A Bengali Handwritten Vowels Recognition Scheme Based on the Detection of Structural Anatomy of the Characters

  • Priyanka DasEmail author
  • Tanmoy Dasgupta
  • Samar Bhattacharya
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 518)


The present paper describes the development of a novel scheme for recognising Bengali handwritten vowels using mathematical morphology where the characters are first categorised on the basis of their anatomical features. The scanned images of the characters are passed through a weighted decision tree which is designed to analyse the feature set present in them. Based on the detected features, the algorithms easily recognise the individual characters. The extraction of some features has been carried out by generating the curvature scale spaces for the characters. The treatment is performed on scanned binary images of the handwritten characters to detect anatomical features such as ‘bowl’, ‘lobe’ and ‘arm’. The scheme developed here is very fast and it does not need training samples to work.


Handwritten character recognition Curvature scale space Mathematical morphology 


  1. 1.
    Chandra, S., Bokil, P., Udaya Kumar, D.: Anatomy of bengali letterforms: A semiotic study. In Chakrabarti, A., ed.: ICoRD15 Research into Design Across Boundaries Volume 1. Volume 34 of Smart Innovation, Systems and Technologies. Springer India (2015) 237–247Google Scholar
  2. 2.
    Ross, F., Shaw, G.: Non-Latin scripts From metal to digital type. St. Bride Foundation, London (2012)Google Scholar
  3. 3.
    Ghosh, P.K.: An approach to type design and text composition in indian scripts. Technical report, Stanford, CA, USA (1983)Google Scholar
  4. 4.
    Sinha, R.: A journey from indian scripts processing to indian language processing. Annals of the History of Computing, IEEE 31(1) (2009) 8–31MathSciNetCrossRefGoogle Scholar
  5. 5.
    Pal, U., Chaudhuri, B.B., Belaïd, A.: A system for bangla handwritten numeral recognition. IETE Journal of Research, Institution of Electronics and Telecommunication Engineers 52(1) (2006) 27–34Google Scholar
  6. 6.
    Mandal, S., Sur, S., Dan, A., Bhowmick, P.: Handwritten bangla character recognition in machine-printed forms using gradient information and haar wavelet. In: Image Information Processing (ICIIP), 2011 International Conference on. (2011) 1–6Google Scholar
  7. 7.
    Das, P., Dasgupta, T., Bhattacharya, S.: A novel scheme for bengali handwriting recognition based on morphological operations with adaptive auto-generated structuring elements. In: 2nd International Conference on Control, Instrumentation, Energy and Communication (CIEC16). (2016) 211–215Google Scholar
  8. 8.
    Jalba, A.C., Wilkinson, M.H.F., Roerdink, J.B.T.M.: Shape representation and recognition through morphological curvature spaces. IEEE Transactions On Image Processing 15(2) (2006) 331–341CrossRefGoogle Scholar
  9. 9.
    Lindeberg, T.: Scale-space theory:a basic tool for analyzing structures at different scales. International Journal Of Computer Vision 11(3) (1993) 283–318CrossRefGoogle Scholar
  10. 10.
    Lindeberg: Feature detection with automatic scale selection. International Journal Of Computer Vision 30(2) (1998)Google Scholar
  11. 11.
    Anand, C. S., Tamilarasan.M, Arjun.P: A study on curvature scale space. International Journal Of Innovative Research in Computer and Communication Engineering 2(3) (2014)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  • Priyanka Das
    • 1
    Email author
  • Tanmoy Dasgupta
    • 2
  • Samar Bhattacharya
    • 2
  1. 1.Department of Electronics and Communication EngineeringTechno India UniversityKolkataIndia
  2. 2.Department of Electrical EngineeringJadavpur UniversityKolkataIndia

Personalised recommendations