Content based mammogram retrieval using biorthogonal wavelet filters in DDSM database

Content-based image retrieval (CBIR) is an active research area over the past few decades. In medical applications like mammogram analysis content based image retrieval techniques helps the radiologists or physicians to access similar images from a large medical database to aid diagnosis. In this paper content-based retrieval of mammograms from DDSM database is performed using fixed, genetic algorithm (GA) based and particle swarm optimization (PSO) based biorthogonal wavelet filters (CDF 9/7). The retrieval performance for large database images are estimated. In this paper, PSO technique is used first time in wavelet filter adaptation and got better results than GA. The results of optimization approaches are comparatively better than fixed wavelet method. In optimization methods PSO gives better results than genetic algorithm.