21-04-2012, 11:28 AM
An Overview Of Character Recognition Focused On Off-line Handwriting
[attachment=20506]
Introduction
The mechanical or electronic translation of images of handwritten, typewritten or printed text into machine-editable text.
A widely OCR systems is to follow a two step schema:
(a) represent the character as a vector of features and
(b) classify the feature vector into classes
Objectives
To increase its efficiency level
To reduce the error
To improve high recognition performance
To enhance resolution rate
Feature extraction
Principal component analysis is a quantitative method for achieving the simplification.
Generates a new set of variables = principal components.
Each principal component is a linear combination of the original variables.
All the principal components are orthogonal to each other, so there is no redundant information.
[attachment=20506]
Introduction
The mechanical or electronic translation of images of handwritten, typewritten or printed text into machine-editable text.
A widely OCR systems is to follow a two step schema:
(a) represent the character as a vector of features and
(b) classify the feature vector into classes
Objectives
To increase its efficiency level
To reduce the error
To improve high recognition performance
To enhance resolution rate
Feature extraction
Principal component analysis is a quantitative method for achieving the simplification.
Generates a new set of variables = principal components.
Each principal component is a linear combination of the original variables.
All the principal components are orthogonal to each other, so there is no redundant information.