期刊名称：International Journal of Advanced Research in Computer Engineering & Technology (IJARCET)
印刷版ISSN：2278-1323
出版年度：2015
卷号：4
期号：5
页码：2405-2408
出版社：Shri Pannalal Research Institute of Technolgy
摘要：Logo detection and recognition are important for brand advertising, and it discovers either improper or non-authorized use of logos. It is a difficult task to match because noise and unclear image greatly complicate the task. To solve this problem, Scale Invariant Feature Transform (SIFT) is used. In the proposed system, Artificial Neural Network (ANN) is used along with SIFT to provide both accuracy and performance. SIFT can robustly identify partial occlusion and illumination changes of the logo. The ANN is used in the training phase in order to classify the logo. In pre-processing stages, noise removal and image enhancement are applied to deliver an image with optimal quality and clarity. The image features are extracted from reference logo and input logo. Further Context extraction is done to get the logo parameter and transform the logo into binary representation. The genuine logo is identified by matching the input logo and trained logo.
