A New Method for Slant Calculation in Off-Line Handwriting Analysis

In this paper, we propose a new method for estimating the slant of word in handwritten text. The method allows a researcher to analyze snippets of a picture containing a few words in different lines. The main goal of the research is to present a tool to observe small changes of slant in the text during work. Student check sheets were used as a database for the research. Some changes in slant depending on speed of writing are discovered.

[1]  Basilios Gatos,et al.  An Efficient Feature Extraction and Dimensionality Reduction Scheme for Isolated Greek Handwritten Character Recognition , 2007, Ninth International Conference on Document Analysis and Recognition (ICDAR 2007).

[2]  N. Mogharreban,et al.  A combined crisp and fuzzy approach for handwriting analysis , 2004, IEEE Annual Meeting of the Fuzzy Information, 2004. Processing NAFIPS '04..

[3]  David J. C. MacKay,et al.  Information Theory, Inference, and Learning Algorithms , 2004, IEEE Transactions on Information Theory.

[4]  Shalini Puri,et al.  A survey on human personality identification on the basis of handwriting using ANN , 2017, 2017 International Conference on Inventive Systems and Control (ICISC).

[5]  D. S. Bormane,et al.  Automatic Emotion Recognition through Handwriting Analysis: A Review , 2015, 2015 International Conference on Computing Communication Control and Automation.

[6]  Matthias Abend,et al.  Handwriting Recognition Soft Computing And Probabilistic Approaches , 2016 .

[7]  Hermann Ney,et al.  Feature Extraction with Convolutional Neural Networks for Handwritten Word Recognition , 2013, 2013 12th International Conference on Document Analysis and Recognition.

[8]  K. Anandakumar,et al.  Automated Human Behavior Prediction through Handwriting Analysis , 2010, 2010 First International Conference on Integrated Intelligent Computing.