Bengali Handwritten Character Classification using Transfer Learning on Deep Convolutional Neural Network

02/25/2019
by   Swagato Chatterjee, et al.
0

In this paper, we propose a solution which uses state-of-the-art techniques in Deep Learning to tackle the problem of Bengali Handwritten Character Recognition ( HCR ). Our method uses lesser iterations to train than most other comparable methods. We employ Transfer Learning on ResNet 50, a state-of-the-art deep Convolutional Neural Network Model, pretrained on ImageNet dataset. We also use other techniques like a modified version of One Cycle Policy, varying the input image sizes etc. to ensure that our training occurs fast. We use the BanglaLekha-Isolated Dataset for evaluation of our technique which consists of 84 classes (50 Basic, 10 Numerals and 24 Compound Characters). We are able to achieve 96.12 BanglaLekha-Isolated dataset. When comparing our method with that of other researchers, considering number of classes and without using Ensemble Learning, the proposed solution achieves state of the art result for Handwritten Bengali Character Recognition. Code and weight files are available at https://github.com/swagato-c/bangla-hwcr-present.

READ FULL TEXT
research
08/29/2020

AKHCRNet: Bengali Handwritten Character Recognition Using Deep Learning

I propose a state of the art deep neural architectural solution for hand...
research
06/18/2019

Crop Lodging Prediction from UAV-Acquired Images of Wheat and Canola using a DCNN Augmented with Handcrafted Texture Features

Lodging, the permanent bending over of food crops, leads to poor plant g...
research
12/04/2016

Word Recognition with Deep Conditional Random Fields

Recognition of handwritten words continues to be an important problem in...
research
02/02/2018

Handwritten Isolated Bangla Compound Character Recognition: a new benchmark using a novel deep learning approach

In this work, a novel deep learning technique for the recognition of han...
research
07/26/2017

A Novel Transfer Learning Approach upon Hindi, Arabic, and Bangla Numerals using Convolutional Neural Networks

Increased accuracy in predictive models for handwritten character recogn...
research
05/30/2022

Deblurring Photographs of Characters Using Deep Neural Networks

In this paper, we present our approach for the Helsinki Deblur Challenge...
research
08/06/2020

Handwritten Character Recognition from Wearable Passive RFID

In this paper we study the recognition of handwritten characters from da...

Please sign up or login with your details

Forgot password? Click here to reset