DEVELOPMENT OF A HYBRID PSO-SVM-BASED OFFLINE OPTICAL CHARACTER RECOGNITION SYSTEM

Journal Title: World Journal of Engineering Research and Technology - Year 2018, Vol 4, Issue 3

Abstract

Optical Character Recognition (OCR) is the mechanical or electronic translation of images of handwritten, typewritten or printed text into machine-editable text. However, with support vector machine, it is difficult to take the proper threshold value and thus end up losing the necessary pixels. On the other hand, SVM only supports atomic concepts rather than complex concepts which makes its applications partially limited. This further makes it difficult to take the scan sample of the forms which includes lots of boxes. In addition, with large size / dimension of features, support vector machine often produce Inaccurate classification results Therefore in this paper, a hybrid of Particle Swarm Optimization (PSO) and Support Vector Machine (SVM) is developed for optical handwritten character recognition. The PSO was used for feature extraction and dimensionality reduction of the resultant features while SVM was used for classification at both training and testing stages. The performance of developed hybrid PSOSVM for OCR was evaluated using accuracy and time. The evaluation results when compared with support vector machine reveal that the developed hybrid PSO-SVM for OCR outperforms the conventional SVM.

Authors and Affiliations

Oyeleye Christopher Akinwale

Keywords

.

Related Articles

MECHANICAL ENGINEERING IN ANCIENT EGYPT, PART 67: OSTRACA INDUSTRY

The ancient Egyptians used ostraca as one of the means for writing and drawing since the Predynastic to their Late Periods. The paper handles how they used this cheaper technique to authorize their different activities a...

ONLINE E-SECRETARY SYSTEM FOR VARIOUS BUSINESSES

In this article, we propose a new Online E-Secretary system which can be presented as a web application connected to a relational database. The online E-Secretary system is a solution that cans helps to manage all appoin...

IMPACTS OF LAND USE ON INFILTRATION

Land use can affect natural ecological processes such as infiltration. There are many land uses applied at Ikeduru L.G.A. in Imo State, Nigeria, thus, the area is selected as a case study. The objective of study is to de...

COMPARATIVE ANALYSIS OF DATA MINING CLASSIFICATION ALGORITHM FOR STUDENTS SOFT SKILLS

Data mining refers to the finding of relevant and useful information from databases. Data mining is also called Knowledge Discovery in Database (KDD), pattern Analysis, Data Archiology, and Business Intelligences. Data m...

3D FEM ANALYSIS OF EXTRUSION PROCESS OF AL2024-BERYL COMPOSITES

Extrusion Process are now getting importance for its abilities to give improved mechanical properties, high production rate and less material waste when compared with that produced by machining, casting or by assembling...

Download PDF file
  • EP ID EP662295
  • DOI -
  • Views 178
  • Downloads 0

How To Cite

Oyeleye Christopher Akinwale (2018). DEVELOPMENT OF A HYBRID PSO-SVM-BASED OFFLINE OPTICAL CHARACTER RECOGNITION SYSTEM. World Journal of Engineering Research and Technology, 4(3), 137-148. https://europub.co.uk./articles/-A-662295