Skip to content

q-viper/final-devanagari-word-char-detector

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Devanagari-Character-Word-Recognition

This is the final project for BSC.CSIT 7th semester.

Devanagari-Character-Recognition

This is the final project of 7th semester BSC.CSIT.

Introduction

Devanagari is the national font of Nepal and is used widely throughout the India also. It contains 10 numerals(०, १, २, ३, ४, ५, ६, ७, ८, ९) and 36 consonants (क, ख, ग, घ, ङ, च, छ, ज, झ, ञ, ट, ठ, ड, ढ, ण, त, थ, द, ध,न, प,फ, ब, भ, म, य, र, ल, व, श, ष, स, ह, क्ष, त्र, ज्ञ). Some consonants are complex and made by combine some other. However, throughout this project i considered them as single character.

The required dataset is publicly available on the link.

Implementation

For this project i am using python 3.6 on anaconda. More importantly i am running it on Jupyter Notebook sometimes but Google Colab is what is used most. For model train/test, Colab is used. For real world image recogniton, i used my Intel I5 with 8gb RAM. The dependencies and libraries i used are:
Python 3.6
Numpy
Matplotlib
OpenCv
Keras

For better project information start with Project Demonstration.

Some snaps

  • Model Model

  • Loss Loss

  • Accuracy Accuracy

  • Image testing Image testing

  • False prediction False Prediction

  • Image Cropping (ROI) Cropping

Cropping

  • Eliminating top Tope Removed

  • Segmenting Segmentation

  • Localization Localization

  • Detection Detection