Multi-feature fusion method for medical image retrieval using wavelet and bag-of-features

Abstract

Color, texture, and shape are the common features used for the retrieval systems. However, many medical images have a spot of color information. Therefore, the discriminative texture and shape features should be extracted to obtain a satisfied retrieval result. In order to increase the credibility of the retrieval process, many features can be combined to be used for medical image retrieval. Meanwhile, more features require more processing time, which will decrease the retrieval speed. In this paper, wavelet decomposition is adopted to generate different resolution images. Bag-of-feature, texture, and LBP feature are extracted from three different-level wavelet images. Finally, the similarity measure function is obtained by fusing these three types of features. Experimental results show that the proposed multi-feature fusion method can achieve a higher retrieval accuracy with an acceptable retrieval time. KEYWORDSWord; medical image retrieval; bag-of-feature; texture feature; LBP feature CONTACT Pang Ming

Triplet Contents based Medical Image Retrieval System for Lung Nodules CT Images Retrieval and Recognition Application

“…Clustering process is implemented using multiple SOM. Our proposed work solves the two major limitations [8] of conventional SOM. For all images that are stored in the databases, feature vectors are pre-computed and similar feature vectors of the images are grouped, which are stored in a database.…”

“…Pleural dragging, (7). Bronchial Mucus Plugs (BMP), (8). Air Bronchogram, (9).Obstructive Pneumonia (OP).…”

“…A good image must compose of these two features. Previous solutions are based on visual contents such as color, shape, texture, and other information [7], [8]. However design a fast and accurate CBMIR is a challenging task of today's researchers.…”