Fuzzy-Membership Based Writer Identification from Handwritten Devnagari Script
2
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
The handwriting based person identification systems use their designer’s perceived structural properties ofhandwriting as features. In this paper, we present a system that uses those structural properties as features thatgraphologists and expert handwriting analyzers use for determining the writer’s personality traits and formaking other assessments. The advantage of these features is that their definition is based on sound historicalknowledge (i.e., the knowledge discovered by graphologists, psychiatrists, forensic experts, and experts ofother domains in analyzing the relationships between handwritten stroke characteristics and the phenomenathat imbeds individuality in stroke). Hence, each stroke characteristic reflects a personality trait. We havemeasured the effectiveness of these features on a subset of handwritten Devnagari and Latin script datasetsfrom the Center for Pattern Analysis and Recognition (CPAR-2012), which were written by 100 people whereeach person wrote three samples of the Devnagari and Latin text that we have designed for our experiments. The experiment yielded 100% correct identification on the training set. However, we observed an 88% and89% correct identification rate when we experimented with 200 training samples and 100 test samples onhandwritten Devnagari and Latin text. By introducing the majority voting based rejection criteria, theidentification accuracy increased to 97% on both script sets.
Abstract
The handwriting based person identification systems use their designer’s perceived structural properties ofhandwriting as features. In this paper, we present a system that uses those structural properties as features thatgraphologists and expert handwriting analyzers use for determining the writer’s personality traits and formaking other assessments. The advantage of these features is that their definition is based on sound historicalknowledge (i.e., the knowledge discovered by graphologists, psychiatrists, forensic experts, and experts ofother domains in analyzing the relationships between handwritten stroke characteristics and the phenomenathat imbeds individuality in stroke). Hence, each stroke characteristic reflects a personality trait. We havemeasured the effectiveness of these features on a subset of handwritten Devnagari and Latin script datasetsfrom the Center for Pattern Analysis and Recognition (CPAR-2012), which were written by 100 people whereeach person wrote three samples of the Devnagari and Latin text that we have designed for our experiments. The experiment yielded 100% correct identification on the training set. However, we observed an 88% and89% correct identification rate when we experimented with 200 training samples and 100 test samples onhandwritten Devnagari and Latin text. By introducing the majority voting based rejection criteria, theidentification accuracy increased to 97% on both script sets.
참고문헌 (35)
- J. E. Downey, "Graphology and the Psychology of Handwriting" (1919), Warwick & York
- A. K. Jain, "An introduction to biometric recognition", IEEE Transactions on Circuits and Systems for Video Technology, 14(1), pp.4~20 (2004)
- P. Lozhnikov, "Exploiting the Knowledge Economy: Issues, Applications, Case Studies" (2006), IOS Press
- E. Sesa-Nogueras, "Biometric recognition using online uppercase handwritten text", Pattern Recognition, 45(1), pp.128~144 (2012)
- L. Schomaker, "Advances in writer identification and verification", Proceedings of the 9th International Conference on Document Analysis and Recognition (ICDAR), pp.1268~1273 (2007)
- P. Ahmed, "On the development of an automated graphology system", Proceedings of the International Conference on Artificial Intelligence (ICAI2008), pp.897~901 (2008)
- E. N. Zois, "Morphological waveform coding for writer identification", Pattern Recognition, 33(3), pp.385~398 (2000)
- K. Franke, "A computer-based system to support forensic studies on handwritten documents", International Journal on Document Analysis and Recognition, 3(4), pp.218~231 (2001)
- C. I. Tomai, "Discriminatory power of handwritten words for writer recognition", Proceedings of the 17th International Conference on Pattern Recognition (ICPR2004), pp.638~641 (2004)
