Pit Pattern Classification of Zoom-Endoscopical Colon Images using Evolved Fourier Feature Vectors

This work describes an experimental study on the classification of images taken from colonoscopy. An emphasis is devoted to the procedure of finding features which allow an adequate classification. The proposed approach applies filters to the images' respective Fourier domains. Good configurations of these filters are obtained using a genetic algorithm, since the complexity of the configuration space is too high to find the optimum in reasonable time. The actual classification is done according to the pit pattern scheme and uses standard methods from statistical pattern recognition.