Download PDFOpen PDF in browser

Variable Length Digit Recognition for Gujarati Language

EasyChair Preprint no. 7672

6 pagesDate: March 29, 2022


In this paper, we describe a method to perform handwritten digit recognition for Gujarati - a regional Indian language. Our method can handle variable-length inputs, meaning that there are no limitations around the digit length for the input image. To our knowledge, this is the first attempt to do variable length digit classification for the Gujarati language numerals. We outline a two-step method to classify handwritten Gujarati numerals. The first step identifies connected components of the input image and predicts the numeric length of each connected component. The second step predicts the actual number that is contained within each connected component. The final result is a concatenation of individual predictions. Our CNN architecture for this task has a low number of output classes (e.g. 30 classes for 3 digit classifier). Our method achieves 83.8\% test set accuracy for 1 to 4 digit Gujarati numerals. On NIST19 dataset, our method achieves 96.1\% test set accuracy for 2 to 6 digit English numerals.

Keyphrases: Convolutional Networks, Digit classifier, Digit Recognition, digit string, english numeral, Gujarati language, Gujarati Lan­guage, Gujarati numeral, Handwritten Digit, Handwritten Digit Recognition, handwritten gujarati numeral, handwritten numeral string, image processing, length classifier, multi length classifier, Multi Output CNN, pattern recognition, Pre-processing, Segmentation based method, Variable Length, variable length digit recognition, variable length string, Vertical projection

BibTeX entry
BibTeX does not have the right entry for preprints. This is a hack for producing the correct reference:
  author = {Shrey Malvi and Nirmal Patel and Pratik Prajapati},
  title = {Variable Length Digit Recognition for Gujarati Language},
  howpublished = {EasyChair Preprint no. 7672},

  year = {EasyChair, 2022}}
Download PDFOpen PDF in browser