MyFinder: near-duplicate detection for large image collections

The explosive growth of multimedia data poses serious challenges to data storage, management and search. Efficient near-duplicate detection is one of the required technologies for various applications. In this paper, we introduce MyFinder, an image near-duplicate detection system for large image collections. MyFinder consists of three major components: 1) a local-feature-based image representation utilizing the proposed LDP (Local-Difference-Pattern) feature, 2) the Locality-Sensitive-Hashing (LSH) as the core indexing structure to assure the most frequent data access occurred in the main memory, and 3) multi-step verification for queries to best exclude false positives and to increase the precision. Categories and Subject Descriptors: I.4.9 [Image Processing and Computer Vision]: Application General Terms: Algorithms, Experimentation Keywords Near-Duplicate Detection, Image Feature, Database Retrieval

• Type: Conference
• Year: 2009
• Where: MM
• Authors: Xin Yang, Qiang Zhu, Kwang-Ting Cheng
• Keywords: Image, Image Near-duplicate Detection, MM 2009, Near-duplicate Detection