원문정보
초록
영어
Medical images have become the recent key investigation tools for medical diagnosis and treatment planning. Due to the advent of digital imaging the need of data storage and retrieval of medical images increased rapidly. Some difficulties in retrieving the medical images are: medical images have only intensity images that carry less information, more noise and records of medical images are large and complex to analyze. To address these problems the present work proposes a novel scheme based on Texture Unit. The proposed scheme reduces texture unit values from 0 to 6561 to 0 to 255 based on Lag values. The Similarity measures are extracted on both schemes and a good comparison is made. The experimental results on MRI images indicate reliability, feasibility and efficacy of the proposed method.
목차
1. Introduction
1.1 Medical CBIR
2. Feature Extraction and Representation
2.1 The Texture
3. Methodology
3.1Texture Unit and Texture Spectrum
3.2 Proposed methods for Texture Unit and Texture Spectrum
4. Experimental Results
5. Conclusions
References