研究目的
To improve the practicability of the level set method and reduce the computational cost by proposing an optimized level set active contour model that embeds the image local information.
研究成果
The optimization algorithm based on the MAP method is the optimal algorithm, greatly saving the evolution time and improving the accuracy of the segmentation. The model has high computational efficiency and accuracy for many types of pictures.
研究不足
The paper does not explicitly mention the limitations of the research.
1：Experimental Design and Method Selection:
The paper proposes a new variational level set model integrating edge information and regional local information, adding a local energy term to the energy function.
2：Sample Selection and Data Sources:
The image is processed to generate saliency maps using three saliency methods to obtain the initial contour.
3：List of Experimental Equipment and Materials:
Matlab 2012b equipped with Intel (R) Core (TM) i5-3470,
4：20 GHz, 4GB RAM on Windows Vista. Experimental Procedures and Operational Workflow:
The image segmentation is implemented by new level set methods based on optimal saliency method, comparing the results and time of four algorithms.
5：Data Analysis Methods:
The segmentation accuracy is evaluated using the precision (accuracy)=TP/(TP+FP), where TP and FP denote the correctly-divided pixels and the wrongly-divided pixels, respectively.
独家科研数据包，助您复现前沿成果，加速创新突破
获取完整内容
