A study of neural network and multi-channel handwritten isolated digit recognition
Recognition of handwritten digits/characters is an important and necessary step in many documents processing application and this has been a popular topic of research for many years. Many approaches and significant research efforts have been proposed and made to solve this problem. Some use only the...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Theses and Dissertations |
| Published: |
2008
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/4030 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Summary: | Recognition of handwritten digits/characters is an important and necessary step in many documents processing application and this has been a popular topic of research for many years. Many approaches and significant research efforts have been proposed and made to solve this problem. Some use only the pixel-image as input to a powerful statistical or neural classifier. Others preprocess the data in order to extract some features that are fed into a classifier. The main difficulty lie in the handwritten recognition task is to tell which digit is represented by a pixel-image of a handwritten digits/character, this is due to the high variability of the scanned image caused by the particular writing style of different persons and also the scanning quality. |
|---|