Content-based histology image retrieval systems have shown great potential in supporting decision making in clinical activities, teaching, and biological research. In content-based image retrieval, feature combination plays a key role.
It aims at enhancing the descriptive power of visual features corresponding to semantically meaningful queries. The images format in the database is RGB format and due to colour changes of the image affected by illumination especially for outdoor image acquisition, so RGB model gives different values in different environment that may reduce the retrieval performance but HSV model gives more stability to that affect since the colour information of HSV space is distributed separately from the illumination part in different channels.
The performance of the image retrieval is differentiated by different wavelet transforms because they provide the image information more effectively and GLCM is an old and classic method used to describe the texture in variety of image recognition fields. GLCM is useful since it can contain three major elements, texture information, histogram information and edge information. GLCM provides the rules that gray scale of a pair of pixels appears in a certain distance away in a certain direction. Finally, a practical results show the better retrieval performance based on wavelet, K-means cluster and GLCM features.
Herein, we? propose the definition of feature vectors using the Local Binary Pattern (LBP)? operator. A study was performed in order to determine the optimum LBP variant? for the general definition of image feature vectors. The chosen LBP variant is then? subsequently used to build an ultrasound image database, and a database with? images obtained from Wireless Capsule Endoscopy.
The image indexing process is? optimized using data clustering techniques for images belonging to the same class.? Finally, the proposed indexing method is compared to the classical indexing Technique, which is nowadays widely used.