Published Paper Details:

Worldwide, colon cancer is among the top causes of cancer-related fatalities. Accurately identifying and classifying colon cancer early on may significantly improve patient outcomes. In recent years, image analysis has shown promise as a technique for locating and categorizing malignant tissues in the colon. The purpose of this research is to assess methods for visual colon cancer detection and classification. As part of the study technique, samples of both malignant and non-cancerous colon tissues were used to create a collection of picture data. Several preprocessing; methods, including color normalization and picture enhancement, are used to improve image quality. Utilizing techniques like texture analysis and morphological procedures, discriminative characteristics are derived from the photos. Several classification methods, such as support vector machines SVM random forests and PSO ( particle swarm optimization ), are used to categorize the photos into noncancerous groups.