Абстрактный

Efficient Content Based Image Retrieval System in Visual Words, Color and Edge Directive Descriptors and Fuzzy Color and Texture Histogram

K. Haridas, Dr. Antony SelvadossThanamani

Content Based Image Retrieval is a challenging method of capturing relevant images from a large storage space. A new low level feature contains histogram, color and texture information. This element is intended for use in image retrieval and image indexing systems. This paper experiments various methods available for Content based image retrieval System, they are precision, recall and accuracy value for Bag of Visual words, Color and Edge Directive Descriptors, Fuzzy Color and Texture Histogram. The methods are implemented and tested based on three parameters like precision value, recall value and Accuracy rate. The Experimental results show that FCTH (Fuzzy Color and Texture Histogram) method is more efficient when comparing with other methods. The FCTH shows 93.21 % accuracy in Content Based Image Retrieval system.