BROKEN CHARACTER RESTORATION USING GRADIENT VECTOR FLOW AND BALLOON FORCE ALGORITHM

The presence of a large number of broken characters in a digital document image represents the main problem in Optical Character Recognition (OCR) of historical documents. This problem still continues a challenge for recent OCR solutions. Broken character restoration from historical documents it is substantial because these documents contain important facts and leaving them leads to losing invaluable information. Gradient Vector Flow (GVF) snake has much more capture range than traditional snake therefore widely used in image segmentation. In this paper we used balloon with triangle steps to improve GVF snake to converge of deep concavity area and Restore broken characters using the improved GVF.

[1]  Laurent D. Cohen,et al.  On active contour models and balloons , 1991, CVGIP Image Underst..

[2]  Subhagata Chattopadhyay,et al.  Recognition and Classification of Broken Characters using Feed Forward Neural Network to Enhance an OCR Solution , 2012 .

[3]  Junaed Sattar.  Snakes , Shapes and Gradient Vector Flow , 2022 .

[4]  Xun Wang,et al.  A comparative study of deformable contour methods on medical image segmentation , 2008, Image Vis. Comput..

[5]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[6]  Manoj Kumar Shukla,et al.  A study of different kinds of degradation in printed Bangla script , 2012, 2012 1st International Conference on Recent Advances in Information Technology (RAIT).

[7]  Swapna Devi,et al.  Image Segmentation Techniques , 2022 .

[8]  Jinyong Cheng,et al.  Medical Image Segmentation with Improved Gradient Vector Flow , 2012 .

[9]  Chinmoy B. Bose,et al.  Connected and degraded text recognition using hidden Markov model , 1992, Proceedings., 11th IAPR International Conference on Pattern Recognition. Vol.II. Conference B: Pattern Recognition Methodology and Systems.

[10]  Hong Yan,et al.  Reconstruction of broken handwritten digits based on structural morphological features , 2001, Pattern Recognit..

[11]  Laurence Likforman-Sulem,et al.  Recognition of degraded characters using dynamic Bayesian networks , 2008, Pattern Recognit..

[12]  Subramaniam Venkatraman.  Degradation Specific OCR , 2010 .