الفهرس 
AbstractOnly 14 pages are availabe for public view
 |  | from | 114 |  |  |
| | | from | 114 | | |
Abstract
This Thesis proposes an efficient approach towards the development of hand written text recognition along with the recognized text encryption. The proposed system incorporates a new method for extracting features in context of Handwritten English character recognition. After a successful extraction, a secured (password protected) encryption of extracted text is also performed based on the hybrid cryptology of RSA and AES. This make the extracted text secured towards any unauthorized used. Hand written text recognition is still an open research issue in the domain of image processing. The choice of optimal feature vectors affects the accuracy of any text recognition system greatly so bit map representation of input samples are utilized as feature vector. These feature vectors are pre-processed and then applied to the ANN along with the generated target vectors; that are generated on the basis on input samples. 3-layer Artificial Neural Network (ANN) is utilized in this work using supervised learning approach. 55 samples of each English alphabet (small letter and capital letter) are used in this ANN training in order to make sure the general applicability of system towards new inputs. Two different learning mechanisms (Resilient Back-propagation and Scaled conjugate gradient) are tested for the ANN training. Additive image processing algorithms are developed in order to deal with the multiple characters input in a single image, tilt image and rotated image. The trained system provides an average accuracy of more than 95 % with the unseen test image.