Cover
Vol. 21 No. 1 (2025)

Published: September 19, 2025

Pages: 168-177

Original Article

A Comparative Study of Deep Learning Methods-Based Object/Image Categorization

Saad Albawi 1 Layth Kamil Almajmaie Ali J. Abboud
1Computer Engineering Department, Engineering College, University of Diyala, Diyala, Iraq
History
  • Received: August 20, 2023
  • Revised: November 8, 2023
  • Accepted: January 1, 2024
  • Available Online: December 27, 2024
DOI

https://doi.org/10.37917/ijeee.21.1.17

Abstract

In recent years, there has been a considerable rise in the applications in which object or image categorization is beneficial for example, analyzing medicinal images, assisting persons to organize their collections of photos, recognizing what is around self-driving vehicles, and many more. These applications necessitate accurately labeled datasets, in their majority involve an extensive diversity in the types of images, from cats or dogs to roads, landscapes, and so forth. The fundamental aim of image categorization is to predict the category or class for the input image by specifying to which it belongs. For human beings, this is not a considerable thing, however, learning computers to perceive represents a hard issue that has become a broad area of research interest, and both computer vision techniques and deep learning algorithms have evolved. Conventional techniques utilize local descriptors for finding likeness between images, however, nowadays; progress in technology has provided the utilization of deep learning algorithms, especially the Convolutional Neural Networks (CNNs) to auto-extract representative image patterns and features for classification The fundamental aim of this paper is to inspect and explain how to utilize the algorithms and technologies of deep learning to accurately classify a dataset of images into their respective categories and keep model structure complication to a minimum. To achieve this aim, must focus precisely and accurately on categorizing the objects or images into their respective categories with excellent results. And, specify the best deep learning-based models in image processing and categorization. The developed CNN-based models have been proposed and a lot of pre-training models such as (VGG19, DenseNet201, ResNet152V2, MobileNetV2, and InceptionV3) have been presented, and all these models are trained on the Caltech-101 and Caltech-256 datasets. Extensive and comparative experiments were conducted on this dataset, and the obtained results demonstrate the effectiveness of the proposed models. The obtained results demonstrate the effectiveness of the proposed models. The accuracy for Caltech-101 and Caltech-256 datasets was (98.06% and 90%) respectively.

