Brahmi character recognition based on SVM (support vector machine) classifier using image gradient features

Abstract Understanding the ancient script can provide rich details of a civilization, like its cultural, political and social scenarios. Brahmi, an ancient mother script, has been a key to the development of many modern Indian scripts like Gurmukhi, Devanagari, Bangla etc. Inferring ancient writings can be a tedious job and moreover, if executed manually, it requires several language experts. The current paper presents a recognition system for Brahmi characters using linear Support Vector machine classifier. Gradient information of the character images pixels is extracted, and histogram of the gradients is stored as a feature vector for each character image. Character dataset includes both handwritten character images and images from the internet. Linear SVM classifier is trained on the feature set of 24 images of each character. The proposed recognition system is performed with an accuracy of 91.6% to recognize the Brahmi characters from the test images.

[1]  Yafang Xue,et al.  Optical Character Recognition , 2022 .

[2]  Vinodh Rajan Sampath,et al.  Quantifying scribal behavior : a novel approach to digital paleography , 2016 .

[3]  Giuseppe Pirlo,et al.  Script Identification of Multi-Script Documents: A Survey , 2017, IEEE Access.

[4]  Wahengbam Kanan Kumar,et al.  Increasing the effectiveness of handwritten Manipuri Meetei-Mayek character recognition using multiple-HOG-feature descriptors , 2019, Sādhanā.

[5]  SOUMEN BAG,et al.  A survey on optical character recognition for Bangla and Devanagari scripts , 2013, Sadhana.

[6]  Umapada Pal,et al.  A comparative study of features for handwritten Bangla text recognition , 2015, 2015 13th International Conference on Document Analysis and Recognition (ICDAR).

[7]  Vijay H. Mankar,et al.  A Review of Research on Devnagari Character Recognition , 2010, ArXiv.

[8]  Lambert Schomaker,et al.  Recognition of handwritten characters using local gradient feature descriptors , 2015, Eng. Appl. Artif. Intell..

[9]  Venu Govindaraju,et al.  Guide to OCR for Indic Scripts , 2010 .

[10]  Ching Y. Suen,et al.  A new benchmark on the recognition of handwritten Bangla and Farsi numeral characters , 2009, Pattern Recognit..

[11]  A. K. Datta.  A Generalized Formal Approach for Description and Analysis of Major Indian Scripts , 1984 .

[12]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[13]  H. Devi.  Thinning: A Preprocessing Technique for an OCR System for the Brahmi Script , 2006 .

[14]  Santanu Chaudhury,et al.  Recognizing ancient Sinhala Inscription Characters using Neural Network Technologies , 2017 .

[15]  Noor A. Jebril,et al.  Recognition of Handwritten Arabic Characters using Histograms of Oriented Gradient (HOG) , 2018 .

[16]  Satoru Ozawa,et al.  Creation of precise alphabet fonts of early Brahmi script from photographic data of ancient Sri Lankan inscriptions , 2012 .

[17]  Tetsushi Wakabayashi,et al.  Handwritten Bangla Compound Character Recognition Using Gradient Feature , 2007, 10th International Conference on Information Technology (ICIT 2007).

[18]  Mita Nasipuri,et al.  A Study of Different Classifier Combination Approaches for Handwritten Indic Script Recognition , 2018, J. Imaging.

[19]  P. Balasubramanie,et al.  Information extraction and text mining of Ancient Vattezhuthu characters in historical documents using image zoning , 2016, 2016 International Conference on Asian Language Processing (IALP).

[20]  Satoru Ozawa,et al.  Computer Analysis of Photographic Data of Sri Lankan Early Brahmi Inscriptions , 2013 .

[21]  Mohamed Abdel-Basset,et al.  A Novel and Comprehensive Trust Estimation Clustering Based Approach for Large Scale Wireless Sensor Networks , 2019, IEEE Access.

[22]  Neha Gautam,et al.  Handwriting Recognition of Brahmi Script (an Artefact): Base of PALI Language , 2016 .

[23]  H. Devi,et al.  Thresholding: A Pixel-Level Image Processing Methodology Preprocessing Technique for an OCR System for the Brahmi Script , 2006 .

[24]  Neha Gautam,et al.  Optical Character Recognition for Brahmi Script Using Geometric Method , 2017 .

[25]  Shuang Xu,et al.  Manchu character segmentation and recognition method , 2017 .

[26]  Shuai Li,et al.  Handwritten character recognition technology combined with artificial intelligence , 2017 .

[27]  Satoru Ozawa,et al.  Image Processing Approach for Ancient Brahmi Script Analysis , 2015 .

[28]  Anil K. Jain,et al.  Feature extraction methods for character recognition-A survey , 1996, Pattern Recognit..

[29]  C. V. Jawahar,et al.  Multilingual OCR for Indic Scripts , 2016, 2016 12th IAPR Workshop on Document Analysis Systems (DAS).

[30]  Gaurav Y. Tawde,et al.  An Overview of Feature Extraction Techniques in OCR for Indian Scripts Focused on Offline Handwriting , 2013 .

[31]  Karamjeet Singh,et al.  Use of Gradient Technique for Extracting Features from Handwritten Gurmukhi Characters and Numerals , 2015 .

[32]  C. Chandra Sekhar,et al.  Block cipher identification using support vector classification and regression , 2010 .

[33]  Mita Nasipuri,et al.  Bangla Handwritten City Name Recognition Using Gradient-Based Feature , 2016, FICTA.

[34]  M. Chandrasekaran,et al.  Machine recognition of Brahmi script , 1983, IEEE Transactions on Systems, Man, and Cybernetics.