Email this article 
Open Access
Subscription or Fee Access
A Study of Existing Techniques for Holistic Word Recognition
Abstract
The study described in this paper focuses on the techniques for the Holistic word recognition. Word Holistic is related to the word holism which means whole, so holistic word recognition concerned with whole word recognition rather than segmentation of word into parts. Holistic word recognition removes the needs for segmentation of the word into characters and also eliminating problems associated with the character recognition. This recognition overcomes the problems of character ecognition. For the word recognition the two necessary steps are classification and feature extraction, so these papers discuss the various techniques for the feature extraction and classification. Also this paper discusses the recognition results of various methods.
Keywords
References
Lavrenko, V. Rath, T.M. Manmatha, R., “Holistic word recognition for handwritten historical documents” Document Image Analysis for Libraries, 2004. Proceedings. First International Workshop on, pp: 278- 287. Current Version Published: 2004-08-24.
Eiki Ishidera, Daisuke Nishiwaki, “A Study on Top-down Word Image Generation for Handwritten Word Recognition,” Document Analysis and Recognition, International Conference on, vol. 2, no. 2, pp. 1173, Seventh International Conference on Document Analysis and Recognition(ICDAR'03) - Volume 2, 2003.
Chatwiriya, W.; Klinkhachorn, P.; Lass, N. “Thai handwriting legal amounts recognition System Theory”, 2003. Proceedings of the 35th Southeastern Symposium on Volume, pp: 381 – 385, Issue , 16.-18 March 2003.
Tony M. Rath and R. Manmatha, “Features for word spotting in historical manuscripts”. Multimedia Indexing and Retrieval Group Center for Intelligent Information Retrieval, Department of Computer Science,University of Massachusetts Amherst, Amherst, MA 01003, USA,August 2006.
Soon Man Choi II-Seok Oh. “A segmentation free recognition of two touching numerals using neural network”. Document Analysis and Recognition, 1999. ICDAR '99. Proceedings of the Fifth International Conference.On pp 253-256, Sep 1999.
Dehghan, M. Faez, K. Ahmadi, M. Shridhar, M. “Holistic handwritten word recognition using discrete HMM andself-organizing feature map”.Dept. of Electr. Eng., Amirkabir Univ. of Technology ., Tehran; On pp:2735-2739 vol.4, 2000 Current Version Published: 2002-08-06.
Allen, T.J.; Sherkat, N.; Whitrow, R.J . “Holistic word case recognition using a multi-layer perceptron neural network”. Document Image Processing and Multimedia (Ref. No. 1999/041), IEEE Colloquium on Volume. On pp(s):9/1 - 9/4. Issue, 1999.
Al-Badr,B. Haralick,R.M. “Segmentation – free word recognition with application to Arabic” Document Analysis and Recognition, 1995.,Proceedings of the Third International Conference..Volume:1. On pp:355-359 vol.1.1995.
Chen, C.H., DeCurtins, J.L. “Word recognition in a segmentation-free approach to OCR” Document Analysis and Recognition, 1993,Proceedings of the Second International Conference on Volume , On pp:573 – 576. Issue, 20-22 Oct 1993.
C. Weliwitage, A.Harvey, A.Jennings. “ Whole of word recognition methods for cursive script”. School of Electrical & Computer Systems Engnineering, RMIT.
Rabiner, L; Rosenberg, A.; Levinson, S. “ Considerations in dynamic time warping algorithms for discrete word recognition” Acoustics, Speech and Signal Processing, IEEE Transactions on Volume 26, On pp: 575 – 582.Issue 6, Dec 1978.
Marc-Peter Schambach Siemens AG, L&A, Frontiers in Handwriting Recognition, 2004. IWFHR-9 2004. Ninth International Workshop on digital object identifier on Volume , Issue , 26-29 Oct. 2004 on pp : 215 – 220.
Morita, M.; Sabourin, R.; Bortolozzi, F.; Suen, C.Y. “ A recognition and verification strategy for handwritten word recognition”. Document Analysis and Recognition, 2003. Issue , 3-6 Aug. 2003 On pp: 482 - 486
Rath, T.M. Manmatha, R., “Computer vision and Pattern Recognition, 2003 .PublicationDate:18-20 June 2003, Volume: 2, On pp : II-521-II-527 vol.2.
Refbacks
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution 3.0 License.