Keywords

References

  1. C. Kamusoko, Image Classification. Springer Geogra- phy. Springer, Singapore, 2019.
  2. Q. Fan, Y. Bi, B. Xue, and M. Zhang, “Genetic pro- gramming for feature extraction and construction in im- age classification,” Applied Soft Computing, vol. 118, p. 108509, 2022.
  3. `Oscar Lorente, I. Riera, and A. Rana, “Image classifi- cation with classic and deep learning techniques,” Com- puter Science, Computer Vision and Pattern Recognition, 2021.
  4. J. e Liu and F.-P. An, “Image classification algorithm based on deep learning-kernel function,” Scientific Pro- gramming, vol. 2020, pp. Article ID 7607612, 14 pages, 2020.
  5. M. Xin and Y. Wang, “Research on image classifica- tion model based on deep convolution neural network,” EURASIP Journal on Image and Video Processing, vol. 40, 2019.
  6. H. Q. Flayyih, J. Waleed, and S. Albawi, “A system- atic mapping study on brain tumors recognition based A B C D E F G H I J K L validation accuracy. The second column (b, d, f, h, j and l) loss and validation loss per epoch using Caltech-101, for VGG19, ResNet152V2, DenseNet201, InceptionV3, MobileNetV2, and the first proposed model respectively. 176 | Albawi, Almajmaie & Abboud A B C D E F G H I J K L validation accuracy. The second column (b, d, f, h, j and l) loss and validation loss per epoch using Caltech-256, for VGG19, ResNet152V2, DenseNet201, InceptionV3, MobileNetV2, and the second proposed model respectively. on machine learning algorithms,” in 2020 3rd Interna- tional Conference on Engineering Technology and its Applications (IICETA), pp. 191–197, 2020.
  7. J. Waleed, S. Albawi, H. Q. Flayyih, and A. Alkhayyat, “An effective and accurate cnn model for detecting tomato leaves diseases,” in 2021 4th International Iraqi Conference on Engineering Technology and Their Appli- cations (IICETA), pp. 33–37, 2021.
  8. W. Wang, Y. Hu, T. Zou, H. Liu, J. Wang, and X. Wang, “A new image classification approach via improved mo- bilenet models with local receptive field expansion in shallow layers,” Computational Intelligence and Neuro- science, vol. 2020, pp. Article ID 8817849, 10 pages, 2020.
  9. C. Ravi, “Image classification using deep learning and fuzzy systems,” Journal of Healthcare Engineering, vol. 2022, pp. Article ID 6216273, 13 pages, 2022.
  10. M. Bansal, M. Kumar, M. Sachdeva, and A. Mittal, “Transfer learning for image classification using vgg19: Caltech-101 image data set,” Journal of Ambient Intelli- gence and Humanized Computing, 2021.
  11. A. S. Rao and K. Mahantesh, “Learning semantic fea- tures for classifying very large image datasets using con- volution neural network,” SN Computer Science, vol. 2, no. 187, 2021.
  12. E. Zeynallı, “Analysis the image classification problem based on transfer learning,” in 14th International Con- ference on Theory and Application of Fuzzy Systems and Soft Computing – ICAFS-2020, Advances in Intelli- gent Systems and Computing, vol. 1306, Springer, Cham, 2021.
  13. H. M. Shyni and E. Chitra, “A comparative study of x-ray and ct images in covid-19 detection using image processing and deep learning techniques,” Computer Methods and Programs in Biomedicine Update, vol. 2, p. 100054, 2022.
  14. J. Waleed, T. Abbas, and T. M. Hasan, “Facemask wear- ing detection based on deep cnn to control covid-19 transmission,” in 2022 Muthanna International Confer- ence on Engineering Science and Technology (MICEST), pp. 158–161, 2022.
  15. V. Kumar, A. Zarrad, R. Gupta, and O. Cheikhrouhou, “Cov-dls: Prediction of covid-19 from x-rays using enhanced deep transfer learning techniques,” Journal of Healthcare Engineering, vol. 2022, pp. Article ID 6216273, 13 pages, 2022. 177 | Albawi, Almajmaie & Abboud
  16. K. Simonyan and A. Zisserman, “Very deep convolu- tional networks for large-scale image recognition,” arXiv preprint, 2014.
  17. K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in 2016 IEEE Con- ference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778, 2016.
  18. K. He, X. Zhang, S. Ren, and J. Sun, “Identity mappings in deep residual networks,” in Computer Vision – ECCV 2016. Lecture Notes in Computer Science, vol. 9908, Springer, Cham, 2016.
  19. G. Huang, Z. Liu, L. V. D. Maaten, and K. Q. Wein- berger, “Densely connected convolutional networks,” in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2261–2269, 2017.
  20. C. Szegedy and et al., “Going deeper with convolutions,” in 2015 IEEE Conference on Computer Vision and Pat- tern Recognition (CVPR), pp. 1–9, 2015.
  21. C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wo- jna, “Rethinking the inception architecture for computer vision,” in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2818–2826, 2016.
  22. M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, “Mobilenetv2: Inverted residuals and linear bottlenecks,” in 2018 IEEE/CVF Conference on Com- puter Vision and Pattern Recognition, pp. 4510–4520, 2018.
  23. L. Fei-Fei, R. Fergus, and P. Perona, “Learning gen- erative visual models from few training examples: an incremental bayesian approach tested on 101 object cat- egories,” Computer Vision and Image Understanding, vol. 106, no. 1, pp. 59–70, 2007.
  24. G. Griffin, A. Holub, and P. Perona, “The caltech-256 object category dataset,” Tech. Rep. CNS-TR-2007-001, Caltech, Pasadena, Calif, USA, 2007.