Active Contours Without Edges and Curvature Analysis for Endoscopic Image Classification.

International Journal of Computer Science and Security

Ravindra Hegadi¹  B.V.Dhandra¹ 

[1] $$

关键词: Active Contours;    Curvature;    Endoscopy;    Jacobi method;    Level sets;   

DOI  :  

来源: Computer Science and Security

【 摘 要 】

Endoscopic images do not contain sharp edges to segment using the traditionalsegmentation methods for obtaining edges. Therefore, the active contours or‘snakes’ using level set method with the energy minimization algorithm isadopted here to segment these images. The results obtained from the abovesegmentation process will be number of segmented regions. The boundary ofeach region is considered as a curve for further processing. The curvature foreach point of this curve is computed considering the support region of each point.The possible presence of abnormality is identified, when curvature of the contoursegment between two zero crossings has the opposite curvature signs to thoseof such neighboring contour segments on the same edge contours. The Knearestneighbor classifier is used to classify the images as normal or abnormal.The experiment based on the proposed method is carried out on 50 normal and50 abnormal endoscopic images and the results are encouraging.

【 授权许可】

Unknown