Active Contour Driven by Region Fitting and Laplacian for Image Segmentation
Run Feng, Chengquan Huang, Xue Long Hu, Lihua Zhou, Lan Zheng · 2021 2nd International Conference on Artificial Intelligence and Computer Engineering (ICAICE) · 2021
The region-based active contour models can easily get stuck in local minimums and the image has intensity inhomogeneity. To solve this problem, we proposed an active contour model driven by region fitting and Laplacian. Firstly, a improved local fitting image is defined by adjusting the local average intensity weight, which can effectively avoid local minimums. Then, a region fitting term is defined by using both global and improved local fitting images. Moreover, local and global signed pressure force functions are introduced in the solution of the energy function to stabilize the gradient descent flow. Finally, a Laplacian energy term is introduced in the energy function, which can smooth the homogeneous regions and enhance edge information. Experimental results with different types of images are used for quantitative and qualitative compared with region-based active contour models show that the proposed model has a higher segmentation accuracy.