Unsupervised 3D Feature Extraction and Edge Detection Algorithm

2019 ◽  
Author(s):  
Charles Davi
2014 ◽  
Vol 536-537 ◽  
pp. 180-185
Author(s):  
Xue Bin Qin ◽  
Mei Wang ◽  
Pai Wang ◽  
Hui Zhen Liang

In the computer vision, feature extraction is an important research orientation. Corner and edge detection is a basic technique for obtaining local feature in this image. In the paper, we propose a method that corner and edge of image is detected simultaneously by an annealed chaotic competitive network. The method is compared with several traditional methods of corner and edge detection algorithm, the experiment result shows a good performance. The clustering method can achieve the corner and edge detection simultaneously.


2012 ◽  
Vol 220-223 ◽  
pp. 1279-1283 ◽  
Author(s):  
Li Hong Dong ◽  
Peng Bing Zhao

The coal-rock interface recognition is one of the critical automated technologies in the fully mechanized mining face. The poor working conditions underground result in the seriously polluted edge information of the coal-rock interface, which affects the positioning precision of the shearer drum. The Gaussian filter parameters and the high-low thresholds are difficult to select in the traditional Canny algorithm, which causes the information loss of gradual edge and the phenomenon of false edge. Consequently, this paper presents an improved Canny edge detection algorithm, which adopts the adaptive median filtering algorithm to calculate the thresholds of Canny algorithm according to the grayscale mean and variance mean. This algorithm can protect the image edge details better and can restrain the blurred image edge. Experimental results show that this algorithm has improved the edge extraction effect under the case of noise interference and improved the detection precision and accuracy of the coal-rock image effectively.


Sign in / Sign up

Export Citation Format

Share Document