Liver CT-image retrieval based on Gabor texture.

Gabor schemes of image representation have shown great success in many texture related computer vision applications. This is mainly because the primitives of image representation in vision have a wavelet form similar to Gabor elementary functions (GEF's). We use Gabor approach to analyze the texture of liver CT-images and extract the corresponding feature vectors. Then, the feature vectors are used to facilitate content-based image retrieval (CBIR). In experiments, a batch of liver CT images containing several types of CT findings is collected, and retrieval results by Gabor texture are present.