Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Improve Efficiency of On-Line Handwriting Recognition Using Hidden Markov Models


Affiliations
1 Dept. of Engineering, Dr. C. V. Raman University, Bilaspur (C.G), India
2 Dept. of Basic Sciences, Dr. C. V. Raman University, Bilaspur (C.G), India
3 Dr. C. V. Raman University, Bilaspur (C.G), India
     

   Subscribe/Renew Journal


In this paper, as signatures continue to play an important role in financial, commercial and legal transactions, truly secured authentication becomes more and more crucial. to perform verification or identification of a signature, several steps must be performed. Online signature verification has been shown to achieve much higher verification rate than offline verification this paper proposes a novel framework for online signature verification. Different from previous methods, our approach makes use of online handwriting instead of handwritten images for registration. The online registrations enable robust recovery of the writing trajectory from an input online signature and thus allow effective shape matching between registration and verification signatures. In addition, the online registrations enable robust recovery of the writing trajectory from an input online signature and thus allow effective shape matching between registration and verification signatures. in addition, the features have been calculated using 16 bits fixed-point arithmetic and tested with different classifiers, such as hidden markov models, support vector machines, and euclidean distance classifier. We propose several new techniques to improve the performance of the new signature verification rate system.

Keywords

Verification Rate, Verification Rate, Hand Writing Recognition, Training Data, Testing Data.
User
Subscription Login to verify subscription
Notifications
Font Size

Abstract Views: 202

PDF Views: 2




  • Improve Efficiency of On-Line Handwriting Recognition Using Hidden Markov Models

Abstract Views: 202  |  PDF Views: 2

Authors

Tarun Dhar Diwan
Dept. of Engineering, Dr. C. V. Raman University, Bilaspur (C.G), India
Bhoopendra Dhar Diwan
Dept. of Basic Sciences, Dr. C. V. Raman University, Bilaspur (C.G), India
Anirudh Kumar Tiwari
Dr. C. V. Raman University, Bilaspur (C.G), India

Abstract


In this paper, as signatures continue to play an important role in financial, commercial and legal transactions, truly secured authentication becomes more and more crucial. to perform verification or identification of a signature, several steps must be performed. Online signature verification has been shown to achieve much higher verification rate than offline verification this paper proposes a novel framework for online signature verification. Different from previous methods, our approach makes use of online handwriting instead of handwritten images for registration. The online registrations enable robust recovery of the writing trajectory from an input online signature and thus allow effective shape matching between registration and verification signatures. In addition, the online registrations enable robust recovery of the writing trajectory from an input online signature and thus allow effective shape matching between registration and verification signatures. in addition, the features have been calculated using 16 bits fixed-point arithmetic and tested with different classifiers, such as hidden markov models, support vector machines, and euclidean distance classifier. We propose several new techniques to improve the performance of the new signature verification rate system.

Keywords


Verification Rate, Verification Rate, Hand Writing Recognition, Training Data, Testing Data.