An implementation of the backpropagation algorithm for images recognition
Corressponding author's email:
hiendt@hcmute.edu.vnKeywords:
images recognition, Backpropagation, algorithmAbstract
A neural network learning algorithm called Backpropagation is among the most effective approaches to machine learning when the data includes complex sensory input such as images. This document provides an implementation of the Backpropagation algorithm to recognize the images. To increase the speed of recognition color images are scaled to gray images. Note that the training process did not consist of a single call to a training function. Instead, the network was trained several times on various input ideal and noisy images. In this case training a network on different sets of noisy images forced the network to learn how to deal with noise, a common problem in the real world.
Downloads: 0
References
Anil K. Jain, Fundamentals of Digital Image Processing. Prentice Hall, 1991.
Bernd Jähne, Digital Image Processing, Spring Verlag 1995
Learning the Uncorrelated, Independent, and Discriminating Color Spaces for Face Recognition Chengjun Liu; Information Forensics and Security, IEEE Transactions on Volume 3, Issue 2, June 2008 Page(s):213 – 222.
Maximum Confidence Hidden Markov Modeling for Face Recognition Jen-Tzung Chien; Chin-Pin Liao; Pattern Analysis and Machine Intelligence, IEEE Transactions on Volume 30, Issue 4, April 2008 Page(s):
606 – 616.
Nguyễn Đình Thúc, Mạng Nơron, Phương Pháp và Ứng Dụng, NXB Giaùo Duïc 2000.
Rein-Lien Hsu, “Face Detection and Modeling for Recognition,” Ph.D. Thesis, Department of Computer Science & Engineering, Michigan State University, USA, 2002.
Downloads
Published
How to Cite
Issue
Section
Categories
License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Copyright © JTE.