Research on the improvement of image edge detection algorithm based on artificial neural network
Abstract
Image edge detection is an essential basis of computer vision that has made rapid progress these years. Given the importance of the edge detection and the maturity of ANN (artificial neural network), we provide a research paper on the algorithms of image edge detection based on ANN. Firstly, we review the classic methods of edge detection and introduce some new methods proposed these years. Secondly, the foundations of ANN are briefly introduced. Subsequently, we present a traditional edge detection method based on ANN and summarize some disadvantages of this method. Finally, a new edge detection method based on ANN and parallel computing is put forward. The new method is superior to the old one in the efficiency and accuracy of detection.
- Publication:
-
Optik
- Pub Date:
- November 2015
- DOI:
- 10.1016/j.ijleo.2015.07.023
- Bibcode:
- 2015Optik.126.2974G
- Keywords:
-
- Image edge detection;
- Artificial neural network;
- Parallel computing;
- Dynamic window