Abstract
Tamil handwritten character recognition system enormously depends on its character features. This paper deals with the feature extraction and the three ways of feature predictions that are experimented in order to grasp features from various Tamil characters possessing variations in style and shape. Shape, shape ordering and location-based instances are the features predicted from the characters. The key features of this paper are the strip tree-based hierarchical formation which deals with the shape features of the characters, the implementation of the Z-ordering algorithm for addressing the structure ordering and finally the representation of PM-Quad tree that deals with extracting locations of the character features. A hierarchical classification algorithm based on support vector machine is used for predicting the character from its character features using divide-and-conquer procedure. Proof of this work shows that this work can address more characters and its varied shapes.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Antony Robert Raj M, Abirami S (2012) A survey on tamil handwritten character recognition using OCR techniques. Second Int Conf Comput Sci Eng Appl (CCSEA) 05:115–127
Antony Robert Raj M, Abirami S (2013) Analysis of statistical feature extraction approaches used in Tamil handwritten. In: OCR 12th Tamil internet conference-INFITT, pp 144–150
Antony Robert Raj M, Abirami S (2014) Offline Tamil handwritten character recognition using chain code and zone based features. In: 13th Tamil internet conference-INFITT, pp 28–34
Antony Robert Raj M, Abirami S (2015a) Strip tree based offline Tamil handwritten character recognition. In: International conference on ICT for intelligent systems, Springer SIST 2190-3018, pp 367–374
Antony Robert Raj M, Abirami S (2015b) Offline Tamil handwritten character recognition using statistical features. AENSI J Adv Nat Appl Sci 9(6):367–374
Antony Robert Raj M, Abirami S (2015c) Hybrid features based offline Tamil handwritten character recognition. In: 14th International Tamil internet conference, vol 2313–4887, pp 360–370
Antony Robert Raj M, Abirami S (2015d) Offline Tamil handwritten character recognition using statistical based quad tree. Aust J Basic Appl Sci 10(2):103–109
Benouareth A, Ennaji A, Sellami M (2008) Semi-continuous HMMs with explicit state duration for unconstrained Arabic word modeling and recognition. Pattern Recognit Lett Elsevier 29:1742–1752
Bhattacharya U, Ghosh SK, Parui SK (2007) A two stage recognition scheme for handwritten tamil characters. Ninth Int Conf Doc Anal Recognit 1:511–515
Dana H, Ballard (1981) Strip trees: a hierarchical representation for curves. ACM, Gr Image Process 24:310–321. ISSN: 0001-0782
Das N, Reddy JM et al (2012) A statistical–topological feature combination for recognition of handwritten numerals. Appl Soft Comput Elsevier 12(2486–2495):54
Desai AA (2010) Gujarati handwritten numeral optical character reorganization through neural network. Pattern Recognit Elsevier 43:2582–2589
Dubey P, Sinthupinyo W (2010) New approach on structural feature extraction for character recognition. In: ISCIT, IEEE, pp 946–949
HP-India (2013) http://lipitk.sourceforge.net/datasets/tamilchardata.htm
Kamble PM, Hegadi RS (2015) Handwritten Marathi character recognition using R-HOG feature, Elsevier. Procedia Comput Sci 45:266–274
Lei LI, Li-liang ZHANG, Jing-fei SU (2012) Handwritten character recognition via direction string and nearest neighbor matching. J China Univ Posts Telecommun Elsevier 19(2):160–165
Liu C-L, Suen CY (2009) A new benchmark on there cognition of handwritten Bangla and Farsi numeral characters, Elsevier. Pattern Recognit 42:3287–3295
Mahmoud S (2008) Recognition of writer-independent off-line handwritten Arabic (Indian) numerals using hidden Markov models. Signal Process Elsevier 88:844–857
Nibaran Das AN, Sarkar R, Basu S et al (2015) Handwritten Bangla character recognition using a sot computing paradigm embedded in two pass approach. Pattern Recognit Elsevier 48:2054–2071
Poullot S, Buisson O, Crucianu M (2007) Z-grid-based probabilistic retrieval for scaling up content-based copy detection. In: Proceedings of the 6th ACM international conference on image and video retrieval, ACM, pp 348–355
Rajashekararadhya SV, Vanaja Ranjan P (2008a) Neural network based handwritten numeral recognition of Kannada and Telugu script. In: IEEE TENCON conference, pp 1–5
Rajashekararadhya SV, Vanaja Ranjan P (2008b) Efficient zone based feature extraction algorithm for handwritten numeral recognition of four popular South Indian scripts. Int J Theor Appl Inf Technol 4:1171–1181
Rajashekararadhya SV, Vanaja Ranjan P (2009) Zone-based hybrid feature extraction algorithm for handwritten numeral recognition of two popular Indian script. In: World congress on nature and biologically inspired computing, pp 526–530
Rajashekararadhya SV, Vanaja Ranjan P, Manhunath Aradhya VN (2008) Isolated handwritten Kannada and Tamil numeral recognition: a novel approach. In: First IEEE international conference on emerging trends in engineering and technology, pp 1192–1195
Roy PP, Bhunia AK, Das A, Dey P, Pal U (2016) HMM-based Indic handwritten word recognition using zone segmentation. Pattern Recognit 60:1057–1075
Sarkhel R, Das N, Saha AK, Nasipuri M (2016) A multi-objective approach towards cost effective isolated handwritten Bangla character and digit recognition. Pattern Recognit 58:172–189
Sarkhel R, Das N, Das A et al (2017) A multi-scale deep quad tree based feature extraction method for the recognition of isolated handwritten characters of popular indic scripts, Elsevier. Pattern Recognit 71:78–93
Shanthi N, Duraiswami K (2007) Performance comparison of different image size for recognizing unconstrained handwritten Tamil character using SVM. J Comput Sci 3(9):760–764
Shanthi N, Duraiswami K (2010) A novel SVM-based handwritten Tamil character recognition system. Springer Pattern Anal Appl 13(2):173–180
Shyni SM, Antony Robert Raj M, Abirami S (2015) Offline Tamil handwritten character recognition using sub line direction and bounding box techniques. Indian J Sci Technol 8(S7):110–116
Sigappi AN, Palanivel S, Ramalingam V (2011) Handwritten document retrieval system for Tamil language. Int J Comput Appl 31:42
Yang G, Liang H, Su Y (2013) Generating Chinese characters based on stroke splitting and feature extraction. Displays 34(4):258–269
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Communicated by V. Loia.
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Raj, M.A.R., Abirami, S. Structural representation-based off-line Tamil handwritten character recognition. Soft Comput 24, 1447–1472 (2020). https://doi.org/10.1007/s00500-019-03978-5
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-019-03978-5