Skip to main content
Top
Published in: Neural Computing and Applications 10/2019

03-03-2018 | Original Article

Off-line Bangla handwritten word recognition: a holistic approach

Authors: Showmik Bhowmik, Samir Malakar, Ram Sarkar, Subhadip Basu, Mahantapas Kundu, Mita Nasipuri

Published in: Neural Computing and Applications | Issue 10/2019

Log in

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

Due to the cursive nature, segmentation of handwritten Bangla words into characters and also recognition of the same sometimes become a very challenging problem to the researchers. Presence of comparatively large character set along with modifiers, ascendants, descendants, and compound characters makes the segmentation task more complex. As holistic method avoids such character-level segmentation, it is generally useful for the recognition of words written in any such complex scripts. In the present work, a holistic handwritten word recognition method is developed using a feature descriptor, designed by combining different Elliptical, Tetragonal and Vertical pixel density histogram-based features. Recognition process is carried out separately using two classifiers, namely multi-layer perceptron (MLP) and support vector machine (SVM). For evaluation of the proposed method, a database of 18,000 handwritten Bangla word images, having 120 word classes, is prepared. The proposed system performs comparatively better with SVM than MLP for the prepared dataset. It has achieved 83.64% accuracy at best case and 79.38% accuracy on an average using fivefold cross-validation. The current method has also outperformed some recently reported holistic word recognition technique tested on the developed dataset. In addition to that the database, prepared in this work, is made freely available to fill the absence of a publicly available standard database for holistic Bangla word recognition.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Footnotes
1
By foreground pixels in a word image, we mean object pixels only and the rest of the pixels are considered as representing the background. In this paper, we have followed this convention.
 