- S. N. Srihari, "Individuality of handwriting", Journal of Forensic Sciences, 47(4), pp.856~872 (2002)
- M. Bulacu, "Text-independent writer identification and verification using textural and allographic features", IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(4), pp.701~717 (2007)
- G. J. Klir, "Fuzzy Sets and Fuzzy Logic, Theory and Applications" (1995), Prentice Hall
- S. Chanda, "Text independent writer identification for Bengali script", Proceedings of the 20th International Conference on Pattern Recognition (ICPR2010), pp.2005~2008 (2010)
- S. Chanda, "Text independent writer identification for Oriya script", Proceedings of the 10th IAPR International Workshop on Document Analysis Systems (DAS), pp.369~373 (2012)
- I. Siddiqi, "Contour based features for the classification of ancient manuscripts", Proceedings of the 14th Conference of the International Graphonomics Society (2009)
- D. Chawki, "A texture based approach for Arabic Writer Identification and Verification", Proceedings of 2010 International Conference on Machine and Web Intelligence (ICMWI), pp.115~120 (2010)
- M. Ozaki, "Examination of effects of character size on accuracy of writer recognition by new local arc method", Proceedings of the 10th International Conference on Knowledge-Based Intelligent Information and Engineering Systems (KES2006), pp.1170~1175 (2006)
- U. Garain, "Off-line multi-script writer identification using AR coefficients", Proceedings of the 10th International Conference on Document Analysis and Recognition (ICDAR'09), pp.991~995 (2009)
- M. Bulacu, "Writer style from oriented edge fragments", Proceedings of the 10th International Conference on Computer Analysis of Images and Patterns (CAIP), pp.460~469 (2003)
- C. Hertel, "A set of novel features for writer identification", Proceedings of the 4th International Conference on Audio- and Video-Based Biometric Person Authentication (AVBPA), pp.679~687 (2003)
- X. Wang, "An effective writer verification algorithm using negative samples", Proceedings of the 9th International Workshop on Frontiers in Handwriting Recognition (IWFHR-9), pp.509~513 (2004)
- H. Kameya, "A segmentation-free biometric writer verification method based on continuous dynamic programming", Pattern Recognition Letters, 27(6), pp.567~577 (2006)
- P. Purkait, "Writer identification for handwritten Telugu documents using directional morphological features", Proceedings of the 2010 International Conference on Frontiers in Handwriting Recognition (ICFHR), pp.658~663 (2010)
- L. Schomaker, "Using codebooks of fragmented connected-component contours in forensic and historic writer identification", Pattern Recognition Letters, 28(6), pp.719~727 (2007)
- A. Bensefia, "A writer identification and verification system", Pattern Recognition Letters, 26(13), pp.2080~2092 (2005)
- H. Kameya, "A segmentation-free biometric writer verification method based on continuous dynamic programming", Pattern Recognition Letters, 27(6), pp.567~577
- I. Siddiqi, "Text independent writer recognition using redundant writing patterns with contourbased orientation and curvature features", Pattern Recognition, 43(11), pp.3853~3865 (2010)
- P. Mukherji, "Analytical handwriting verification system for ‘Devnagari’ script", Proceedings of the 6th IASTED International Conference on Visualization, Imaging, And Image Processing (2006)
- B. A. Vighnesh, "Autonomous bilingual character recognition and writer identification", International Journal of Engineering and Innovative Technology, 2(10), pp.219~224 (2013)
- K. Amend, "Handwriting Analysis: The Complete Basic Book" (1980), Newcastle Pub. Co
- R. Kumar, "A benchmark dataset for Devnagari document recognition research", Proceedings of the 6th International Conference on Visualization, Imaging and Simulation (VIS'13), pp.258~263 (2013)
- R. Kumar, "Handwritten Devnagari digit recognition : benchmarking on new dataset", Journal of Theoretical & Applied Information Technology, 60(3), pp.543~555 (2014)
- R. Kumar, "On the performance of Devnagari handwritten character recognition", World Applied Sciences Journal, 31(6), pp.1012~1019 (2014)
- S. R. Deans, "The Radon Transform and Some of Its Applications" (1983), Wiley
- Y. Lee, "Handwritten digit recognition using k nearest-neighbor, radial-basis function, and backpropagation neural networks", Neural Computation, 3(3), pp.440~449 (1991)