Segmentation Using Saturation Thresholding and Its Application in Content-Based Retrieval of Images

We analyze some of the visual properties of the HSV (Hue, Saturation and Value) color space and develop an image segmentation technique using the results of our analysis. In our method, features are extracted either by choosing the hue or the intensity as the dominant property based on the saturation value of a pixel. We perform content-based image retrieval by object-level matching of segmented images. A freely usable webenabled application has been developed for demonstrating our work and for performing user queries.

• Type: Conference
• Year: 2004
• Where: ICIAR
• Authors: A. Vadivel, M. Mohan, Shamik Sural, Arun K. Majumdar
• Keywords: Content-based Image Retrieval, ICIAR 2004, Image Segmentation Technique, Saturation Value