摘要
A novel algorithm for image edge detection is presented. This algorithm combines the nonsubsampled contourlet transform and the mathematical morphology. First, the source image is decomposed by the nonsubsampled contourlet transform into multi-scale and multi-directional subbands. Then the edges in the high-frequency and low-frequency sub-bands are respectively extracted by the dualthreshold modulus maxima method and the mathematical morphology operator. Finally, the edges from the high- frequency and low-frequency sub-bands are integrated to the edges of the source image, which are refined, and isolated points are excluded to achieve the edges of the source image. The simulation results show that the proposed algorithm can effectively suppress noise, eliminate pseudo-edges and overcome the adverse effects caused by uneven illumination to a certain extent. Compared with the traditional methods such as LoG, Sobel, and Carmy operators and the modulus maxima algorithm, the proposed method can maintain sufficient positioning accuracy and edge details, and it can also make an improvement in the completeness, smoothness and clearness of the outline.
提出了一种新的图像边缘检测算法,该算法融合了非下采样轮廓波变换与数学形态学方法来实现图像的边缘检测.首先,源图像被非下采样轮廓波变换分解成多尺度、多方向子带;然后,分别采用双阈值模极大值算法和数学形态学方法提取高频与低频子带的边缘信息;最后,综合高频、低频子带边缘信息,得到源图像全部的边缘信息,并进行细化,剔除孤立点,获得源图像的边缘.仿真实验结果表明:新算法能够有效抑制噪声,去除伪边缘,一定程度上克服了光照不均引起的不良影响;与传统经典算法LoG,Sobel和Canny及模极大值方法相比,该算法能保持足够的定位精度和边缘细节,且边缘轮廓的完整性、光滑度、清晰度等得到明显提升.
基金
The National Key Technologies R&D Program during the 12th Five-Year Period of China(No.2012BAJ23B02)
Science and Technology Support Program of Jiangsu Province(No.BE2010606)
