Pit Pattern Classification of Zoom-Endoscopical Colon Images Using DCT and FFT

Author

Häfner, Michael ; Brunauer, Leonhard ; Payer, Hannes ; Resch, Robert ; Wrba, Friedrich ; Gangl, Alfred ; Vécsei, Andreas ; Uhl, Andreas

Author_Institution

Vienna Med. Univ., Vienna

fYear

2007

fDate

20-22 June 2007

Firstpage

159

Lastpage

164

Abstract

This work presents a classification approach for images taken from magnifying colonoscopy. Classification is done according to the pit pattern scheme. Images are not classified directly in the proposed classifier. Instead, they are transformed to a frequency domain using discrete cosine or Fourier transformation. Feature selection is optimized using a genetic algorithm, the actual classification is done using standard methods from statistical pattern recognition (a Bayes normal classifier).

Keywords

Bayes methods; Fourier transforms; discrete cosine transforms; endoscopes; feature extraction; genetic algorithms; image classification; Bayes normal classifier; Fourier transformation; colon images; colonoscopy; discrete cosine transformation; feature selection; genetic algorithm; pattern recognition; pit pattern classification; zoom endoscopy; Biomedical imaging; Cancer; Colon; Colonic polyps; Colonoscopy; Discrete cosine transforms; Endoscopes; Lesions; Medical diagnostic imaging; Pattern classification;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer-Based Medical Systems, 2007. CBMS '07. Twentieth IEEE International Symposium on

Conference_Location

Maribor

ISSN

1063-7125

Print_ISBN

0-7695-2905-4

Type

conf

DOI

10.1109/CBMS.2007.85

Filename

4262643