• Home
  • Search
  • Comparative Study of Character Recognition for Handwritten Characters
  • Cite Icon1
  • https://doi.org/10.52783/cana.v32.5102Copy DOI Icon

Comparative Study of Character Recognition for Handwritten Characters

Show More
  • Abstract
  • Literature Map
  • Citations
  • Similar Papers
Abstract

Optical Character Recognition (OCR) represents an important technology in the context of computer vision, which facilitates the extraction of textual data with the help images. Although a lot of investigations have examined various OCR models, there is a notable absence of comparative studies evaluating different algorithms on a unified standardized dataset. This research targets to fill this void by assessing multiple OCR models across two distinct datasets: one consisting of 28×28-pixel images and the other comprising of 64×64-pixel images. The models evaluated include ten Convolutional Neural Networks (CNNs) characterized by diverse activation functions, architectural depths, and, dropout rates, in addition to Long Short-Term Memory (LSTM) networks, Support Vector Machines (SVM), Encoder-Decoder frameworks, and Random Forest classifiers. Through our analysis, it was revealed that the CNN-based models demonstrate exceptional performance, with the leading 64×64 CNN model achieving an accuracy of 0.9882, while the highest-performing 28×28 CNN model reported an accuracy of 0.9763. The Encoder-Decoder model also showed formidable results, achieving an accuracy of 0.9781 on the 64×64 dataset and 0.9810 on the 28×28 dataset. SVM exhibited robust performance on the higher-resolution dataset, achieving an accuracy of 0.9777, but encountered significant challenges on the 28×28 dataset, where the accuracy of only 0.7252 was reported. The Random Forest classifier maintained a consistent accuracy of 0.9538 across both datasets. Conversely, LSTM models struggled to generalize effectively for OCR applications, with the best LSTM model achieving a mere 0.0346 accuracy on the 64×64 dataset and performing poorly on the 28×28 dataset as well. Through the comprehensive study of CNN model, it was observed that, Model 3 attained the highest accuracy of 0.9907 across both datasets, accompanied by minimal validation loss (0.0377 for 28×28 and 0.0577 for 64×64). Other CNN models exhibited varying levels of performance, with deeper architectures generally surpassing their shallower counterparts. Our methodology encompassed preprocessing the datasets, partitioning them into training and testing sets, and training each model with suitable hyperparameters. The findings underscore that CNN-based architectures are the most effective for OCR tasks, particularly at elevated resolutions. These results offer significant insights into the efficacy of various OCR models.

Similar Papers
  • Research Article

Comparison of Long Short-Term Memory and Convolutional Neural Network Models for Emergency Department Patients’ Arrival Daily Forecasting

  • Mar 02, 2024
  • Journal of Archives in Military Medicine
  • Sina Moosavi Kashani +3
  • Research Article
  • Citations25

CNN vs. LSTM: A Comparative Study of Hourly Precipitation Intensity Prediction as a Key Factor in Flood Forecasting Frameworks

  • Sep 06, 2024
  • Atmosphere
  • Isa Ebtehaj +1
  • Research Article
  • Citations15

Evaluation of Cryptocurrency Price Prediction Using LSTM and CNNs Models

  • Nov 30, 2023
  • JOIV : International Journal on Informatics Visualization
  • Ng Shi Wen +1
  • Book Chapter
  • Citations4

Evaluating a Comparing Deep Learning Architectures for Blood Glucose Prediction

  • Jan 01, 2021
  • Touria El Idrissi +1
  • PDF
  • Research Article
  • Citations88

A Novel Hybrid Deep Neural Network to Predict Pre-impact Fall for Older People Based on Wearable Inertial Sensors.

  • Feb 12, 2020
  • Frontiers in Bioengineering and Biotechnology
  • Xiaoqun Yu +2
  • Research Article
  • Citations557

Short-term water quality variable prediction using a hybrid CNN–LSTM deep learning model

  • Feb 01, 2020
  • Stochastic Environmental Research and Risk Assessment
  • Rahim Barzegar +2
  • Research Article

Sign Language Detection Using CNN and LSTM Based Model

  • May 09, 2024
  • INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT
  • Bhavya Chauhan
  • Research Article
  • Citations2

Cryptocurrency Predictive Analytics: A Comparative Study of LSTM, CNN, and GRU Models

  • Jan 30, 2025
  • Pakistan Business Review
  • Jahanzaib Alvi +4
  • Research Article

A Channel Quality Prediction Approach for a Commercial Multiband Mobile Nertwork

  • Dec 30, 2025
  • Sciences des Structures et de la Matiere
  • Ndolane Diouf +4
  • Research Article
  • Citations9

Multilingual web traffic forecasting for network management using artificial intelligence techniques

  • Jun 01, 2025
  • Results in Engineering
  • Sama Salam Samaan +3
  • Research Article

Sentiment Analysis About Legislative Elections using Deep Learning with LSTM and CNN Models

  • Jun 29, 2024
  • Building of Informatics, Technology and Science (BITS)
  • Nadya Arda Angraini +1
  • Research Article
  • Citations45

Daily suspended sediment concentration forecast in the upper reach of Yellow River using a comprehensive integrated deep learning model

  • Jun 08, 2023
  • Journal of Hydrology
  • Jinsheng Fan +2
  • PDF
  • Research Article
  • Citations144

An Investigation of Deep Learning Models for EEG-Based Emotion Recognition

  • Dec 23, 2020
  • Frontiers in Neuroscience
  • Yaqing Zhang +9
  • Research Article
  • Citations1

Performance Comparison of Convolutional Neural Network and Long Short-Term Memory for the Classification of Handwritten Digits

  • Jan 01, 2025
  • International Journal of Research and Innovation in Applied Science
  • Oluwatobi Joel Toyobo +3
  • Research Article
  • Citations111

Tunnel boring machine vibration-based deep learning for the ground identification of working faces

  • Dec 01, 2021
  • Journal of Rock Mechanics and Geotechnical Engineering
  • Mengbo Liu +5
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.