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

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.

2013 ◽  
Vol 446-447 ◽  
pp. 976-980
Author(s):  
De Rui Song ◽  
Dao Yan Xu ◽  
Li Li

This paper proposes a novel algorithm of edge detection using LUV color space. Firstly, according to peer group filtering (PGF), a nonlinear algorithm for image smoothing and impulse noise removal in color image is used. Secondly, color image edges in an image are obtained automatically by combining an improved isotropic edge detector and a fast entropy threshold technique. Thirdly, according to color distance between the pixel and its eight neighbor-pixels, color image edges can further be detected. Finally, the experiment demonstrates the outcome of proposed algorithm in color image edge detection.


2012 ◽  
Vol 263-266 ◽  
pp. 2483-2487
Author(s):  
Ang Yan Tu ◽  
Jian Cheng Chen

Based on synthesizing quaternion and the R, G, B component of color image , a color image edge detection algorithm was proposed combining quaternion with Echo State Networks(ESN) in this paper . The pixel and its eight neighbourhood average is used to calculate vector product as the characteristic vectors of image edge. Then the ESN has been trained by the characteristic vectors. After training , the ESN is directly used for edge detection. Experiments show that this method has good effect of fabric edge detection, and have a stronger ability to keep the details.


Author(s):  
Aliyu Musa ◽  
Sani Muhammad ◽  
Abubakar Muhammad ◽  
Abubakar Umar ◽  
Khadija Sani ◽  
...  

2014 ◽  
Vol 519-520 ◽  
pp. 714-718
Author(s):  
Jian Cheng Chen ◽  
Ang Yan Tu

Based on synthesizing octonions and the R, G, B components of color image , a color image edge detection algorithm is proposed ,combining octonions with Echo State Networks(ESN) . The judged pixel and its eight-neighbourhood mean is used to calculate vector product as the feature vectors of image edge. Then the ESN is trained with training samples and the trained ESN is directly used for edge detection. Experiments show that this method has good effect of fabric edge detection with a stronger ability to keep the details.


2015 ◽  
Vol 30 (1) ◽  
pp. 143-150 ◽  
Author(s):  
陈虎 CHEN Hu ◽  
凌朝东 LING Chao-dong ◽  
张浩 ZHANG Hao ◽  
杨骁 YANG Xiao ◽  
汤炜 TANG Wei

Sign in / Sign up

Export Citation Format

Share Document