In this paper a novel fast fuzzy backpropagation algorithm for classification of colon cell images is proposed. The experimental results show that the accuracy of the method is very high. The algorithm is evaluated using 116 cancer suspects and 88 normal colon cells images and results in a classification rate of 96.4%. The method automatically detects differences in biopsy images of the colorectal polyps, extracts the required image texture features and then classifies the cells into normal and cancer respectively. The net function computation is significantly faster. Convergence is quicker. It has an added advantage of being independent of the feature extraction procedure adopted, with knowledge and learning to overcome the sharpness of class characteristics associated with other classifiers algorithms. It can also be used to resolve a situation of in-between classes.
|Title of host publication||Advances in Neural Networks - ISNN 2006|
|Publication status||Published - 2006|
|Name||LECTURE NOTES IN COMPUTER SCIENCE|