DocumentCode :
3050521
Title :
Rotation-Invariant Texture Characterization Using Hough and Fourier Transforms
Author :
Xiao, Songshan ; Zhai, Ruizhan ; Wu, Yongxing
Author_Institution :
Coll. of Precision Instrum. & Opto-Electron. Eng., Tianjin Univ., Tianjin
fYear :
2007
fDate :
6-8 July 2007
Firstpage :
841
Lastpage :
844
Abstract :
Texture analysis as a basic issue in medical image processing and content based medical image retrieval (CBMIR) has made great progress during the past few years. The work present in this paper aims to develop a new method to extract the rotation-invariant texture features. In doing so, we use Hough transform to convert the rotation of the image to the translation in the parameter space, then make Fourier transform and eliminate the translation by take the modules of it. The proposed method is also robust to additive white noise. To test and evaluate the method we did some experiments, the results show the feasibility and validity of the proposed method and its robustness to additive white noise.
Keywords :
Fourier transforms; Hough transforms; feature extraction; image retrieval; image texture; medical image processing; Fourier transforms; Hough transforms; additive white noise; content based medical image retrieval; medical image processing; rotation-invariant texture feature; texture analysis; Additive white noise; Biomedical image processing; Biomedical imaging; Content based retrieval; Fourier transforms; Image analysis; Image converters; Image retrieval; Image texture analysis; Noise robustness;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Bioinformatics and Biomedical Engineering, 2007. ICBBE 2007. The 1st International Conference on
Conference_Location :
Wuhan
Print_ISBN :
1-4244-1120-3
Type :
conf
DOI :
10.1109/ICBBE.2007.219
Filename :
4272703
Link To Document :
بازگشت