Literature
1.
go back to reference Chacko BP, Krishnan VRV, Raju G, Anto PB (2012) Handwritten character recognition using wavelet energy and extreme learning machine. Int J Mach Learn Cybern 3(2):149–161CrossRef Chacko BP, Krishnan VRV, Raju G, Anto PB (2012) Handwritten character recognition using wavelet energy and extreme learning machine. Int J Mach Learn Cybern 3(2):149–161CrossRef
2.
go back to reference Prasad JR, Kulkarni U (2015) Gujrati character recognition using weighted k-NN and mean χ2 distance measure. Int J Mach Learn Cybern 6(1):69–82CrossRef Prasad JR, Kulkarni U (2015) Gujrati character recognition using weighted k-NN and mean χ2 distance measure. Int J Mach Learn Cybern 6(1):69–82CrossRef
3.
go back to reference Pal U, Roy K, Kimura F (2009) A lexicon-driven handwritten city-name ecognition scheme for Indian postal automation. IEICE Trans Inf Syst 92(5):1146–1158CrossRef Pal U, Roy K, Kimura F (2009) A lexicon-driven handwritten city-name ecognition scheme for Indian postal automation. IEICE Trans Inf Syst 92(5):1146–1158CrossRef
4.
go back to reference Pal U, Roy RK, Kimura F (2012) Multi-lingual city name recognition for Indian postal automation. In: 2012 international conference on frontiers in handwriting recognition (ICFHR), pp 169–173 Pal U, Roy RK, Kimura F (2012) Multi-lingual city name recognition for Indian postal automation. In: 2012 international conference on frontiers in handwriting recognition (ICFHR), pp 169–173
5.
go back to reference Morita M, El Yacoubi A, Sabourin R, Bortolozzi F, Suen CY (2001) Handwritten month word recognition on Brazilian bank cheques. In: Sixth international conference on document analysis and recognition. Proceedings, pp 972–976 Morita M, El Yacoubi A, Sabourin R, Bortolozzi F, Suen CY (2001) Handwritten month word recognition on Brazilian bank cheques. In: Sixth international conference on document analysis and recognition. Proceedings, pp 972–976
6.
go back to reference Bunke H, Bengio S, Vinciarelli A (2004) Offline recognition of unconstrained handwritten texts using HMMs and statistical language models. IEEE Trans Pattern Anal Mach Intell 26(6):709–720CrossRef Bunke H, Bengio S, Vinciarelli A (2004) Offline recognition of unconstrained handwritten texts using HMMs and statistical language models. IEEE Trans Pattern Anal Mach Intell 26(6):709–720CrossRef
7.
go back to reference Madhvanath S, Govindaraju V, Ramanaprasad V, Lee D-S, Srihari SN (1995) Reading handwritten US census forms. In: Proceedings of the third international conference on document analysis and recognition, vol 1, pp 82–85 Madhvanath S, Govindaraju V, Ramanaprasad V, Lee D-S, Srihari SN (1995) Reading handwritten US census forms. In: Proceedings of the third international conference on document analysis and recognition, vol 1, pp 82–85
8.
go back to reference Srihari SN, Shin YC, Ramanaprasad V, Lee D-S (1995) Name and address block reader system for tax form processing. In: Proceedings of the third international conference on document analysis and recognition, vol 1, pp 5–10 Srihari SN, Shin YC, Ramanaprasad V, Lee D-S (1995) Name and address block reader system for tax form processing. In: Proceedings of the third international conference on document analysis and recognition, vol 1, pp 5–10
9.
go back to reference Prasad JR, Kulkarni U (2015) Gujarati character recognition using adaptive neuro fuzzy classifier with fuzzy hedges. Int J Mach Learn Cybern 6(5):763–775CrossRef Prasad JR, Kulkarni U (2015) Gujarati character recognition using adaptive neuro fuzzy classifier with fuzzy hedges. Int J Mach Learn Cybern 6(5):763–775CrossRef
10.
go back to reference Broumandnia A, Shanbehzadeh J, Varnoosfaderani MR (2008) Persian/arabic handwritten word recognition using M-band packet wavelet transform. Image Vis Comput 26(6):829–842CrossRef Broumandnia A, Shanbehzadeh J, Varnoosfaderani MR (2008) Persian/arabic handwritten word recognition using M-band packet wavelet transform. Image Vis Comput 26(6):829–842CrossRef
11.
go back to reference El Qacimy B, Kerroum MA, Hammouch A (2015) Word-based Arabic handwritten recognition using SVM classifier with a reject option. In: 2015 15th international conference on intelligent systems design and applications (ISDA), pp 64–68 El Qacimy B, Kerroum MA, Hammouch A (2015) Word-based Arabic handwritten recognition using SVM classifier with a reject option. In: 2015 15th international conference on intelligent systems design and applications (ISDA), pp 64–68
12.
go back to reference Dehghan M, Faez K, Ahmadi M, Shridhar M (2001) Handwritten Farsi (Arabic) word recognition: a holistic approach using discrete HMM. Pattern Recognit 34(5):1057–1065CrossRef Dehghan M, Faez K, Ahmadi M, Shridhar M (2001) Handwritten Farsi (Arabic) word recognition: a holistic approach using discrete HMM. Pattern Recognit 34(5):1057–1065CrossRef
