Title :
A new filter for feature extraction of line pattern texture with application to cancer detection
Author :
Hasegawa, Jun-ichi ; Toriwaki, Jun-ichiro
Author_Institution :
Dept. of Comput. Sci., Chukyo Univ., Toyota, Japan
fDate :
30 Aug-3 Sep 1992
Abstract :
Proposes a nonlinear filter for extracting local features of linear texture patterns. This filter calculates at each pixel the degree of local concentration of line patterns based upon a new measure called the concentration index. Basic properties of this measure are shown both theoretically and experimentally, and the filter is applied to detection of cancer lesions from stomach X-ray images
Keywords :
diagnostic radiography; feature extraction; filtering and prediction theory; image texture; medical image processing; cancer detection; cancer lesions; feature extraction; image texture; line patterns; linear texture patterns; nonlinear filter; stomach X-ray images; Application software; Biomedical imaging; Cancer detection; Computer science; Feature extraction; Filters; Image processing; Medical diagnostic imaging; Stomach; X-ray imaging;
Conference_Titel :
Pattern Recognition, 1992. Vol.III. Conference C: Image, Speech and Signal Analysis, Proceedings., 11th IAPR International Conference on
Conference_Location :
The Hague
Print_ISBN :
0-8186-2920-7
DOI :
10.1109/ICPR.1992.201997
