The Study of Handwriting Character Recognition (HCR) and Support Vector Machine (SVM)

نویسندگان

  • Dewi Nasien
  • Habibollah Haron
  • Siti Sophiayati Yuhaniz
چکیده

The development of handwriting character recognition (HCR) is an interesting area in pattern recognition. HCR is the ability of a computer to receive and interpret intelligible handwritten input such as digital cameras and other devices. HCR system consists of a number of stages which are preprocessing, feature extraction, classification and followed by the actual recognition. Handwritten can be classified into two components which are on-line and off-line recognition. Off-line recognition is selected as a focus of this paper. Off-line character recognition has been extensively studied over the last few decades and many such commercial systems are available today. Some of its application areas are automatic postal sorting, bank cheque processing, form processing and others. This paper introduces the principle stages of HCR for off-line system and support vector machine (SVM) in the classification process for recognizing a handwritten character.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

IJASCSE, Volume 2, Issue 4, 2013

There are a lot of intensive researches on handwritten character recognition (HCR) for almost past four decades. The research has been done on some of popular scripts such as Roman, Arabic, Chinese and Indian. In this paper we present a review on HCR work on the four popular scripts. We have summarized most of the published paper from 2005 to recent and also analyzed the various methods in crea...

متن کامل

Model selection for the LS-SVM. Application to handwriting recognition

Support Vector Machine(SVM) is a powerful classifier used successfully in many pattern recognition problems. Furthermore, the good performance of SVM classifier has been shown in handwriting recognition field. Least Squares SVM, like SVM, is based on the marginmaximization principle performing structural risk, but its training is easier: it is only needed to solve a convex linear problem rather...

متن کامل

A review on handwritten character and numeral recognition for Roman, Arabic, Chinese and Indian scripts

There are a lot of intensive researches on handwritten character recognition (HCR) for almost past four decades. The research has been done on some of popular scripts such as Roman, Arabic, Chinese and Indian. In this paper we present a review on HCR work on the four popular scripts. We have summarized most of the published paper from 2005 to recent and also analyzed the various methods in crea...

متن کامل

Speeding Up Isolated Vietnamese Handwritten Recognition by Combining SVM and Statistical Features

Based on SVMs (Support Vector Machines) classification where statistical features are extracted, this paper proposes an efficient recognition model for isolated Vietnamese handwritten character recognition. We apply combining reduced set method and dimension reduction of input feature vectors to improve the speed of recognition model. Our test results over Vietnamese handwriting with 52,485 cha...

متن کامل

Multi-class SVM Classifier With Neural Network For Handwritten Character Recognition

The paper describes the process of character recognition using the Multi Class SVM classifier combined with a neural Network approach. The character recognition techniques or the OCRs are either a printed document recognition or the handwritten character recognition. SVM (Support Vector Machine) classifiers often have superior recognition rates in comparison to other classification methods. In ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2009