Open Access Open Access  Restricted Access Subscription Access

Character Analysis Using Space in Handwriting Image


Affiliations
1 Department of Computer Science and Engineering, RCC Institute of Information Technology, Kolkata – 700015, West Bengal, India
 

Handwriting analysis is an effective and reliable indicator of personality and behaviour. It occurs in several stages. Initially, the handwriting samples are collected on plain paper. For better appearance, pre-processing steps such as binarization and noise removal etc are performed. First step begins with considering colour image or gray scale image as an input, then thresholding converts the image into binary image and noise removal technique is also applied. Then line segmentation, word segmentation and character segmentation are performed. After each segmentation process, normalization techniques are applied for normalization purpose to find out space between lines, words and letters in handwriting images. Finally, the mean of the space between all the closed loops formed by the characters has been found out and compared with the word spaces to determine the character. This paper focuses on efficient method of space analysis in handwritten document. The proposed method based on determination of behaviour based on space analysis. The proposed method was tested on images of IAM database which detect the exact space in between lines, words and characters before and after skew normalization of a document. The experimental result shows that proposed algorithm achieves more than 63% accuracy.

Keywords

Document Image, Feature Extraction, Line Segmentation, Space Analysis, Word Segmentation.
User
Notifications
Font Size

  • Nicolas S, Paquet T, Heutte L. Text line segmentation in handwritten document using a production system. IEEE Proceedings of the 9th Int’l Workshop on Frontiers in Handwriting Recognition (IWFHR-9 2004); 2004.

  • Kedar S, Nair V, Kulkarni S. Personality identification through handwriting analysis. IJARCSSE. 2015.

  • Sarfraj M, Rasheed Z. Skew estimation and correction of text using bounding box. Fifth IEEE Conference on Computer Graphics, Imaging and Visualization; 2008. p. 259–64.

  • Srihari SN, Govindraju. Analysis of textual image using the Hough transform. Machine Vision Applications. 1989; 2:141–53.

  • Andria G, Savino M, Trotta A. Application of Wigner-Ville distribution to measurements on transient signals, instrumentation and measurement. IEEE Transactions. 1994 Apr; 43(2):187–93.

  • Otsu N. A threshold selection method from Gray level histogram. IEEE Transaction on System, Man, Cybernetics. 1979 Jan; SMC-9:62–6.

  • Niblack. An introduction to digital image processing. Englewood Cliffs, New Jersey: Prentice-Hall; 1986.

  • Plamondon R, Srihari SN. On-line and off-line handwriting recognition: A comprehensive survey. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2000 Jan; 22(1).

  • Marti U-V, Bunke H. Text line segmentation and word recognition in a system for general writer independent handwriting recognition. IEEE. 2001.

  • Roy A, Bhowmik TK, Parui SK, Roy U. A novel approach to skew detection and character segmentation for handwritten Bangla words. IEEE Proceedings of the Digital Imaging Computing: Techniques and Applications; 2005.

  • Panwar S, Nain N. A novel approach of skew normalization for handwritten text lines and words. IEEE Eighth International Conference on Signal Image Technology and Internet Based Systems; 2012.

  • Gupta JD, Chanda B. Novel methods for slope and slant correction of offline handwritten text word. 2012 IEEE Third International Conference on Emerging Applications of Information Technology (EAIT); 2012.

  • Panwar S, Nain N. Handwritten text documents binarization and skew normalization approaches. IEEE Proceedings of 4th International Conference on Intelligent Human Computer Interaction; Kharagpur, India. 2012 Dec 27-29.

  • Pastor-Pellicer J, Espana-Boquera S, Zamora-Martınez F, Castro-Bleda MJ. Handwriting normalization by zone estimation using HMM/ANNs. 2014 IEEE 14th International Conference on Frontiers in Handwriting Recognition; 2014 .

  • Roy PP, Dey P, Roy S, Pal U, Kimura F. A novel approach of bangla handwritten text recognition using HMM. 2014 IEEE 14th International Conference on Frontiers in Handwriting Recognition; 2014.

  • Mohammed bin Abdl K, Mohd Hashim SZ. Handwriting identification: A direction review. IEEE International Conference on Signal and Image Processing Applications; 2009.

  • Abdul Rahiman M, Varghese D, Manoj Kumar G. HABIT: handwritten analysis based individualistic traits prediction. International Journal of Image Processing (IJIP). 2013.

  • Simistira F, Papavassiliou V, Stafylakis T. Enhancing handwritten word segmentation by employing local spatial features. IEEE International Conference on Document Analysis and Recognition. 2011.

  • Zimmermann M, Bunke H. Automatic segmentation of the IAM Off-line Database for Handwritten English Text. IEEE. 2002.

  • Liwicki M, Bunke H. IAM-OnDB - an On-Line English Sentence Database Acquired from Handwritten Text on a Whiteboard. IEEE Proceedings of the 2005 Eight International Conference on Document Analysis and Recognition (ICDAR’05); 2005.

