NORMALIZATION OF HANDWRITTEN WORD IMAGES BEFORE RECOGNITION

In the paper we are considering pre-treatment the handwritten words images before being recognition. The difficulty lies in the phase image features of handwritten words , compared with a printed text , as expressed in the presence of the upper and lower graphic elements. An important criterion is the quality of reforms carried out by the absence of additional distortions. We are offering an algorithm for normalization image of the word with image rotation compensation.

1. Papandreou, B. Gatos Slant estimation and core-region detection for handwritten Latin words // Pattern Recognition Letters 35 (2014) S. 16–22.

2. A.H. Toselli, Integrated Handwriting Recognition and Interpretation using Finite-State Models [Text] // IJPRAI, vol. 18, no. 4, 2004, P. 519-539.

3. M.P. Krivenko, Pre-processing for text recognition according to the image of low quality // Informatics and its applications, 2012.V. 6. Issue. 4.P. 49-56.

4. P. Slavik, Equivalence of different methods for slant and skew corrections in word recognition applications // IEEE Trans. PAMI, 2001, P. 323-326.

5. J. Russell, R. Cohn Оператор Собеля // Книга по требованию, 2013, 106с.

6. E. Kavallieratou, N. Fakotakis, G. Kokkinakis Slant estimation algorithm for OCR systems // Pattern Recognition 34 (2001) С. 2515-2522.

7. M. Pastor, A. Toselli, E. Vidal Projection profile based algorithm for slant removal // Image Analysis and Recognition, Springer, 2004, С. 183–190.

8. Papandreou, B. Gatos Word Slant Estimation using Non-Horizontal Character Parts and Core-Region information // 10th IAPR International Workshop on Document Analysis Systems, 2012.

9. А.А. Мозговой Преобразование Хафа в задачах автоматического распознавания рукописного текста // Вестник Воронежского института высоких технологий 2012. №9. С. 62-64.

10. J. Pradeep, E. Srinivasan, S. Himavathi Diagonal based feature extraction for handwritten alphabets recognition system using neural network // International Journal of Computer Science & Information Technology (IJCSIT), Vol 3, No 1, Feb 2011, P. 27-38.

11. V.P. Agnihotri Offline Handwritten Devanagari Script Recognition // Information Technology and Computer Science, 2012, vol. 8, P. 37-42.

12. P. Singh, S. Budhiraja Feature Extraction and Classification Techniques in O.C.R. Systems for Handwritten Gurmukhi Script – A Survey // International Journal of Engineering Research and Applications Vol. 1, Issue 4, 2012, P. 1736-1739.

13. S. Saha, N. Paul, S.K. Das, S. Kundu Optical Character Recognition using 40-point Feature Extraction and Artificial Neural Network // International Journal of Advanced Research in Computer Science and Software Engineering, Volume 3, Issue 4, April 2013, P. 495-502.

14. Р.A. Гонсалес, Р. Вудс Цифровая обработка изображений // Морфологическая обработка изображений. – М.:Техносфера, 2006.

15. Mrinaljit, M.K. Ghose A Survey onselected slant estimation and removal techniques // Volume-1, Issue-3, 8th August-2013.