06-02-2012, 12:33 PM
Offline Handwriting Recognition Using Genetic Algorithm
Introduction
Handwriting Recognition:
Handwriting recognition is the ability of a computer to receive and interpret handwritten input from sources such as paper documents, photographs, touch-screens and other devices.
Offline handwriting recognition refers to the recognition technique where the final figure is given to us.
OVERVIEW:
ARTIFICIAL NEURAL NETWORKS:
Artificial Neural Networks involve training of the system with all the
Characters.
GENETIC ALGORITHM:
It can be used as an excellent means of combining various styles of writing a character and generating new styles.
Iwe try to match the input to the training data and the data generated from intermixing of training data, to find the best match for the given input data.
RECOGNITION ALGORITHM
HandwritingRecognition(Language,TrainingData,Inpu
T Image)
Step1: For every character c in language
Step2: For every input i for the character c in test data
Step3: Generate Graph of i
Step4: Generate graph t of input image
Step5: For every character c in language
Step6: Use Genetic Algorithm to generate hybrid graphs
Step7: Return character corresponding to graph with the minimum most fitness function.
Overview
Applications:
Bank-Check Processing
Signature Verification
Automated form filling
Document Digitizing
Proposed Project
We are planning to implement a handwriting recognition system for form filling application.
Input form will be scanned and corresponding entries will be made in digitized form template.
System will recognize printed as well as handwritten characters and will convert it into a text format. So there no need of manually updating databases.
References
1] IJCSI International Journal of Computer Science Issues, Vol. 7, Issue 2, No 1, March 2010
2] Paper from Sixth International Conference on Information Research and Applications – i.Tech 2008, Varna, Bulgaria, June-July 2008
