干旱区生态环境知识资源中心

This paper presents a new feature descriptor for biomedical image indexing and retrieval. A local neighboring binary pattern (LNBP) is proposed based on the difference of grey values in local neighborhood. LNBP is computed by comparing the difference of grey values of neighboring pixels with grey value of middle pixel for a given reference pixel in an image. The proposed method captured all directional edge information by computing all local neighbors in a clockwise direction. The computational time is reduced significantly. The effectiveness of the proposed method has been tested on three well-known databases: Open access series of imaging studies (OASIS) MRI, Emphysema-CT and NEMA-CT. The average retrieval precision (ARP) and average retrieval rate (ARR) are used to evaluate the performance of the proposed system. It has been observed from the experimental results that the performance of proposed method outperform the well-known existing methods.