Application for Handwritten Devnagari Optical Character Recognition
Journal Title: International Journal of Innovative Research in Computer Science and Technology - Year 2014, Vol 2, Issue 2
Abstract
Handwritten character recognition is used frequently to describe the ability of computer to translate human writing into text. The technical challenges in character recognition arise mainly from three sources. First the symbols: the set of idealized shapes that can occur, often in a hierarchy where simple symbols are assembled into more complex ones, at several levels of organization. Second is deformation: the range of shape variations that each symbol is allowed to undergo, including geometric transformation (translation, rotation, scaling, Stretching, etc.) and more complex or time dependent distortion. Third is an image defect: the imperfections in image due to printing, optics, scanning, quantization, binarization [1], etc. Handwriting and machine print demand a different approach. Handwriting consists of elongated strokes, whereas the machine print consists of regularly spaced blobs. Approx. 500 million people around the world use Devnagari script. It provides written form to over forty languages which
Authors and Affiliations
Shahid Shaikh, Suyog Sankpal, Akshay Sonawane, Prasad Chavan
Keywords
Related Articles
- EP ID EP749426
- DOI -
- Views 46
- Downloads 0
Artificial Intelligence in Banking and Finance
Artificial intelligence (AI) has revolutionized the banking and financial industry by improving client relations, precision, and operational efficiency. This paper explores the use of artificial intelligence (AI) in bank...
Comparative Study on Layout and Drawable Resource Behavior in Android for Supporting Multi Screen
this paper on Android deals with multi layout supports on various size of Android device. While writing an Android application developer should consider various size and type of device. So this paper on Android deals wit...
Iris Recognition Based Data Security for Secure Transmission Over Internet of Things Network
The biometric traits of any human being such as fingerprint, tongue prints, face recognition, Retina Scan, Iris recognition, etc. are unique and cannot be replicated or fabricated using modern technologically advanced pr...
Exploratory Data Analysis of Global Power Plants using Various Machine Learning Algorithms
Nuclear plants' rewards and prices, etc and severe negative costs, are determined by their technology and the amount of electricity they create. Most nations, especially emerging ones where electricity output is expected...
An Identified Kidney Cancer Using Decision Tree and Naïve Bayes Algorithm in Data Mining
Several clients with kidney cancer are able to receive curative treatment because there is nowadays no way to detect the cancer in its initial stages. To decrease the likelihood of kidney tumor cells and the need for tra...