Parallel Improved Pulse Coupled Neural Network Application for Edge Detection in Image Processing

2017 ◽  
Vol 06 (02) ◽  
Author(s):  
Arsham Abedini ◽  
Aref Miri ◽  
Alireza Maleki
Keyword(s):  
Neural Network ◽  
Image Processing ◽  
Edge Detection ◽  
Pulse Coupled Neural Network ◽  
Network Application

An improved pulse coupled neural network for image processing

2007 ◽  
Vol 17 (3) ◽  
pp. 255-263 ◽  
Author(s):  
Luping Ji ◽  
Zhang Yi ◽  
Lifeng Shang
Keyword(s):  
Neural Network ◽  
Image Processing ◽  
Pulse Coupled Neural Network

scholarly journals A Novel Method for L Band SAR Image Segmentation Based on Pulse Coupled Neural Network

2021 ◽  
Vol 4 (2) ◽  
pp. 117
Author(s):  
Harwikarya Harwikarya ◽  
Sabar Rudiarto ◽  
Glorin Sebastian
Keyword(s):  
Neural Network ◽  
Image Processing ◽  
Network Architecture ◽  
Third Generation ◽  
Sar Image ◽  
Neural Network Architecture ◽  
Pulse Coupled Neural Network ◽  
Sar Image Segmentation ◽  
Novel Method ◽  
L Band

Pulse Coupled Neural Network (PCNN) is claimed as a third generation neural network. PCNN has wide purpose in image processing  such as segmentation, feature extraction, sharpening etc.  Not like another neural network architecture, PCNN do not need training. The only weaknes point  of PCNN is parameter tune due to  seven parameters in its five equations. In this research we proposed a novel method for segmentation based on modified PCNN.  In order to evaluate the proposed method, we processed L Band Multipolarisation  Synthetic Apperture Radar Image. The Results showed all area extracted both by using PCNN and ICM-PCNN from the SAR image are match to the groundtruth. There fore the proposed method is work properly.Copyright © 2017  International Journal of  Artificial Intelegence Research.All rights reserved.

scholarly journals APLICAÇÃO DE REDES NEURAIS CONVOLUCIONAIS NO RECONHECIMENTO DE CARACTERES EM PLACAS INFORMATIVAS JAPONESAS

2021 ◽  
Vol 13 (2) ◽  
pp. 12-24
Author(s):  
Rafael Yuji Hirata Furusho ◽  
Francisco Assis da Silva ◽  
Leandro Luiz de Almeida ◽  
Danillo Roberto Pereira ◽  
Mário Augusto Pazoti ◽  
...  
Keyword(s):  
Neural Network ◽  
Image Processing ◽  
Edge Detection ◽  
Convolutional Neural Network ◽  
Mathematical Morphology ◽  
Digital Image Processing ◽  
Digital Image ◽  
Image Processing Techniques ◽  
Processing Techniques

Unlike most Western countries, which have a Latin-derived base alphabet, Japan has two syllabic alphabets called Hiragana and Katakana, and a Chinese alphabet, called Kanji. The vast differences in the writing of these Eastern alphabets to Western alphabets, Western alphabet-based OCR algorithms tend not to efficiently detect Japanese characters. This work contributes to a methodology applying digital image processing techniques, such as color range-based segmentation, edge detection and mathematical morphology techniques, to detect Japanese traffic informationalplates correctly the perspective and segment the characters contained in it. A convolutional neural network wasused to perform the classification of Hiragana characters contained in the segmented plates, withaccuracyof 94.37%.

Sign in / Sign up

Export Citation Format

Share Document