The week's pick
Random Articles
Reseach Article
Analysis of Feature Generated of Marathi Word
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 91 - Number 2 |
| Year of Publication: 2014 |
| Authors: C. Namrata Mahender, K. V. Kale |
10.5120/15850-4743
|
C. Namrata Mahender, K. V. Kale . Analysis of Feature Generated of Marathi Word. International Journal of Computer Applications. 91, 2 ( April 2014), 1-4. DOI=10.5120/15850-4743
Abstract
A continuous segmentation approach is used to get the isolated letters or pseudo character from the handwritten word for feature extraction. The preprocessing is done using morphological operation to remove noise, compress and provide smoother way for Feature extraction. To get better results Invariant moments (IM) are applied for feature extraction once preprocessing and segmentation is over because invariant moments are insensitive to translation, scale change, mirroring, and rotation. After segmentation it is often necessary to evaluate the quality of the image for that objective quality measure like mean and standard deviation are used and to see the relevance of our features for post-processing, correlation between the average of the group of similar pseudo-unit and sample of the similar pseudo-unit is calculated.
References
- Verma, B. , Blumenstein, M. , Kukarni, S, 1998, "Recent Achievements in Off-line Handwriting Recognition Systems. " International Conference on Computational Intelligence and Multimedia Applications, Australia.
- E. Kavallieratou N. Fakotakis G. Kokkinakis, 1999, "New Algorithms For Skewing Correction And Slant Removal On Word-Level (OCR)". The 6th IEEE International Conference on Electronics, Circuits and Systems, Vol 2, 1159 - 1162.
- Hasan Al-Rashaideh, 2006, "Preprocessing phase for Arabic Word Handwritten Recognition", Information Transmissions in Computer Networks, 11-19.
- S. Madhvanath and V. Govidaraju, 2001, "The Role of Holistic Paradigms in Handwritten Word Recognition", IEEE PAMI, Vol. 23, No. 2, 149-164.
- Celebi, M. E. and Aslandogan Y. A. , 2005, "A comparative study of three moment-based shape descriptors", Information Technology: Coding and Computing, International Conference, Vol 1, 788-793.
- Gonzalez, Woods, and Eddins, 2004, "Digital Image Processing Using Matlab", Prentice Hall, 470-472.
- K. Karacs and T. Roska, 2004, "Holistic Feature extraction from handwritten words on wave computers", Cellular Neural Networks and their Applications. Proceedings of the 8th IEEE international workshop Budapest, 364-369.
- S. Madhvanath, kim. G and Govindaraju,V, 1997," Chain code Processing for handwritten Word Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence vol 21, 928- 932.
- Feng Pan and Mike Keane, 1994, "A New Set of Moment Invariants for Handwritten Numeral Recognition. Proceedings 1994, International Conference on Image Processing, Austin, Texas, USA, November 13-16, IEEE Computer Society.
- R. M. Bozinovic, and S. N. Srihari, 1980, "Off-Line Cursive Script Word Recognition", IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 11, 68-83.
- K. V. Kale,,R. R. Manza,S. S. Gornale,P. D. Deshmukh and Vikas Humbe, 2006, SWT Based Composite Method For Fingerprint Image Enhancement, 27-30.
- M. Blumenstein ,L. B. Verma,1999, Neural Based Solution For The Segmentation And Recognition Of Difficult Handwritten Words From Benchmark Database. Document Analysis and Recognition, 1999. ICDAR '99. proceedings of the Fifth International Conference,281-284
- C. Namrata Mahender and K. V. Kale, 2006, "Preprocessing of Offline Handwritten Marathi Word", Proceeding in National Conference on Image Processing, NCIP-2006, Pandharpur India, 24-25th December 2006.
Index Terms
Keywords