The Development of Undistortion Digital Image Application using Backpropogation Neural Network Model
Author(s) -
Sakonthawat Inban,
Nopadol Uchaipichat,
Nitikarn Nimsuk
Publication year - 2010
Publication title -
international journal of computer applications
Language(s) - English
Resource type - Journals
ISSN - 0975-8887
DOI - 10.5120/1701-2230
Subject(s) - computer science , artificial neural network , image (mathematics) , development (topology) , artificial intelligence , digital image , computer vision , image processing , mathematics , mathematical analysis
paper reports our study in digital image geometrical distortion correction. The Artificial Neural Network (ANN) was employed to correct the distorted digital image which is simulated in computer. The ANN was trained to map the distorted points to the distortion-free points. As the results, our proposed technique can correct the detected distort-points with . 10 -4 1. 10 -2 pixel of mean square error along the x axis and . 10 -4 1. 10 -2 pixel of mean square error along the y axis. KeywordsDistortion, Artificial Neural Network, Undistortion
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom