Color Based Properties Query for CBIR

These days there are millions of digital images stored in image database. People will take a lot of time to find the right image for their query. Similarly, using keyword image retrieval may produce wrong result due to incorrect annotation. An image retrieval system is one of the tools that can be used for searching and retrieving images from a large database of digital images. In general, images features (color, texture, shape) are extracted to represent the images. This project focuses on color image features by applying global color histogram matching technique for HSV color space. The CBIR system is tested through query image of about 100 images from database. The retrieval obtained was good. From the result of precision and recall, we suggest some importing to consider for the future research.