13.
go back to reference Liu C-L, Koga M, Fujisawa H (2002) Lexicon-driven segmentation and recognition of handwritten character strings for Japanese address reading. IEEE Trans Pattern Anal Mach Intell 24(11):1425–1437CrossRef Liu C-L, Koga M, Fujisawa H (2002) Lexicon-driven segmentation and recognition of handwritten character strings for Japanese address reading. IEEE Trans Pattern Anal Mach Intell 24(11):1425–1437CrossRef
14.
go back to reference Su T (2013) Chinese handwriting recognition: an algorithmic perspective. Springer, BerlinCrossRef Su T (2013) Chinese handwriting recognition: an algorithmic perspective. Springer, BerlinCrossRef
15.
go back to reference Srihari SN, Yang X, Ball GR (2007) Offline Chinese handwriting recognition: an assessment of current technology. Front Comput Sci China 1(2):137–155CrossRef Srihari SN, Yang X, Ball GR (2007) Offline Chinese handwriting recognition: an assessment of current technology. Front Comput Sci China 1(2):137–155CrossRef
16.
go back to reference Koerich AL, Sabourin R, Suen CY (2005) Recognition and verification of unconstrained handwritten words. IEEE Trans Pattern Anal Mach Intell 27(10):1509–1522CrossRef Koerich AL, Sabourin R, Suen CY (2005) Recognition and verification of unconstrained handwritten words. IEEE Trans Pattern Anal Mach Intell 27(10):1509–1522CrossRef
17.
go back to reference Bunke H (2003) Recognition of cursive Roman handwriting: past, present and future. In: Seventh international conference on document analysis and recognition. Proceedings, pp 448–459 Bunke H (2003) Recognition of cursive Roman handwriting: past, present and future. In: Seventh international conference on document analysis and recognition. Proceedings, pp 448–459
18.
go back to reference Bozinovic RM, Srihari SN (1989) Off-line cursive script word recognition. IEEE Trans Pattern Anal Mach Intell 11(1):68–83CrossRef Bozinovic RM, Srihari SN (1989) Off-line cursive script word recognition. IEEE Trans Pattern Anal Mach Intell 11(1):68–83CrossRef
20.
go back to reference Das N, Sarkar R, Basu S, Saha PK, Kundu M, Nasipuri M (2015) Handwritten Bangla character recognition using a soft computing paradigm embedded in two pass approach. Pattern Recognit 48(6):2054–2071CrossRef Das N, Sarkar R, Basu S, Saha PK, Kundu M, Nasipuri M (2015) Handwritten Bangla character recognition using a soft computing paradigm embedded in two pass approach. Pattern Recognit 48(6):2054–2071CrossRef
21.
go back to reference Rahman MM, Akhand MAH, Islam S, Shill PC, Rahman MMH (2015) Bangla handwritten character recognition using convolutional neural network. Int J Image Graph Signal Process 7(8):42CrossRef Rahman MM, Akhand MAH, Islam S, Shill PC, Rahman MMH (2015) Bangla handwritten character recognition using convolutional neural network. Int J Image Graph Signal Process 7(8):42CrossRef
22.
go back to reference Das N, Basu S, Saha PK, Sarkar R, Kundu M, Nasipuri M (2015) A GA based approach for selection of local features for recognition of handwritten Bangla numerals. arXiv Prepr. arXiv:1501.05495 Das N, Basu S, Saha PK, Sarkar R, Kundu M, Nasipuri M (2015) A GA based approach for selection of local features for recognition of handwritten Bangla numerals. arXiv Prepr. arXiv:​1501.​05495
23.
go back to reference Plamondon R, Srihari SN (2000) Online and off-line handwriting recognition: a comprehensive survey. IEEE Trans Pattern Anal Mach Intell 22(1):63–84CrossRef Plamondon R, Srihari SN (2000) Online and off-line handwriting recognition: a comprehensive survey. IEEE Trans Pattern Anal Mach Intell 22(1):63–84CrossRef
24.
go back to reference Tappert CC, Suen CY, Wakahara T (1990) The state of the art in online handwriting recognition. IEEE Trans Pattern Anal Mach Intell 12(8):787–808CrossRef Tappert CC, Suen CY, Wakahara T (1990) The state of the art in online handwriting recognition. IEEE Trans Pattern Anal Mach Intell 12(8):787–808CrossRef
25.
go back to reference Ruiz-Pinales J, Jaime-Rivas R, Castro-Bleda MJ (2007) Holistic cursive word recognition based on perceptual features. Pattern Recognit Lett 28(13):1600–1609CrossRef Ruiz-Pinales J, Jaime-Rivas R, Castro-Bleda MJ (2007) Holistic cursive word recognition based on perceptual features. Pattern Recognit Lett 28(13):1600–1609CrossRef
26.
go back to reference Dasgupta J, Bhattacharya K, Chanda B (2016) A holistic approach for Off-line handwritten cursive word recognition using directional feature based on Arnold transform. Pattern Recognit Lett 79:73–79CrossRef Dasgupta J, Bhattacharya K, Chanda B (2016) A holistic approach for Off-line handwritten cursive word recognition using directional feature based on Arnold transform. Pattern Recognit Lett 79:73–79CrossRef
