Character recognition through image processing

Abstract

Recognition of alphabetic characters is a basic need in incorporating intelligence to computers. Machine intelligence involves several aspects among which optical recognition is a tool, which can be integrated to text recognition. To make these aspects effective character recognition with better accuracy is important. However, handwritten character recognition is still a difficult task because of the high variability in the character shapes written by individuals. Input is paragraphs of running text, which is pre-processed to segment it into normalized individual words. A neural network is trained onto the dataset containing 55 samples for each of the 26 alphabets for recognition. The paper entitled “Character Recognition” is comparable to optical character recognition software where input is fed through a camera, from internet or some scanned image as well and the processing is done at the instant of taking input. The goal is to recognize only the text component from the image stream which may have text-characters buried in the colour background, complex patterns and text like structures.

Authors and Affiliations

Khushboo, Smriti Srivastava

Keywords

Related Articles

Study of Pedestrian Safety and Accident Analysis on Chennai City

Each year, more than 270 000 pedestrians lose their lives on the roads. Globally, pedestrians constitute 22% of all road traffic fatalities, and in some countries this proportion is as high as two thirds of all road tra...

Self-Destructing Messages Using Layered Encryption for Mobile Devices

Communication through SMS is very popular now-a-days and it is cheap, fast and simple. However, when confidential information is exchanged using SMS, it is very difficult to protect the information from SMS security thr...

Numerical solution of fractional-order logistic equations by fractional Euler’s method

In this article, fractional descriptions of logistic equations are solved by using fractional Euler's formula. The fractional derivative in this problem is in the Caputo sense. Special attention is focused on the stabil...

Ethanol Fuelled SI Engine For The Measurement Of Acetaldehyde Emission

The Ethanol-gasoline blend is utilized in this work to measure the acetaldehyde (CH3CHO) coming out from the engine exhaust using the alcohol/gasoline blends by the following method and to Characterize the aldehyde emis...

A Quality Function Deployment Methodology for Product Development

A constant challenge for any fast paced industry, such as consumer electronics, is the very short technology life span needed to successfully take a product from conception to market while staying competitive with other...

Download PDF file
  • EP ID EP18738
  • DOI -
  • Views 313
  • Downloads 9

How To Cite

Khushboo, Smriti Srivastava (2014). Character recognition through image processing. International Journal for Research in Applied Science and Engineering Technology (IJRASET), 2(9), -. https://europub.co.uk/articles/-A-18738