COMPARATIVE STUDY AND NEW APPROACH MULTI CLASSIFIERS: APPLICATION TO THE RECOGNITION OF ARABIC NUMERALS

Abstract

 Generally, most of the problems of recognition are due to the classification of the feature vectors, or to the mismatch between learning conditions and test, so to improve the robustness of the existing recognition systems, it is necessary to efficient extraction, to reduce these differences between the reference corpus (learning) and test, and finally achieve a reliable and valid comparison. In fact, the task at first is devoted to study and present the different classifications algorithms (classifiers) and fly on the theoretical basis of algorithms recognition, which allows us to address the principle of operation of systems recognition in their totality. And in a second step, we compared the different classification algorithms to identify the advantages and disadvantages of such algorithms, and assess the level and performance of the system already made, to directly filter and keep only the positive side of each method. In the end, an analysis and comparison of the results were made along this work, which has led us to propose a hybrid classifier, and provides us a significant increase in the rate of speech recognition performing a biometric authentication tool powerful enough as possible.

Authors and Affiliations

Abdelmajid LAMKADAM

Keywords

Related Articles

 Zero Gas Flaring, A Realistic Panacea For Robust Socio

 Gas plays a major role in the economic development and energy security of any oil and gas producing nation. The current world gas reserve stands at 5302TCF while Nigeria gas reserve stands at about 187tcf (about 3...

 A HONEY BEE SWARM INTELLIGENCE ALGORITHM FOR COMMUNICATION NETWORKS

 A particular intelligent behavior of a honey bee swarm, foraging behavior, is considered and a new artificial bee colony algorithm simulating this behavior of real honey bees for solving multidimensional and multi...

 WITRICITY: THE TECHNOLOGICAL MIRACLE OF WIRELESS ELECTRICITY TRANSFER

 The main theme of this paper is to transfer power wirelessly using the concept of highly resonant coupling. Witricity can make an amazing change by removing the use of conventional copper cables and current carryi...

 SIMULATION OF TRANSFORMERLESS DC- DC BOOST CONVERTER FOR HIGH STEP-UP VOLTAGE GAIN

 This paper presents the performance analysis of transformer less dc-dc converters to achieve high step-up voltage gain without an extremely high duty ratio. The technique used to design the equivalent circuit of t...

 Creating a Virtual Touch Screen Using MEMS and Flex Sensors: A Survey

 The objective of this project is to create an interactive virtual touch screen. The technologies used here are microelectromechanical- systems (MEMS), Flex sensors, Zigbee network protocol. MEM is the technology o...

Download PDF file
  • EP ID EP106988
  • DOI 10.5281/zenodo.54645
  • Views 61
  • Downloads 0

How To Cite

Abdelmajid LAMKADAM (30).  COMPARATIVE STUDY AND NEW APPROACH MULTI CLASSIFIERS: APPLICATION TO THE RECOGNITION OF ARABIC NUMERALS. International Journal of Engineering Sciences & Research Technology, 5(6), 29-33. https://europub.co.uk/articles/-A-106988