27.
go back to reference Koerich AL, Sabourin R, Suen CY (2003) Large vocabulary off-line handwriting recognition: a survey. Pattern Anal Appl 6(2):97–121MathSciNetCrossRef Koerich AL, Sabourin R, Suen CY (2003) Large vocabulary off-line handwriting recognition: a survey. Pattern Anal Appl 6(2):97–121MathSciNetCrossRef
28.
go back to reference Plötz T, Fink GA (2009) Markov models for offline handwriting recognition: a survey. Int J Doc Anal Recognit 12(4):269–298CrossRef Plötz T, Fink GA (2009) Markov models for offline handwriting recognition: a survey. Int J Doc Anal Recognit 12(4):269–298CrossRef
29.
go back to reference Madhvanath S, Govindaraju V (2001) The role of holistic paradigms in handwritten word recognition. IEEE Trans Pattern Anal Mach Intell 23(2):149–164CrossRef Madhvanath S, Govindaraju V (2001) The role of holistic paradigms in handwritten word recognition. IEEE Trans Pattern Anal Mach Intell 23(2):149–164CrossRef
30.
go back to reference Madhvanath S, Kleinberg E, Govindaraju V (1999) Holistic verification of handwritten phrases. IEEE Trans Pattern Anal Mach Intell 21(12):1344–1356CrossRef Madhvanath S, Kleinberg E, Govindaraju V (1999) Holistic verification of handwritten phrases. IEEE Trans Pattern Anal Mach Intell 21(12):1344–1356CrossRef
31.
go back to reference Malakar S, Sharma P, Singh PK, Das M, Sarkar R, Nasipuri M (2017) A holistic approach for handwritten hindi word recognition. Int J Comput Vi. Image Process 7(1):59–78CrossRef Malakar S, Sharma P, Singh PK, Das M, Sarkar R, Nasipuri M (2017) A holistic approach for handwritten hindi word recognition. Int J Comput Vi. Image Process 7(1):59–78CrossRef
32.
go back to reference Tamen Z, Drias H, Boughaci D (2017) An efficient multiple classifier system for Arabic handwritten words recognition. Pattern Recognit Lett 93:123–132CrossRef Tamen Z, Drias H, Boughaci D (2017) An efficient multiple classifier system for Arabic handwritten words recognition. Pattern Recognit Lett 93:123–132CrossRef
33.
go back to reference Pechwitz M, Maddouri SS, Märgner V, Ellouze N, Amiri H (2002) IFN/ENIT-database of handwritten Arabic words. Proc CIFED 2:127–136 Pechwitz M, Maddouri SS, Märgner V, Ellouze N, Amiri H (2002) IFN/ENIT-database of handwritten Arabic words. Proc CIFED 2:127–136
34.
go back to reference Roy PP, Dey P, Roy S, Pal U, Kimura F (2014) A novel approach of Bangla handwritten text recognition using HMM. In: 2014 14th international conference on frontiers in handwriting recognition (ICFHR), pp 661–666 Roy PP, Dey P, Roy S, Pal U, Kimura F (2014) A novel approach of Bangla handwritten text recognition using HMM. In: 2014 14th international conference on frontiers in handwriting recognition (ICFHR), pp 661–666
35.
go back to reference Roy PP, Bhunia AK, Das A, Dey P, Pal U (2016) HMM-based Indic handwritten word recognition using zone segmentation. Pattern Recognit 60:1057–1075CrossRef Roy PP, Bhunia AK, Das A, Dey P, Pal U (2016) HMM-based Indic handwritten word recognition using zone segmentation. Pattern Recognit 60:1057–1075CrossRef
36.
go back to reference Vajda S, Roy K, Pal U, Chaudhuri BB, Belaid A (2009) Automation of Indian postal documents written in Bangla and English. Int J Pattern Recognit Artif Intell 23(8):1599–1632CrossRef Vajda S, Roy K, Pal U, Chaudhuri BB, Belaid A (2009) Automation of Indian postal documents written in Bangla and English. Int J Pattern Recognit Artif Intell 23(8):1599–1632CrossRef
37.
go back to reference Bhowmik TK, Roy U, Parui SK (2012) Lexicon reduction technique for Bangla handwritten word recognition. In: 2012 10th IAPR international workshop on document analysis systems (DAS), pp 195–199 Bhowmik TK, Roy U, Parui SK (2012) Lexicon reduction technique for Bangla handwritten word recognition. In: 2012 10th IAPR international workshop on document analysis systems (DAS), pp 195–199
38.
go back to reference Bhowmik TK, Parui SK, Roy U (2008) Discriminative HMM training with GA for handwritten word recognition. In: ICPR 2008. 19th international conference on pattern recognition, pp 1–4 Bhowmik TK, Parui SK, Roy U (2008) Discriminative HMM training with GA for handwritten word recognition. In: ICPR 2008. 19th international conference on pattern recognition, pp 1–4
39.
go back to reference Bhowmik S, Roushan MG, Sarkar R, Nasipuri M, Polley S, Malakar S (2014) Handwritten Bangla word recognition using HOG descriptor. In: Proceedings—4th international conference on emerging applications of information technology, EAIT Bhowmik S, Roushan MG, Sarkar R, Nasipuri M, Polley S, Malakar S (2014) Handwritten Bangla word recognition using HOG descriptor. In: Proceedings—4th international conference on emerging applications of information technology, EAIT
