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
- EP ID EP662295
- DOI -
- Views 174
- Downloads 0
MECHANICAL ENGINEERING IN ANCIENT EGYPT, PART 41: STATUES OF GAZELLE, BABOON AND HEDGEHOG
This is the 41st research paper exploring the evolution of Mechanical Engineering in Ancient Egypt. The paper investigates the production of gazelle, baboon and hedgehog statues in ancient Egypt during the Predynastic an...
MECHANICAL PROPERTIES AND CHARACTERISTICS OF NATURAL FIBER-A REVIEW PAPER
The need of friendly environmental materials has been enforced highly in the engineering field, the very good alternative materials for synthetic fibers for automotive and aircraft fields without much compromising the me...
EFFICACY OF CBR ON COPPER AND STEEL SLAG IN EXPANSIVE SOILS
A large part of Central India and a portion of South India are covered with black cotton soils. These soils have high swelling and shrinkage characteristics and extremely low CBR value and shear strength. Hence, there is...
SEARCH FOR HEAVY TRACE METALS IN SPECIES SARDINA PILCHARDUS AT THE BAY OF ALGIERS
Our study involves the determination of heavy metals in a fishery product from the Bay of Algiers. This study involved a representative sampling of Sardina pilchardus of homogeneous size. The study was conducted over a t...
MODELLING AND ASSESSMENT OF WIND ENERGY RESOURCE FOR POWER DISTRIBUTION SYSTEM
This paper presents Stochastic Modeling for investigating the performance of wind energy technology using wind speed data for the city of Maiduguri (11.850 N; 13.083 E; altitude 354 m), North-Eastern Nigeria. In this pap...