摘要
在基于边缘的活动轮廓模型中,边缘停止函数的选择是十分重要的。传统的边缘停止函数依赖于图像高斯平滑后的梯度模,这容易导致模型分割速度慢,无法准确分割被噪声严重污染或背景复杂的图像。结合小波变换,提出一个新的边缘停止函数。实验表明,基于该函数的边缘模型可以有效地解决上述问题,而且可以应用于多目标的选择性分割。
The edge stopping function is very important in edge-based active contour models. It typically depends on the gradient magnitude of Gaussian smoothed image, which leads the corresponding models evolving slowly and having difficulty to segment images with strong noise and complex background. In this paper, a novel edge stopping function related to wavelet transform is proposed. Experimental results show that, based on the new edge stopping function, edge-based models can not only effectively address the problems above, but also be applied to selective detection of multiple objects.
出处
《计算机工程与应用》
CSCD
2014年第10期27-30,共4页
Computer Engineering and Applications
基金
重庆市教育委员会科学技术研究项目(No.KJ130604)
重庆师范大学基金项目(No.12XLB034)
关键词
图像分割
活动轮廓模型
边缘停止函数
小波变换
image segmentation
active contour model
edge stopping function
wavelet transform
