In this paper, we propose an improved whale search optimization technique for ovarian tumor segmentation in ultrasound images. First, we collect the feature from input images and extract to improve the quality of training data set which extracted from each of the images as the low-level texture features. Second, we introduce an improved whale search optimization technique for segmentation and cascaded as one fusion feature that can represent both the semantic context and the texture patterns distributed in the image. The proposed design is implemented in MATLAB tool and the performance is compare with the existing state-of-art techniques. The performance comparison shows the effectiveness of proposed design over existing segmentation designs.

K. Srilatha

Papers

Images using Improved Whale Search Optimization Technique