Enhancing Image Classification Through a Hybrid Approach: Integrating Convolutional Neural Networks with Hidden Markov Mod

In the field of computer vision, image classification stands as a pivotal task, aiming to categorize images based on their inherent visual information. This paper presents an innovative hybrid approach, merging the strengths of Convolutional Neural Networks (CNNs) and Hidden Markov Models (HMMs) to...

Full description

Saved in:
Bibliographic Details
Published in:Traitement du signal 2024-02, Vol.41 (1), p.383-390
Main Authors: Djalab, Abdelhak, Lalaoui, Lahouaoui, Bisker, Aya, Hadibi, Aicha
Format: Article
Language:English
Subjects:
Accuracy
Algorithms
Artificial intelligence
Artificial neural networks
Classification
Computer vision
Data analysis
Datasets
Deep learning
Effectiveness
Feature extraction
Gesture recognition
Image classification
Image enhancement
Markov chains
Methods
Neural networks
Recall
Spatial data
Spatial dependencies
Visual fields
Visual tasks
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In the field of computer vision, image classification stands as a pivotal task, aiming to categorize images based on their inherent visual information. This paper presents an innovative hybrid approach, merging the strengths of Convolutional Neural Networks (CNNs) and Hidden Markov Models (HMMs) to enhance the efficacy of image classification. The integration of these two methodologies, each excelling in distinct aspects of data analysis, forms the cornerstone of our research. CNNs, renowned for their proficiency in extracting spatial data and fine-grained features, are adept at generalizing across diverse datasets. Conversely, HMMs, with their robust sequential data modeling capabilities, adeptly capture dependencies within the feature sets derived from CNNs. This synergy is embodied in the HMM-CNN framework, wherein CNNs serve to extract pertinent features from images, while HMMs model the spatial dependencies between adjacent pixels. Empirical evaluations on benchmark datasets substantiate the superior performance of this hybrid approach over traditional CNNs, particularly in scenarios where temporal dependencies are paramount, such as video analysis, action recognition, and gesture classification. A comparative analysis employing five datasets and six metrics-recall, precision, val_loss, val_accuracy, val_precision, and val_recall-reveals the superiority of the CNN-HMM model. Specifically, against a standalone CNN model with an accuracy of 87%, the CNN-HMM model demonstrates an accuracy of approximately 89.09%. This paper's findings underscore the efficacy of combining CNN and HMM methodologies for advanced image classification tasks, offering significant implications for future research in this domain.
ISSN:0765-0019
1958-5608
DOI:10.18280/ts.410132