A comparison of conventional and deep learning methods of image classification

• Autorzy: Dovbnych Maryna , Plechawska-Wójcik Małgorzata

Identyfikatory

DOI

10.35784/jcsi.2727

Warianty tytułu

PL

Porównanie metod klasycznego i głębokiego uczenia maszynowego w klasyfikacji obrazów

• Języki publikacji: EN

Abstrakty

EN

The aim of the research is to compare traditional and deep learning methods in image classification tasks. The conducted research experiment covers the analysis of five different models of neural networks: two models of multi–layer perceptron architecture: MLP with two hidden layers, MLP with three hidden layers; and three models of convolutional architecture: the three VGG blocks model, AlexNet and GoogLeNet. The models were tested on two different datasets: CIFAR–10 and MNIST and have been applied to the task of image classification. They were tested for classification performance, training speed, and the effect of the complexity of the dataset on the training outcome.

PL

Celem badań jest porównanie metod klasycznego i głębokiego uczenia w zadaniach klasyfikacji obrazów. Przeprowa-dzony eksperyment badawczy obejmuje analizę pięciu różnych modeli sieci neuronowych: dwóch modeli wielowar-stwowej architektury perceptronowej: MLP z dwiema warstwami ukrytymi, MLP z trzema warstwami ukrytymi; oraz trzy modele architektury konwolucyjnej: model z trzema VGG blokami, AlexNet i GoogLeNet. Modele przetrenowano na dwóch różnych zbiorach danych: CIFAR–10 i MNIST i zastosowano w zadaniu klasyfikacji obrazów. Zostały one zbadane pod kątem wydajności klasyfikacji, szybkości trenowania i wpływu złożoności zbioru danych na wynik trenowania.

Słowa kluczowe

EN

image classification; machine learning; deep learning; neural networks

PL

klasyfikacja obrazów; uczenie maszynowe; uczenie głębokie; sieci neuronowe

• Wydawca: Wydawnictwo Politechniki Lubelskiej
• Czasopismo: Journal of Computer Sciences Institute
• Rocznik: 2021
• Tom: Vol. 21
• Strony: 303--308
• Opis fizyczny: Bibliogr. 25 poz., fig,

Twórcy

autor

Dovbnych Maryna

• Department of Computer Science, Lublin University of Technology, Nadbystrzycka 36B, 20–618 Lublin, Poland

autor

Plechawska-Wójcik Małgorzata

• Department of Computer Science, Lublin University of Technology, Nadbystrzycka 36B, 20–618 Lublin, Poland

