Spine MR Image Retrieval using Co-Occurrence Matrix and Texture Spectrum

The main objective of content based medical image retrieval (CBMIR) is to efficiently retrieve medical images that are visually similar to a query image. Medical images are usually retrieved on the basis of low level and high level features. This work addresses the concept of texture based spine MR image retrieval in the wavelet compressed domain. We proposed two statistical methods such as Haralick features and texturespectrum for spine MR image features extraction and project them to a set of signatures. The created texture features are classifying, according to various types of spine MR images using k-mean clustering algorithm. Then the research is carried out by calculating the distance between the signatures in the database images and the query image. These methods are applied around 300 spine MR images and improvements of retrieval efficiency were found with usual precision and recall analysis.