Evaluation of Euclidean and Manhanttan metrics in Content Based Image Retrieval system

Content-Based Image Retrieval is used nowadays for generating signatures of images in databases and then comparing these stored signatures with the signature of the query image. In this paper color histogram is used as signature of an image and used to compare two images based on Manhattan distance (L1 norm) and Euclidean distance (L2 norm) distance metrics..In this paper, Corel database is used to evaluate the performance of Manhattan and Euclidean distance metrics. The experimental results showed that Manhattan showed better precision rate than Euclidean distance metric. The evaluation is made using Content based image retrieval application developed using color moments of the Hue, Saturation and Value(HSV) of the image and Gabor descriptors are adopted as texture features.