Performance evaluation on segmentation methods for medical images
ACAI '11 Proceedings of the International Conference on Advances in Computing and Artificial Intelligence
| Hi-index | 0.00 |
Segmentation of target is an important step in forming realistic target models. To assist in classifying the relevant literature, two types of segmentation are identified where each type adds its own additional level of uniqueness. The first type is composed of the simplest forms of image analysis through thresholding, the second is characterized by region based in which the application meets the uncertainty models and optimization effects during segmentation process. The work proposed in this paper explores the strength and weaknesses of the methods and are analyzed for practical purposes. The progress towards the work is validated with SAR image database in which objective and subjective quantitative performance is clearly identified. The comparison is based on the potential performance measures. The methods show special strength in providing designers with an adequate degree of freedom in choosing the proper objects of the SAR image for their application purposes.