Comparison of Local Binary Pattern Variants for Ultrasound Kidney Image Retrieval

Abstract Local Binary Pattern (LBP) is a simple yet very efficient texture operator which labels the pixels of an image by threshold the neighbourhood of each pixel and considers the result as a binary number. Due to its discriminative power and computational simplicity, LBP texture operator has become a popular approach in various applications. It can be seen as a unifying approach to the traditionally divergent statistical and structural models of texture analysis. In this paper, the concept of LBP is applied to Ultrasound Kidney Image Retrieval system. For extracting the texture features from ultrasound kidney images the LBP, rotational invariant LBP and centre symmetric LBP operator is used. The performance of ultrasound kidney image retrieval system with LBP operator, Rotational Invariant LBP operator and centre symmetric LBP is compared. The efficiency of the system is measured by Recall and Precision parameters. The experimental results show that the centre symmetric LBP operator gives the better performance for retrieving ultrasound kidney images.