Performance Evaluation of Image Retrieval System using Non-parametric Techniques

This paper considered performance of content based image retrieval system using image representation nonparametric algorithms. Performance comparison of Epanechnikov, Gaussian and Histogram non-parametric algorithms was done in a generic image retrieval system. Chan & Vese and Cosine Angle Distance algorithms were used for segmentation and similarity matching respectively. The performance of the non-parametric techniques was measured using recall-precision curve and the Bull’s Eye performance score. The experimental results showed that estimating techniques performed better than the absolute value technique. The study then looked at the limitations of these techniques.