Recent Trends in Sensor Research & Technology

Offline Handwritten Sanskrit Character Recognition System

  1. R.Dinesh Kumar ✉
  2. M. Kalimuthu
  3. C. Sridhathan

Abstract

Despite technological improvements, computers still lag behind in language recognition. The majority of character recognition systems are incapable of reading cracked documents or handwritten characters or words. Sanskrit, an alphabetic script, is spoken by more than 100 million people worldwide. This study is about converting scanned handwriting images into text. This contains the steps below. The scanned image is initially segmented using a spatial space detection approach, after which the images are turned into paragraphs. Then, using histogram approaches, paragraphs are segmented into lines, words, and characters. After that, it is subjected to a Support Vector Machine (SVM) extraction technique, a supervised learning algorithm for classification and these classes are mapped onto Unicode for recognition. Finally the text is reconstructed using Unicode fonts which are subjected to readable and editable documents

Keywords

References (11)

  1. Papageorgiou C, Poggio T. A trainable system for object detection. Int J Comput Vis. 2000; 38(1): 15–33.
  2. Palit S, Chaudhuri BB. A feature-based scheme for the machine recognition of printed Devanagari script. In: Das PP, Chatterjee BN, editors. Pattern Recognition, Image processing and Computer Vision. India: Narosa Publishing House; 1995; 163–168.
  3. Jonsson K, Matas J, Kittler J, Li Y. Learning Support Vectors for face verification and recognition. In Proc IEEE Int Conf on Automatic Face and Gesture Recognition. 2000; 208–213.
  4. Bansal Veena, Sinha RMK. Integrating knowledge sources in Devanagari text recognition system. IEEE Trans Syst Man Cybern A: Syst Hum. 2000 Jul; 30(4): 500–505.
  5. Thapliya Roshan, Koizumi Hirokazu, Kodate Kashiko, Kamiya Takeshi. Parallel optical recognition of Devanagari script with feature extraction. Conference on Lasers and Electro-Optics Europe, Technical Digest 1998. IEEE, Piscataway, NJ, USA, 98CB36178. 1998; 412–413.
  6. Scholkopf B, Simard P, Smola A, Vapnik V. Prior knowledge in support vector kernels. In Advances in Neural Inf. Proc. Systems. Vol. 10. MIT Press; 1998; 640–646.
  7. Chapelle O, Haffner P, Vapnik V. SVMs for histogram-based image classification. IEEE Trans Neural Netw, special issue on Support Vectors. 1999 Sep; 10(5): 1055–1064.
  8. Chaudhuri BB, Pal U, Kundu PK. Non-word error detection and correction of an inflectional Indian language. Symposium on machine aids for translation and communication (SMATAC-96), New- Delhi. 1996 Apr 11–12.
  9. Kumar RD, Julie EG, Robinson YH, et al. Recognition of food type and calorie estimation using neural network. J Super Comput. 2021; 77(8): 8172–8193. https://doi.org/10.1007/s11227-021- 03622-w
  10. Dinesh Kumar R, Golden Julie E, Harold Robinson Y, Vimal S, Gaurav Dhiman, Murugesh Offline Handwritten Sanskrit Character Recognition System Kumar et al. © STM Journals 2022. All Rights Reserved 37 Veerasamy. Deep Convolutional Nets Learning Classification for Artistic Style Transfer. Sci Program. 2022; 2022: Article ID 2038740, 1- 9 . https://doi.org/10.1155/2022/2038740.
  11. Dinesh Kumar R, Suganthi J. Sanskrit Character Recognition System Using Neural Network. Indian J Sci Technol. 2015; 8(1): 65–69. https://doi.org/10.17485/ijst/2015/v8i1/52878.

Read more of it

Subscribe to one journal or build your own list of several. One invoice, one payment, access for a full year.

Subscribe to journals →

Publish your article

Peer-reviewed journals across every subject, with open access options. Send your manuscript to the right editor today.

Publish with us → Calculate your APC
Support