ABSTRACT Now a day’s people are mostly affected by tumors. so, the major intend of this paper is to identify the tumor in a body and detecting the nearest area effected and that will be done by using machine learning with region-based energetic contour model, region based active contour model is efficient in dividing images by badly distinct boundaries but frequently not succeed while functional image surrounding intensity in homogeneity. Machine learning approaches are extremely efficient in conducting the homogeneity, but frequently consequences in noises from miss confidential pixels. Therefore, proposed system point out the integration of the machine learning region based active contour of the k-nearest neighbors and the support vector machine with the chanvese technique, and by comparing this result with the traditional technique of chanvese technique. Better exactness, velocity and less compassion to constraint tuning which are being observed in this paper.