A Two-Stage Deep Feature Selection Method for Online Handwritten Bangla and Devanagari Basic Character Recognition

In this paper, we have proposed a two-stage deep feature selection (FS) approach for the recognition of online handwritten Bangla and Devanagari basic characters. At the beginning of the approach, we have checked the performance of nine pre-trained transfer learning models namely, DenseNet121, Effic...

Full description

Saved in:
Bibliographic Details
Published in:SN computer science 2022-07, Vol.3 (4), p.260, Article 260
Main Authors: Bhattacharyya, Ankan, Chakraborty, Rajatsubhra, Saha, Soumyajit, Sen, Shibaprasad, Sarkar, Ram, Roy, Kaushik
Format: Article
Language:English
Subjects:
Accuracy
Algorithms
Character recognition
Classification
Computer Imaging
Computer Science
Computer Systems Organization and Communication Networks
Data Structures and Information Theory
Feature selection
Handwriting
Handwriting recognition
Heuristic methods
Information Systems and Communication Service
Machine learning
Optimization techniques
Original Research
Pattern Recognition and Graphics
Progresses in Image Processing
Software Engineering/Programming and Operating Systems
Vision
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we have proposed a two-stage deep feature selection (FS) approach for the recognition of online handwritten Bangla and Devanagari basic characters. At the beginning of the approach, we have checked the performance of nine pre-trained transfer learning models namely, DenseNet121, EfficientNetB0, NASNetMobile, VGG-16, VGG-19, ResNet50, InceptionV3, Xception, and MobileNetV2 for the recognition of the said handwritten characters. After that we have considered the best-performing model which is VGG-19 in our case. The obtained features from this model are then reduced using a two-stage FS approach. In the first stage, features are ranked using a filter method, called ReliefF. Then in the second stage, the ranked features are optimized by applying a nature-inspired meta-heuristic, called gray wolf optimization. The experimental outcomes reveal that not only the proposed approach reduces the feature dimension by 88.5% for Bangla and 91.9% for Devanagari, but also it increases classification accuracy for Bangla (reaches 100%) and retains it for Devanagari (which is 99.61%).
ISSN:2661-8907
2662-995X
2661-8907
DOI:10.1007/s42979-022-01157-2