Medical Image Retrieval Based on Semantic of Neighborhood Color Moment Histogram

Content-based medical image retrieval is getting more and more importance in aspect of clinical assistant diagnose. This paper in allusion to gastroscopic images, make use of latent semantic indexing technology to implement image retrieval which based on its semantic information. First extract image's histogram of neighborhood color moments of low-level features, and then use normalizing, term weighting and singular value decomposition to realize low-level features mapping into high-level semantic features. In this way, the retrieval results will be more in accordance with the doctor's comprehension of the image's semantic content. The experimental results according to the prototype system show that the approach proposed in the paper could improve the retrieval performance steadily.