Automated Colon Cancer Detection Using Kernel Sparse Representation Based Classifier
Seena Thomas1, Anjali Vijayan2

1Seena Thomas, Assistant Professor, Department of Computer Science and Engineering, Kerala University, Trivandrum (Kerala), India.
2Anjali Vijayan, Department of Computer Science and Engineering, Kerala University, Trivandrum (Kerala), India.

Manuscript received on 15 August 2015 | Revised Manuscript received on 25 August 2015 | Manuscript Published on 30 August 2015 | PP: 317-322 | Volume-4 Issue-6, August 2015 | Retrieval Number: F4252084615/15©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: Colon cancer causes deaths of about half a million people every year. Common method of its detection is histopathological tissue analysis, which correlated to the tiredness, experience, and workload of the pathologist. Researchers have been working since decades to get rid of manual inspection, and to develop trustworthy systems for detecting colon cancer. Lesion detection can be difficult due to low contrast between lesions and normal anatomical structures. Lesion characterization is also challenging due to similar spatial characteristics between the tumor and abnormal nodes. To tackle this problem, Gabor wavelet filter algorithm is proposed. The detection of cancerous tissue in tissue image is divided into three main stages. The feature extraction and selection using the Gabor algorithm plays a critical role in the performance of the classifier. Higher accuracy of the classifier can be also achieved by the selection of optimum feature set. Features like the time (spatial) and frequency information can be extracted by using t-test algorithm and the tunable kernel size allows it to perform multi-resolution analysis.
Keywords: Feature Extraction and Selection, Graph Cut Segmentation, Gabor Filter.

Scope of the Article: Classification