Color image edge detection based on quaternion and self-organizing map neural network

2013 ◽  
Vol 32 (2) ◽  
pp. 510-513
Author(s):  
Zheng WANG ◽  
Xing-min LI
Keyword(s):  
Neural Network ◽  
Edge Detection ◽  
Color Image ◽  
Self Organizing Map ◽  
Image Edge Detection ◽  
Image Edge ◽  
Self Organizing

An Improved Approach of Color Edge Detection Based on Robustness of Cell Neural Network

2011 ◽  
Vol 403-408 ◽  
pp. 1879-1882
Author(s):  
Qing Ling Jiang
Keyword(s):  
Neural Network ◽  
Edge Detection ◽  
Color Image ◽  
Color Space ◽  
Robustness Analysis ◽  
Detection Algorithm ◽  
Edge Extraction ◽  
Image Edge Detection ◽  
Image Edge ◽  
Rgb Color Space

For the disadvantage of cell neural network (CNN) method which can not directly deal with color images, we present a new color image edge detection algorithm according to CNN model. Through robustness analysis for CNN template, a CNN theorem be carried out which can compute in the RGB color space. The experimental results show that our approach can effectively carry out edge extraction and locates accurately.

Local Adaptive Perceptual Color Difference for Color Image Edge Detection

2013 ◽  
Vol 34 (9) ◽  
pp. 2058-2063
Author(s):  
Xian Yang ◽  
Bo Li ◽  
Wen Ding ◽  
Qi-mei Chen
Keyword(s):  
Edge Detection ◽  
Color Image ◽  
Color Difference ◽  
Image Edge Detection ◽  
Image Edge

Edge Detection of Color Images Based on Improved Morphological Gradient Operators

2014 ◽  
Vol 511-512 ◽  
pp. 550-553 ◽  
Author(s):  
Jian Yong Liang
Keyword(s):  
Edge Detection ◽  
Detection Method ◽  
Color Image ◽  
Color Images ◽  
Morphological Gradient ◽  
Image Edge Detection ◽  
Gradient Based ◽  
Image Edge ◽  
Edge Detection Method ◽  
Traditional Approaches

Edge detection is an old and hot topic in image processing, pattern recognition and computer vision. Numerous edge detection approaches have been proposed to gray images. It is difficult to extend these approaches to color image edge detection. A novel edge detection method based on mathematical morphology for color images is proposed in this paper. The proposed approach firstly compute vector gradient based on morphological gradient operators, and then compute the optimal gradient according to structure elements with different size. Finally, we use a threshold to binary the gradient images and then obtain the edge images. Experimental results show that the proposed approach has advantages of suppressing noise and preserving edge details and it is not sensitive to noise pixel. The finally edge images via the proposed method have high PSNR and NC compared with the traditional approaches.

Sign in / Sign up

Export Citation Format

Share Document