Edges Detection of Brain Magnetic Resonance Images by Multiscale Morphology
Yuqian Zhao, Weihua Gui, Zhencheng Chen, Lingyun Li · International journal of tomography and simulation · 2007
Edges detection of brain magnetic resonance images is an important image processing work for clinical diagnosis of brain diseases, and it is an essential pre-processing step in medical image segmentation and 3-D reconstruction. Differential operators can’t filter the noise effective, and common morphological edge detection operation blurs the edge of image. This paper represents a new multiscale morphological edge detection algorithm. To utilize the noiseproof feature of larger scale elements to restrain the noise, and to utilize the allocation feature of smaller scale elements to trace and detect the edges, multiscale synthetic weighted method is proposed to compromise the merits of different scale elements. The experimental results show that the algorithm is effective in detecting the edge of brain magnetic resonance images.