IRJET-ANALYZING GUIDANCE INFORMATION USING RANDOM FORESTS FOR THERAPEUTIC IMAGE SEGMENTATION PROCESS (original) (raw)

Labeled training data be used for challenging medical image segmentation problems to learn different characteristics of the relevant domain. The Random Forest (RF) classifiers and their learned knowledge during training and ways to exploit it for improved image segmentation. Apart early learning discriminative features, RFs also quantify their importance in classification. Feature importance is use to design a feature selection strategy critical for high segmentation and classification accuracy, and also to propose a efficiency cost in a second-order MRF framework for graph cut segmentation. The cost function combines the contribution of different image skin texture like intensity, texture, and curving information. Experimental outcome on medical images show that this strategy leads to better segmentation accuracy than conventional graph cut algorithms that use only intensity information in the smoothness cost.