Click here to Skip to main content
Rate this: bad
Please Sign up or sign in to vote.
See more: C#
Hello, I need to built an OCR using back propagation neural networks. What I need are some ideas.
my task is to load a number of .png images that I can train my neural network with, and then with other images I can be able to read the character.
Up till now I am able to load an image and convert it to 1's and 0's using the bitmap function. Now I am stuck I how should use the binary string so that I can use them as inputs to my Neural Network
Please give me some hints. Thanks
Posted 17-Nov-12 2:43am

1 solution

Rate this: bad
Please Sign up or sign in to vote.

Solution 1

Read the following articles :
Neural Network OCR[^]
Unicode Optical Character Recognition[^]

This content, along with any associated source code and files, is licensed under The Code Project Open License (CPOL)

  Print Answers RSS
0 Sergey Alexandrovich Kryukov 271
1 OriginalGriff 253
2 nv3 50
3 VJ Reddy 45
4 Mehdi Gholam 45
0 Sergey Alexandrovich Kryukov 6,696
1 OriginalGriff 6,149
2 CPallini 2,473
3 Richard MacCutchan 1,697
4 Abhinav S 1,560

Advertise | Privacy | Mobile
Web04 | 2.8.140821.2 | Last Updated 17 Nov 2012
Copyright © CodeProject, 1999-2014
All Rights Reserved. Terms of Service
Layout: fixed | fluid

CodeProject, 503-250 Ferrand Drive Toronto Ontario, M3C 3G8 Canada +1 416-849-8900 x 100