Artificial Intelligence Key Laboratory of Sichuan Province, Automation and Information Engineering, Sichuan University of Science and Engineering, Zigong, China.
College of Automation and Information Engineering, Sichuan University of Science and Engineering, Zigong, China.
PLoS One. 2021 Jun 7;16(6):e0251914. doi: 10.1371/journal.pone.0251914. eCollection 2021.
Active contour models driven by local binary fitting energy can segment images with inhomogeneous intensity, while being prone to falling into a local minima. However, the segmentation result largely depends on the location of the initial contour. We propose an active contour model with global and local image information. The local information of the model is obtained by bilateral filters, which can also enhance the edge information while smoothing the image. The local fitting centers are calculated before the contour evolution, which can alleviate the iterative process and achieve fast image segmentation. The global information of the model is obtained by simplifying the C-V model, which can assist contour evolution, thereby increasing accuracy. Experimental results show that our algorithm is insensitive to the initial contour position, and has higher precision and speed.
基于局部二值拟合能量的主动轮廓模型可以分割不均匀强度的图像，但容易陷入局部最小值。然而，分割结果在很大程度上取决于初始轮廓的位置。我们提出了一种具有全局和局部图像信息的主动轮廓模型。模型的局部信息通过双边滤波器获得，这也可以在平滑图像的同时增强边缘信息。在轮廓演化之前计算局部拟合中心，这可以减轻迭代过程并实现快速图像分割。模型的全局信息通过简化 C-V 模型获得，这可以辅助轮廓演化，从而提高准确性。实验结果表明，我们的算法对初始轮廓位置不敏感，具有更高的精度和速度。
