An Efficient Content-Based Medical Image Retrieval Using Local Vector Pattern

This paper presents image feature extraction and matching framework for image retrieval used in medical image database management and disease diagnosis applications. Since the process of retrieval has facilitated one to find out the required medical image automatically, based on its content, the proposed system is called as Content-Based Medical Image Retrieval (CBMIR) system. The goal of CBMIR system is to enhance visual information analysis by increasing the overall search capabilities to physicians. The proposed system encompasses image feature extraction scheme using Local Vector Pattern (LVP) descriptor and image matching using histogram to retrieve relevant images from a MRI brain images database. The main characteristics of the MRI images are their poor contrast, sensitive to noise and large intensity variations. These challenges are tackled by implementing LVP which was proved as best facial feature extracting approach in the existing system with the first and second order derivatives to improve the recognition performance of the system. Ultimately, results were compared with existing local pattern descriptors such as Local Binary Pattern (LBP), Local Derivative Pattern (LDP) and Local Tetra Pattern (LTrP). We proved that an average recognition rate obtained for implementing LVP in medical image database is better than the other state-of-the-art local pattern descriptor techniques.