Edge detection method based on relative variation

Abstract

The invention proposes a cellular neural network edge detection method based on relative variation regularization. The method includes image preprocessing and edge detection after the preprocessing. The image preprocessing mainly adopts the relative variation to smooth noises and textures; and the edge detection after the preprocessing mainly adopts a cellular neural network method to detect images. The method is capable of extracting effective and reliable and accurate effective edge information from pictures which are rich in noises and complex in textures. Compared with a traditional Canny method, the method restrains effects from the noises and the textures and compared with a standard cellular neural network method, the method prevents advance design of complex CNN template parameters.

Description

technical field [0001] The invention relates to an edge detection method based on relative variation, belonging to the fields of computer vision and video retrieval. technical background [0002] The edge of an image is one of the most basic features of an image. Its detection and extraction has always been a research hotspot in the field of image processing and computer vision. It is an important basis for image analysis and understanding such as image segmentation, texture feature extraction, and shape feature extraction. Many scholars at home and abroad have done in-depth research in this area. At present, the classic image edge detection methods include differential operator methods, such as Roberts operator, Sobel operator, Prewitt operator, Laplacian operator, and most operator methods, such as LOG operator, Canny operator. In addition, in recent years, some new methods have emerged in the field of image edge detection, such as wavelet multi-scale methods, cellular ne...

AI Technical Summary

Problems solved by technology

But the wavelet transform is too complex

Images