• Dr. Sachin S Agrawal
• Prof. R. S. Jaiswal

Feature extraction is very difficult with medical images since it contains lot of information. Computer-aided diagnosis helps in extracting useful information from medical images to make diagnosis decision easier and quicker. Application of image processing technologies plays a pivotal role in analysis and feature extraction of medical images. One of the most important and challenging task in image processing is extraction of objects from images. In order to study their shapes, characterize them and process them, another challenge is to extract their contour and boundaries. In proposed approach, we are going to introduce more effective and efficient method to extract objects in an image. This paper aims at identifying the methods and tools for evaluation of segmentation algorithms. The study of similarity-based and discontinuity-based segmentation algorithms is carried out and new approach based on global & local region information for segmentation is proposed. The primary goal of this research is to provide a new methodology to aid the analysis and feature extraction of images. The proposed approach works better in terms of performance and efficiency than existing segmentation algorithms. For calculating various metrics and comparing the existing and proposed approach experimentation needs to be done, which require a large amount of data. This experimentation is done with ultrasound images dataset. The comparative analysis and comprehensive study shows that proposed approach puts forward for better performance among the other comparative algorithms..

Feature extraction, similarity-based discontinuity-based

"Performance Evaluation of Segmentation Algorithms for Medical Image Analysis", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 7, page no.262-271, July-2018, Available :http://www.jetir.org/papers/JETIR1807A39.pdf

"Performance Evaluation of Segmentation Algorithms for Medical Image Analysis", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 7, page no. pp262-271, July-2018, Available at : http://www.jetir.org/papers/JETIR1807A39.pdf