Bibliografia

• [1] MNIST handwritten digit database, http://yann.lecun.com/exdb/mnist [13.02.2021]
• [2] Y. LeCun, L. Bottou, Y. Bengio, P. Haffner, Gradient–based learning applied to document recognition, Proceedings of the IEEE 86(11) (1998) 2278–2324.
• [3] S. B. Driss, M. Soua, R. Kachouri, M. Akil, A comparison study between MLP and convolutional neural network models for character recognition, in SPIE Conference on RealTime Image and Video Processing, Anaheim, United States, 10–11 April (2017) 1022306.
• [4] N. Sharma, V. Jain, A. Mishra, An analysis of convolutional neural networks for image classification, Procedia computer science 132 (2018) 377–384.
• [5] J. M. Peña, P. A. Gutiérrez, C. Hervás–Martínez, J. Six, R. E. Plant, F. López–Granados, Object–based image classification of summer crops with machine learning methods, Remote Sensing 6(6) (2014) 5019–5041.
• [6] D. X. Zhou, Universality of deep convolutional neural networks, Applied and computational harmonic analysis 48(2) (2020) 787–794.
• [7] I. M. Dheir, A. S. A. Mettleq, A. A. Elsharif, S. S. Abu–Naser, Classifying Nuts Types Using Convolutional Neural Network, International Journal of Academic Information Systems Research 3(12) (2020) 12–18.
• [8] Y. Li, J. Nie, X. Chao, Do we really need deep CNN for plant diseases identification?, Computers and Electronics in Agriculture 178 (2020) 105803.
• [9] P. Sharma, Y. P. S. Berwal, W. Ghai, Performance analysis of deep learning CNN models for disease detection in plants using image segmentation, Information Processing in Agriculture 7(4) (2019) 566–574.
• [10] J. G. A. Barbedo, Impact of data set size and variety on the effectiveness of deep learning and transfer learning for plant disease classification, Computers and electronics in agriculture 153 (2018) 46–53.
• [11] P. T. T. Ngo, M. Panahi, K. Khosravi, O. Ghorbanzadeh, N. Karimnejad, A. Cerda, S. Lee, Evaluation of deep learning algorithms for national scale landslide susceptibility mapping of Iran, Geoscience Frontiers 12(2) (2020) 505–519.
• [12] I. Banerjee, Y. Ling, M. C. Chen, S. A. Hasan, C. P. Langlotz, N. Moradzadeh, B. Chapman, T. Amrhein, D. Mong, D. L. Rubin, O. Farri, M. P. Lungren, Comparative effectiveness of convolutional neural network (CNN) and recurrent neural network (RNN) architectures for radiology text report classification, Artificial intelligence in medicine 97 (2019) 79–88.
• [13] C. L. Chowdhary, M. Mittal, P. A. Pattanaik, Z. Marszalek, An efficient segmentation and classification system in medical images using intuitionist possibilistic fuzzy C–mean clustering and fuzzy SVM algorithm, Sensors 20(14) (2020) 3903.
• [14] T. Nakaura, T. Higaki, K. Awai, O. Ikeda, Y. Yamashita, A primer for understanding radiology articles about machine learning and deep learning, Diagnostic and Interventional Imaging 101(12) (2020) 763–844.
• [15] X. Yang, Y. Ye, X. Li, R. Y. Lau, X. Zhang, X. Huang, Hyperspectral image classification with deep learning models., IEEE Transactions on Geoscience and Remote Sensing 56(9) (2018) 5408–5423.
• [16] A. F. Agarap, An architecture combining convolutional neural network (CNN) and support vector machine (SVM) for image classification, arXiv:1712.03541v2 (2019).
• [17] Y. Sun, B. Xue, M. Zhang, G. G. Yen, J. Lv, Automatically Designing CNN Architectures Using the Genetic Algorithm for Image Classification, IEEE Transactions on Cybernetics 50(9) (2020) 3840–3854.
• [18] F. Sultana, A. Sufian, P. Dutta, Evolution of image segmentation using deep convolutional neural network: A survey, Knowledge–Based Systems 201–202 (2020) 106062.
• [19] O. Sbai, C. Couprie, M. Aubry, Impact of base data set design on few–shot image classification, in Computer Vision–ECCV 2020: 16th European Conference, Glasgow, United Kingdom, August 23–28 (2020) 597–613.
• [20] C. Gambella, B. Ghaddar, J. Naoum–Sawaya, Optimization problems for machine learning: a survey, European Journal of Operational Research 290(3) (2020) 807–828.
• [21] Y. Wang, Y. Li, Y. Song, X. Rong, The Influence of the Activation Function in a Convolution Neural Network Model of Facial Expression Recognition, Applied Sciences 10(5) (2020) 1897.
• [22] D. Bashir, G. D. Montanez, S. Sehra, P. S. Segura, J. Lauw, An Information–Theoretic Perspective on Overfitting and Underfitting, in AI 2020: Advances in Artificial Intelligence: 33rd Australasian Joint Conference, Canberra, Australia, November 29–30 (2020) 347–358.
• [23] T. Kiran, Computer Vision Accuracy Analysis with Deep Learning Model Using TensorFlow, International Journal of Innovative Research in Computer Science & Technology (IJIRCST) 8(4) (2020) 2347–5552.
• [24] T. P. P. Padilha, L. E. A. de Lucena, A Systematic Review About Use of TensorFlow for Image Classification and Word Embedding in the Brazilian Context, Academic Journal on Computing, Engineering and Applied Mathematics 1(2) (2020) 24–27.
• [25] The CIFAR–10 dataset, https://www.cs.toronto.edu/~kriz/cifar.html [13.02.2021]

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).