CONCLUSIONS
This research work involves using SVM and SVM-KNN to classify the input sample image into normal image or abnormal image. Experimental outcome show the effectiveness of the two models. SVM with Quadratic kernel achieves maximum of 96% classification accuracy and Hybrid classifier (SVM-KNN) achieves 98% classification accuracy rate on the same test set. We conclude that SVM-KNN TABLE II gives better accuracy rate than the SVM TABLE I.