Character Recognition Using Neural Networks

1
Character Recognition Using Neural Networks

• EE 368 Semester Project
• Randy Dimmett

2
Purpose
Use a neural network to recognize text in a
scanned image
3
Procedure
Used Courier New font for sample data and
targets Develop network Test with ideal
input Test with non-ideal input
4
Procedure
Generation of all letters in Courier New 12
pt. 27 inputs each having 108 attributes
5
Procedure
Ideal test data
Non-Ideal data
6
Tested Neural Networks
Linear Associator using Pseudoinverse Rule Up to
9 Accuracy (25 if including spaces) THE ONLY
GOOD DAY OF SCHOOL IS THE LAST ONE MLE RBNV FRRM
M?Y PN ZBLQPO KZ OJJ LFFU LGN
7
Tested Neural Networks
4-Layers using Back-propagation(2,5,2,and 1
neurons) Reached minimum MSE of .01 Very, Very
Bad Results.
8
Tested Neural Networks
5-Layers using Back-propagation(2,5,5,5, and 1
neurons) Reached MSE of about 0. Accuracy less
than 6 THE ONLY GOOD DAY OF SCHOOL IS THE LAST
ONE YBJ RACS AVST SAZ UZ YEGQRD ZW ZBH GAAZ SBF
9
Troubleshooting
Problems with data Noisy Off-Set Effect
10
Troubleshooting Adding Noise
With noise added to sample data, Linear
Associator gives 12 accuracy THE ONLY GOOD DAY
OF SCHOOL IS THE LAST ONE XLT OHPZ SIKD CGY BP
KPNDCQ OQ ?JM KKLS KNP
11
Troubleshooting Getting Data
Using sample data gotten from scanner, the Linear
Associator gives 21 accuracy THE ONLY GOOD DAY
OF SCHOOL IS THE LAST ONE QHP ONJV OLOD E?S NP
KOEKNP JT SDN LFEO LNG
12
Summary of Results



13
Conclusions

Character Recognition is not a good pattern
recognition problem. Results depend greatly on
the sample data used.
14


Questions?