- Breast cancer has become the leading cause of cancer deaths among women in developed countries including Thailand. To decrease the related mortality, the disease must be treated as early as possible. However, it is hard to detect and diagnose tumors at an early stage. Moreover, even when the existence of the tumor is evident it is hard to outline its contours. However, the accurate segmentation of the tumor may reveal important features (such as irregularity of the border) which help to detect the malignancy or exclude it without performing harmful biopsies. Therefore, the project offers a new approach to segmentation of ultrasound images of the breast tumors based on the active contour method combined with a new force field analysis techniques. The techniques are based on continuous force field analysis, the phase portrait analysis, multi resolution and multiple cooperating quadratic snakes. The numerical tests against standard techniques and the recently published modifications of the active contours favor the proposed family of algorithms. The algorithms have been applied to the segmentation of medical images and also to a variety of other interesting problems such as extraction of the roads from satellite images and even for breaking digital CAPTCHAs. The output of the project is 5 research papers with the impact factor, and two PhD dissertations Dr. Sirikan Chucherd (2011) and Mr. Yoichi Nakaguro (2013, completed).