40.
go back to reference Bhowmik S, Malakar S, Sarkar R, Nasipuri M (2014) Handwritten Bangla word recognition using elliptical features. In: 2014 international conference on computational intelligence and communication networks (CICN), pp 257–261 Bhowmik S, Malakar S, Sarkar R, Nasipuri M (2014) Handwritten Bangla word recognition using elliptical features. In: 2014 international conference on computational intelligence and communication networks (CICN), pp 257–261
41.
go back to reference Bhowmik S, Polley S, Roushan MG, Malakar S, Sarkar R, Nasipuri M (2015) A holistic word recognition technique for handwritten Bangla words. Int J Appl Pattern Recognit 2(2):142–159CrossRef Bhowmik S, Polley S, Roushan MG, Malakar S, Sarkar R, Nasipuri M (2015) A holistic word recognition technique for handwritten Bangla words. Int J Appl Pattern Recognit 2(2):142–159CrossRef
42.
go back to reference Barua S, Malakar S, Bhowmik S, Sarkar R, Nasipuri M (2017) Bangla handwritten city name recognition using gradient-based feature, vol 515 Barua S, Malakar S, Bhowmik S, Sarkar R, Nasipuri M (2017) Bangla handwritten city name recognition using gradient-based feature, vol 515
43.
go back to reference Ghosh M, Malakar S, Bhowmik S, Sarkar R, Nasipuri M (2017) Memetic algorithm based feature selection for handwritten city name recognition, vol 776 Ghosh M, Malakar S, Bhowmik S, Sarkar R, Nasipuri M (2017) Memetic algorithm based feature selection for handwritten city name recognition, vol 776
44.
go back to reference Ban JC (2015) Neural network equations and symbolic dynamics. Int J Mach Learn Cybern 6(4):567–579CrossRef Ban JC (2015) Neural network equations and symbolic dynamics. Int J Mach Learn Cybern 6(4):567–579CrossRef
45.
go back to reference Li Z, Zhou M, Lin H, Pu H (2014) A two stages sparse SVM training. Int J Mach Learn Cybern 5(3):425–434CrossRef Li Z, Zhou M, Lin H, Pu H (2014) A two stages sparse SVM training. Int J Mach Learn Cybern 5(3):425–434CrossRef
46.
go back to reference Liu CL, Koga M, Fujisawa H (2005) Gabor feature extraction for character recognition: comparison with gradient feature. In: Eighth international conference on document analysis and recognition (ICDAR’05), pp 121–125 Liu CL, Koga M, Fujisawa H (2005) Gabor feature extraction for character recognition: comparison with gradient feature. In: Eighth international conference on document analysis and recognition (ICDAR’05), pp 121–125
47.
go back to reference Sarkar R, Das N, Basu S, Kundu M, Nasipuri M, Basu DK (2012) CMATERdb1: a database of unconstrained handwritten Bangla and Bangla-English mixed script document image. Int J Doc Anal Recognit 15(1):71–83CrossRef Sarkar R, Das N, Basu S, Kundu M, Nasipuri M, Basu DK (2012) CMATERdb1: a database of unconstrained handwritten Bangla and Bangla-English mixed script document image. Int J Doc Anal Recognit 15(1):71–83CrossRef
49.
go back to reference Otsu N (1975) A threshold selection method from gray-level histograms. Automatica 11(285–296):23–27 Otsu N (1975) A threshold selection method from gray-level histograms. Automatica 11(285–296):23–27
50.
go back to reference Soille P (2005) Erosion and dilation. In: Morphological image analysis. Springer, pp 63–103 Soille P (2005) Erosion and dilation. In: Morphological image analysis. Springer, pp 63–103
51.
go back to reference Yang M, Kpalma K, Ronsin J (2008) A survey of shape feature extraction techniques. IN-TECH Yang M, Kpalma K, Ronsin J (2008) A survey of shape feature extraction techniques. IN-TECH
52.
go back to reference Smith TC, Frank E (2016) Introducing machine learning concepts with WEKA. Stat Genomics Methods Protoc 1418:353–378CrossRef Smith TC, Frank E (2016) Introducing machine learning concepts with WEKA. Stat Genomics Methods Protoc 1418:353–378CrossRef
53.
go back to reference Bhunia AK, Das A, Roy PP, Pal U (2015) A comparative study of features for handwritten Bangla text recognition. In: 2015 13th international conference on document analysis and recognition (ICDAR), pp 636–640 Bhunia AK, Das A, Roy PP, Pal U (2015) A comparative study of features for handwritten Bangla text recognition. In: 2015 13th international conference on document analysis and recognition (ICDAR), pp 636–640
Metadata
Title
Off-line Bangla handwritten word recognition: a holistic approach
Authors
Showmik Bhowmik
Samir Malakar
Ram Sarkar
Subhadip Basu
Mahantapas Kundu
Mita Nasipuri
Publication date
03-03-2018
Publisher
Springer London
Published in
Neural Computing and Applications / Issue 10/2019
Print ISSN: 0941-0643
Electronic ISSN: 1433-3058
DOI
https://doi.org/10.1007/s00521-018-3389-1

Other articles of this Issue 10/2019

Neural Computing and Applications 10/2019 Go to the issue

Premium Partner