Optical Character Recognition for Nepali, English Character and Simple Sketch Using Neural Network
Optical Character Recognition (OCR) is the process of text extraction from of images of typewritten or handwritten text. It deals with the recognition of optically processed characters, with the advent of digital optical scanners a lot of paper based book
- PDF / 270,697 Bytes
- 9 Pages / 439.37 x 666.142 pts Page_size
- 31 Downloads / 210 Views
Abstract Optical Character Recognition (OCR) is the process of text extraction from of images of typewritten or handwritten text. It deals with the recognition of optically processed characters, with the advent of digital optical scanners a lot of paper based books, textbooks, magazines, articles and documents are being transformed into an electronic version that can be manipulated by a computer. Unlike English character recognition, Nepali languages are complicated in terms of structure and computations. Nepali language are derived from Devanagari Script; written from left to right fashion having common features of containing straight line on top ‘Shiro Rekha’. The OCR systems developed for the Nepali language carry a very poor recognition rate due to error in character segmentation, ambiguity with similar character, unique character representation style. In this paper we proposed an OCR for Nepali text in Devanagari script, using multi-layer feed forward back propagation Artificial Neural Network (ANN), which improved its efficiency and accuracy. Adaptive learning rate with Gradient descent algorithm is implemented in Neural net with 2 hidden layers used with input and output and MMSE is the performance criteria. Various classifiers for training characters are created and stored. De-noised test sheet is carefully segmented and inputted in trained neural net resulted higher accuracy. Also we have included recognizing simple sketch like as tree, home, and ball. Keywords OCR
⋅
Neural net
⋅
Nepal font
⋅
Image processing
S. Shakya (✉) ⋅ A. Basnet ⋅ S. Sharma ⋅ A.B. Gurung Department of Electronics and Computer Engineering, Central Campus Institute of Engineering, Tribhuvan University, Kirtipur, Nepal e-mail: [email protected] A. Basnet e-mail: [email protected] S. Sharma e-mail: [email protected] A.B. Gurung e-mail: [email protected] © Springer International Publishing Switzerland 2016 P. Meesad et al. (eds.), Recent Advances in Information and Communication Technology 2016, Advances in Intelligent Systems and Computing 463, DOI 10.1007/978-3-319-40415-8_6
45
46
S. Shakya et al.
1 Introduction OCR (Optical Character Recognition) also called Optical Character Reader is a system that provides a full alphanumeric recognition of printed or handwritten characters at electronic speed by simply scanning. Recognition is the mapping of a low-level vector to a higher-level concept, For example mapping bitmaps to characters. Learning is to find out which low-level vectors correspond to high-level concepts. Intelligent Character Recognition (ICR) has been used to describe the process of interpreting image data, in particular alphanumeric text. Images of handwritten or printed characters are turned into ASCII data (machine-readable characters). Usually, OCR uses a modular architecture that is open source, scalable, and workflow controlled. It includes forms definition, scanning, image pre-processing, and recognition capabilities. Artificial Neural Network (ANN) is nonlinear parallel distributed highly connected mathe
Data Loading...
