International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 82 - Number 13 |
Year of Publication: 2013 |
Authors: Khushbu, Sakshi Mehta |
10.5120/14175-2165 |
Khushbu, Sakshi Mehta . Image Pre-processing on Character Recognition using Neural Networks. International Journal of Computer Applications. 82, 13 ( November 2013), 11-15. DOI=10.5120/14175-2165
This paper, presents a theoretical and practical basis of pre-processing on handwritten text for character recognition using forward-feed neural networks. Afterwards, the Feed forward algorithm gives working of a neural network followed by the Back Propagation Algorithm which compromises Training, Calculating Error, and Modifying Weights. The proposed solutions focus on applying Back Propagation Algorithm model with the use of flexible pre-processing methods. The use of artificial neural network in applications can dramatically simplify the code and improve quality of recognition while achieving good performance. The relative performance evaluation of these algorithms has been also carried out based on the network noises and their connection recovered.