  • Luthy F, Varga T, Bunke H. Using Hidden Markov Models as a tool for handwritten text line segmentation. Ninth International Conference on Document Analysis and Recognition (ICDAR’2007); 2007.

  • Stafylakis T, Papavassiliou V, Katsouros V, Carayannis G. Robust text-line and word segmentation for handwritten documents images. IEEE Greek Secretariat for Research and Technology under the Program; 2008.

  • Suarez SPD, Mello CAB, Oliveira ALI, Alves VMO. Text line segmentation in images of handwritten historical documents. IEEE Image Processing Theory, Tools and Applications; 2008.

  • Gupta JD, Chanda B. A model based text line segmentation method for off-line handwritten documents. 2010 IEEE 12th International Conference on Frontiers in Handwriting Recognition; 2010.

  • Javed M, Nagabhushan P, Chaudhuri BB. Extraction of line-word-character segments directly from run-length compressed printed text-documents. IEEE; Jodhpur. 2013 Dec 18-21. ISBN:978-1-4799-1586-6.

  • Zhang X, Tan CL. Text line segmentation for handwritten documents using constrained seam carving. 2014 IEEE 14th International Conference on Frontiers in Handwriting Recognition; 2014 .

  • Zimmermann M, Bunke H. Hidden Markov Model length optimization for handwriting recognition systems. IEEE Proceedings of the Eighth International Workshop on Frontiers in Handwriting Recognition (IWFHR’02); 2002.

  • Champa HN, Ananda Kumar KR. Automated human behavior prediction through handwriting analysis. 2010 IEEE First International Conference on Integrated Intelligent Computing; 2010.

  • Papavassiliou V, Stafylakis T, Katsouros V, Carayannis G. Handwritten document image segmentation into text lines and words. Pattern Recognition. 2010 Jan; 43:369–377. DOI: 10.1016/j.patcog.2009.

  • Solihin Y, Leedham CG. Noise and background removal from handwriting images. IEEE; 1997.

  • Bal A, Saha R. An effective method for skew normalization in handwriting analysis. Proceedings of the IEEE International Conference CSNT-2016; Mar 2016.

  • Bal A, Saha R. An improved method for text segmentation and skew normalization of handwriting image. Proceedings of the Springer International Conference (ICACNI-2016); 2016 Sep.

  • Story G, O’Gorman L, Fox D, Schaper L, Jagadish H. The right pages image-based electronic library for alerting and browsing. Computer. 1992 Sep; 25(9):17–26.

  • Dounskaia N, Van Gemmert A, Stelmach GL, Leis BC. Biased wrist and finger coordination in handwriting analysis. Pattern Recognition. 2009 Oct; 9:351–60.

  • Rice L. Practical graphology or the science of reading character through handwriting. Kessinger Publishing; Sep 2010. ISBN: 10:1163173592, ISBN: 13:978-11631735.


Abstract Views: 1034

PDF Views: 477




  • Character Analysis Using Space in Handwriting Image

Abstract Views: 1034  |  PDF Views: 477

Authors

Subham Nagar
Department of Computer Science and Engineering, RCC Institute of Information Technology, Kolkata – 700015, West Bengal, India
Sudiksha Chakraborty
Department of Computer Science and Engineering, RCC Institute of Information Technology, Kolkata – 700015, West Bengal, India
Arka Sengupta
Department of Computer Science and Engineering, RCC Institute of Information Technology, Kolkata – 700015, West Bengal, India
Joymallya Maji
Department of Computer Science and Engineering, RCC Institute of Information Technology, Kolkata – 700015, West Bengal, India
Rajib Saha
Department of Computer Science and Engineering, RCC Institute of Information Technology, Kolkata – 700015, West Bengal, India

Abstract


Handwriting analysis is an effective and reliable indicator of personality and behaviour. It occurs in several stages. Initially, the handwriting samples are collected on plain paper. For better appearance, pre-processing steps such as binarization and noise removal etc are performed. First step begins with considering colour image or gray scale image as an input, then thresholding converts the image into binary image and noise removal technique is also applied. Then line segmentation, word segmentation and character segmentation are performed. After each segmentation process, normalization techniques are applied for normalization purpose to find out space between lines, words and letters in handwriting images. Finally, the mean of the space between all the closed loops formed by the characters has been found out and compared with the word spaces to determine the character. This paper focuses on efficient method of space analysis in handwritten document. The proposed method based on determination of behaviour based on space analysis. The proposed method was tested on images of IAM database which detect the exact space in between lines, words and characters before and after skew normalization of a document. The experimental result shows that proposed algorithm achieves more than 63% accuracy.

Keywords


Document Image, Feature Extraction, Line Segmentation, Space Analysis, Word Segmentation.

References