Simulated Annealing Based Simplified Snakes for Weak Edge Medical Image Segmentation
基于模拟退火的简化Snake弱边界医学图像分割

Segmentation on weak edged medical image is a difficulty in segmenting technology. In this paper, a simplified snake algorithm for image segmentation is proposed. This proposed model introduces the idea of simplified snake to improve the traditional snake model especially by adding an area energy term with variable coefficients into the internal energy term. This area energy term does well in improving the initialization problem, furthermore, it keeps the low time complexity of original simplified model. And besides, this paper also introduces simulated annealing algorithm to this improved simplified snake model and this algorithm makes a better effects on image segmentation. In this paper, the author discusses the choice of adjacent region, mechanism of generating random variables and the acceptance principles, etc. which are all playing an important role in searching the ideal optimum solution in simulated annealing algorithm. This simulated annealing based simplified snake model proposed in the paper has been tested on medical images. Enough experiments and the results comparing with traditional snake have proved that this proposed algorithm shows a significant improvement in segmenting weak edged medical images with a low time complexity.