Medical Image Retrieval Based on Shape Features in DCT Domain

Abstract

Compressed medical images are widely used in clinical teaching and diagnosis. To save computing cost and storage spaces, research on compressed medical image retrieval is meaningful. This paper proposes a novel medical image retrieval scheme in DCT (Discrete Cosine Transformation) compressed domain. We firstly obtain the multi resolution image by reorganizing the DCT coefficients, then, segment the medical image’s ROI (Region of Interest) and acquires the shape binary image in DCT compressed domain. We use Hu invariant moments to extract shape feature vectors, and measure the similarity by weighting method. Experiments were carried out on an image database which contains 1000 medical CT images. The experimental results show that this algorithm can correctly extract shape features of ROI and get good retrieval performance on JPEG medical images.

DOI : http://dx.doi.org/10.11591/telkomnika.v12i2.4413