>>
>>
关键字：Edge detection;Cable sheathing - Image processing - Insulating materials - Insulation;Accurate location - Cable insulation layer - Canny algorithm - Degree of automation - Detection performance - Edge detection algorithms - Gaussian filters - Image preprocessing
摘要：The paper mainly introduces the application of improved Canny algorithm in the cable insulation layer measurement. This method bases on the traditional Canny edge detective algorithm. In order to obtain ideal parameters, firstly, an adaptive Gaussian filter is used for image pre-processing. And then, the improved amplitude and direction of the gradient are applied in this paper. And to refine the roof of gradient amplitude, non-maxima oppression is used to remove noise. Finally, the product of dual-threshold is greater than single threshold, which leads to better edge detection performance. The adaptive canny algorithm used in this paper maintains traditional Canny operator"s original advantages such as high signal-noise ratio, accurate location low single-edge response, furthermore, this method increases the ability to suppress false edge; moreover, the degree of automation has been improved, and the method has achieved good results in experiment. On the basis of this method, the traditional edge detection algorithm and other algorithms have been tested, and the experimental results show that the improved method is a feasible and effective way for edge detection in measuring cable insulation parameters system. © 2009 IEEE.<br/>
卷号：2
是否译文：否
