HANDWRITTEN ENGLISH CHARACTER RECOGNITION USING LVQ AND KNN

Abstract

 A Handwritten character recognition (HCR) is an important task of detecting and recognizing in characters from the input digital image and convert it to other equivalent machine editable form. It gives high growth in image processing and pattern recognition. It has big challenges in data interpretation from language identification, bank cheques and conversion of any handwritten document into structural text form. Handwritten character recognition system uses a soft computing method like neural network, having area of research for long time with multiple theories and developed algorithm. Feature Extraction done in character recognition by introducing a new approach, diagonal based feature extraction. We used two Dataset, first one is own database of 26 alphabets, 10 numbers and 5 special characters written by various people and second is standard CEDAR database. The character recognition is carried out by supervised KNN classifier and LVQ. The results show that KNN has better results than LVQ.

Authors and Affiliations

Rasika R. Janrao

Keywords

Related Articles

 Design and Analysis of Catalytic Converter Using Computational Fluid Dynamics (CFD)

 Now a days the global warming and air pollution are big issues in the world. The 70% of air pollution is due to emissions from an internal combustion engine. The harmful gases like NOX, CO, unburned HC and particu...

 Thermal Biometrics: A New Approach in Biometrics Detection

 Authentication and verification in any system environment has become a very crucial part in today’s age. There are many methods to verify personality or validate anyone. This field is started right from the use of...

 Stabilization of Black Cotton Soil With Sand and Cement as a Subgrade for Pavement

 Expansive soil (Black cotton soil) is very weak and does not have enough stability for any type of construction work. In pavement, subgrade layer is the bottommost layer underlying the base course or surface cour...

 On the Assessment of Solid and Hazardous Waste Management in Port Harcourt, Nigeria

 This study examines the management of both solid and hazardous waste constituents in Port Harcourt, Nigeria. For this purpose, the study area was divided into four zones and were further classified into low, mediu...

 The Logic of Good and Bad

 This paper is designed to solve a problem of artificial intelligence where the purpose is to develop a generic idea to solve the subjective issue of Good and Bad. If generic idea is not found then it would be impo...

Download PDF file
  • EP ID EP133650
  • DOI 10.5281/zenodo.60830
  • Views 65
  • Downloads 0

How To Cite

Rasika R. Janrao (30).  HANDWRITTEN ENGLISH CHARACTER RECOGNITION USING LVQ AND KNN. International Journal of Engineering Sciences & Research Technology, 5(8), 904-912. https://www.europub.co.uk/articles/-A-133650