Handwritten Devanagari (Marathi) Compound Character Recognition using Seventh Central Moment

نویسنده

  • V M Thakare
چکیده

Compound character recognition of Devanagari Script (Marathi language) is one of the challenging tasks since the compound character is combination of one or more characters. These characters can be treated as fusion of two or more characters and hence these are complex in structure. Marathi, Hindi, Sanskrit and Nepali are written with Devanagari script. All these languages have compound characters. The characters may be formed with different sequence of combinations of basic characters such as vowels and consonants. Thus the recognition of compound characters makes this task more challenging to the researcher. So, as compared to English like Roman script, one of the major obstacles in handwritten Marathi character recognition is the large number of complex shaped compound characters. Considering the complexity of the problem, the present algorithm makes an attempt to identify the compound character. This paper discuss the recognition of compound character using combination of 7 Invariant Moment (Rotational Moment) and 7 order Central Moment(Translation Moment). SVM is used as classifier. The overall performance of the proposed system is 93.87%.

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

Zernike Moment Feature Extraction for Handwritten Devanagari (Marathi) Compound Character Recognition

Compound character recognition of Devanagari script is one of the challenging tasks since the characters are complex in structure and can be modified by writing combination of two or more characters. These compound characters occurs 12 to 15% in the Devanagari Script. The moment based techniques are being successfully applied to several image processing problems and represents a fundamental too...

متن کامل

Handwritten and Printed Devanagari Compound using Multiclass SVM Classifier with Orthogonal moment Feature

Handwritten Devanagari character plays a vital role in the research area. Number of technique has been adopted in previous decades and still some new are arising to get good results from recognition system. In Devanagari, Compound character are complex in structure, they are written by combination two or more character. Due to complex structure in it, it gives a challenging task to the research...

متن کامل

A Survey on Handwritten Character Recognition Using Artificial Neural Network

To automatically recognize the handwritten Hindi character is a very tricky task. Because these characters are written in unlike sizes, dimension, orientation, thickness and format. The Hindi Language is one of the complex language which having compound characters. Compound characters are the combination of one or more characters to make complex characters. Thus the structure of these is comple...

متن کامل

Performance Comparison of Features on Devanagari Hand-printed Dataset

Devanagari script is being used in various languages, in south Asian subcontinent, such as Sanskrit, Rajasthani, Marathi and Nepali and it is also the script of Hindi, the mother tongue of majority of Indians. Recognition of handwritten characters of Devanagari alphabet set is an important area of research. The work done for the recognition of Devanagari handwritten script is negligible in lite...

متن کامل

Recognition of Handwritten Devanagari Words Using Neural Network

Handwritten Word Recognition is an important problem of Pattern Recognition. Online handwritten recognition system for Devanagari words is still in developing stage and becoming challenging due to the large complexity involvement. In India, more than 300 million people use Devanagari script for documentation. There has been a significant improvement in the research related to the recognition of...

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 2015