Recognition of Handwritten English Text U Minimisation

In handwritten character recognition one of the most challenging task is segmentation. This is mainly due to different challenges like skewness of textlines, overlapping characters, connected components etc. This paper proposes a character recognition method of handwritten English documents. The textlines are segmented based on information energy that is calculated for every pixel in the scanned document and the characters are recognized using Artificial Neural Network (ANN). The recognition has an accuracy of almost 92 %. The proposed method can also be further improved to work on other languages as well as increase the accuracy.

[1]  Neeta Nain,et al.  Cursive stroke sequencing for handwritten text documents recognition , 2013, 2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG).

[2]  Radu Ioanitescu,et al.  Handwritten Documents Text Line Segmentation based on Information Energy , 2014, Int. J. Comput. Commun. Control.

[3]  Goutam Sanyal,et al.  HMM based Offline Handwritten Writer Independent English Character Recognition using Global and Local Feature Extraction , 2012 .

[4]  Laurence Likforman-Sulem,et al.  A Hough based algorithm for extracting text lines in handwritten documents , 1995, Proceedings of 3rd International Conference on Document Analysis and Recognition.

[5]  Xi Zhang,et al.  Text Line Segmentation for Handwritten Documents Using Constrained Seam Carving , 2014, 2014 14th International Conference on Frontiers in Handwriting Recognition.

[6]  Umapada Pal,et al.  Multi-Oriented and Multi-Sized Touching Character Segmentation Using Dynamic Programming , 2009, 2009 10th International Conference on Document Analysis and Recognition.

[7]  Luiz Eduardo Soares de Oliveira,et al.  An implicit segmentation-based method for recognition of handwritten strings of characters , 2006, SAC.

[8]  R. Manmatha,et al.  A scale space approach for automatically segmenting words from historical handwritten documents , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  David D. Palmer,et al.  A Trainable Rule-Based Algorithm for Word Segmentation , 1997, ACL.

[10]  Nikos Fakotakis,et al.  Handwritten character recognition based on structural characteristics , 2002, Object recognition supported by user interaction for service robots.

[11]  Fei Yin,et al.  Handwritten text line extraction based on minimum spanning tree clustering , 2007, 2007 International Conference on Wavelet Analysis and Pattern Recognition.

[12]  Tien D. Bui,et al.  Text line segmentation in handwritten documents using Mumford-Shah model , 2009, Pattern Recognit..

[13]  Venu Govindaraju,et al.  Markov Random Field Based Text Identification from Annotated Machine Printed Documents , 2009, 2009 10th International Conference on Document Analysis and Recognition.

[14]  Syed Saqib Bukhari,et al.  Script-Independent Handwritten Textlines Segmentation Using Active Contours , 2009, 2009 10th International Conference on Document Analysis and Recognition.