Multi Feature CBIR Model for Trademark Image Distinctiveness
More InformationShow full item record
A Content-Based Image Retrieval (CBIR) system can help in detecting trademark infringement. This paper describes an improvement and extension of previous work for the existing Universal Model for a CBIR system, which only uses texture along with color to produce a reliable and capable system. To enhance the security and efficiency of the CBIR based Universal Model, the extension is a Multi Feature CBIR Model that can utilize many parameters including color, texture, and shape with the facility of choosing a suitable and flexible set of features. The supported selection techniques give priority to individual features and help increase the efficiency of the system. I am going to provide write-ups with the proven computational work over the existing feature methods of the Universal Model, which becomes the foundation for the Multi-Feature CBIR Model. In comparison to the Universal Model, the Multi-Feature CBIR Model can obtain higher recall and precision values.