Title :
Research on medical image retrieval based on texture feature
Author :
Wang Mingquan ; Cai Guohua ; Zhang Shi
Author_Institution :
Coll. of Inf. Sci. & Eng., Northeastern Univ., Shenyang, China
Abstract :
Feature extraction is one of the most important steps in content-based medical image retrieval (CBMIR). In this paper, we propose a new method of improved Gray Level Co-occurrence Matrix (GLCM). In this method, we apply the Gradient Phase Mutual Information (GP-MI) combined with the method of masked image to overcome the shortcoming that the traditional GLCM is impacted greatly by the rotation angle and the background region. The method of GP-MI is applied to compute the angle between two images and the method of masked image is applied to remove the background of the image. After these two steps, we divide the image into several blocks equally and calculate the GLCM of every block. Then we sum the GLCM of every block by different weights as the final texture feature. Lastly medical image retrieval was executed according to the similarity calculation. The results of the test indicate that the proposed method has a promising effect.
Keywords :
content-based retrieval; feature extraction; image retrieval; image texture; matrix algebra; medical image processing; CBMIR; GLCM; GP-MI; background region; content-based medical image retrieval; feature extraction; gradient phase mutual information; gray level cooccurrence matrix; masked image; rotation angle; texture feature; Computed tomography; Educational institutions; Feature extraction; Image retrieval; Medical diagnostic imaging; Mutual information; gradient phase mutual information; gray level co-occurrence matrix; masked image; medical image retrieval; texture feature;
Conference_Titel :
Signal Processing, Communication and Computing (ICSPCC), 2012 IEEE International Conference on
Conference_Location :
Hong Kong
Print_ISBN :
978-1-4673-2192-1
DOI :
10.1109/ICSPCC.2012.6335699