to recognize the logo contained in the query, if any. Efficient method presented which is better the existing method in terms of FRR and FAR. In this project we are extending the same method for improved scalability of logo detection and recognition. The recent method of logo detection and recognition is based on the definition of a “ContextDependent Similarity” kernel that directly incorporates the spatial context of local features is under investigation. Formally, the Context Dependent Similarity Kernel function is defined as the fixedpoint of three terms 1) an energy function which balances a fidelity term, 2) a context criterion, 3) an entropy term. In this project we are extending this method further for scalability as well as other rigid, non-rigid logo transformations. The analysis of proposed approach will be developed using MATLAB. During the simulation we will first do comparative analysis proposed Context dependent similarity matching and detection procedure against nearest neighbor SIFT matching, nearest neighbor matching with RANSAC verification so that we can claim the proposed method is best as compared existing once. Second we will evaluate the performance of proposed by considering the scalability factor and compute its precision and recall rate. Keywords— logo recognition, CDS, SIFT, RANSAC.