Smartphone Photos Categorization Using Markov Model with Limited Training Data

Zulkarnaen Hatala, Muhammad Hudzaly

Sari


This writing investigates the classification of images taken using a smartphone. Due to the large number of photos and the large number of photo categories, it is necessary to automatically categorize these photos. Photos are classified using two different approaches. The first method uses Hidden Markov Model (HMM) and the second technique employs Siamese Network from Convolutional Neural Network (CNN) architecture. The same data are used for training and testing for both models. For HMM we use Discrete Cosine Transform (DCT) to extract salient features of images. The number of training examples is very small compared to the test set. Here we carried out few-shot classification method. For recognition of the HMM, Viterbi algorithm is applied. Performances of both procedures were measured. For only 109 test samples HMM achieve 98% accuracy, while twin network achieves 90%. The use of HMM has advantage over Siamese in term of faster computation. HMM opens the opportunity of the smartphone with low computation capability to categorize photos automatically.

Teks Lengkap:

PDF

Referensi


B. Mor, S. Garhwal, and A. Kumar, “A Systematic Review of Hidden Markov Models and Their Applications,†Arch. Comput. Methods Eng., vol. 28, no. 3, pp. 1429–1448, May 2021, doi: 10.1007/s11831-020-09422-4.

L. R. Rabiner, “A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition,†Proc. IEEE, vol. 77, no. 2, 1989.

I. B. Kadhim, A. N. Nasret, and Z. S. Mahmood, “Enhancement and modification of automatic speaker verification by utilizing hidden Markov model,†Indones. J. Electr. Eng. Comput. Sci., vol. 27, no. 3, p. 1397, Sep. 2022, doi: 10.11591/ijeecs.v27.i3.pp1397-1403.

D. Ali, I. Touqir, A. M. Siddiqui, J. Malik, and M. Imran, “Face Recognition System Based on Four State Hidden Markov Model,†IEEE Access, vol. 10, pp. 74436–74448, 2022, doi: 10.1109/ACCESS.2022.3188717.

A. Aggarwal, M. Alshehri, M. Kumar, P. Sharma, O. Alfarraj, and V. Deep, “Principal component analysis, hidden Markov model, and artificial neural network inspired techniques to recognize faces,†Concurr. Comput. Pract. Exp., vol. 33, no. 9, p. e6157, 2021.

S. Tena, R. Hartanto, and I. Ardiyanto, “Content-based image retrieval for fabric images: A survey,†Indones. J. Electr. Eng. Comput. Sci., vol. 23, no. 3, p. 1861, Sep. 2021, doi: 10.11591/ijeecs.v23.i3.pp1861-1872.

M. Mouret, C. Solnon, and C. Wolf, “Classification of Images Based on Hidden Markov Models,†in 2009 Seventh International Workshop on Content-Based Multimedia Indexing, Chania, Crete: IEEE, Jun. 2009, pp. 169–174. doi: 10.1109/CBMI.2009.22.

C. Wang, Z. Yu, Z. Long, H. Zhao, and Z. Wang, “A few-shot diabetes foot ulcer image classification method based on deep ResNet and transfer learning,†Sci. Rep., vol. 14, no. 1, pp. 1–9, 2024.

J. Dong, Y. Wang, J.-H. Lai, and X. Xie, “Improving adversarially robust few-shot image classification with generalizable representations,†in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 9025–9034.

B. M. S. Maia et al., “Transformers, convolutional neural networks, and few-shot learning for classification of histopathological images of oral cancer,†2024.

K. Dunphy, M. Buwaneswaran, K. Grolinger, and A. Sadhu, “Few-Shot Learning Augmented with Image Transformation for Multiclass Structural Damage Classification,†J. Comput. Civ. Eng., vol. 39, no. 3, p. 04025021, 2025.

W. Song and Y. Huang, “Adaptive feature recalibration transformer for enhancing few-shot image classification,†Vis. Comput., pp. 1–15, 2025.

G. Koch, R. Zemel, R. Salakhutdinov, and others, “Siamese neural networks for one-shot image recognition,†in ICML deep learning workshop, Lille, 2015.

M. Hamid, “DCT-based image feature extraction and its application in image self-recovery and image watermarking,†PhD Thesis, Concordia University, 2016.

L. Tan and J. Jiang, Digital signal processing: fundamentals and applications, 3rd ed. Academic press, 2019.

V. V. Kohir and U. B. Desai, “Face recognition using a DCT-HMM approach,†in Proceedings Fourth IEEE Workshop on Applications of Computer Vision. WACV’98 (Cat. No.98EX201), Princeton, NJ, USA: IEEE Comput. Soc, 1998, pp. 226–231. doi: 10.1109/ACV.1998.732884.

J. Li and R. M. Gray, Image segmentation and compression using hidden Markov models, vol. 571. Springer Science & Business Media, 2000.

F. S. Samaria, “Face recognition using hidden Markov models,†PhD Thesis, University of Cambridge Cambridge, UK, 1994.

L. R. Rabiner, J. G. Wilpon, and B.-H. Juang, “A segmental k-means training procedure for connected word recognition,†ATT Tech. J., vol. 65, no. 3, pp. 21–31, 1986.

G. D. Forney, “The viterbi algorithm,†Proc. IEEE, vol. 61, no. 3, pp. 268–278, 1973.

A. Allahverdyan and A. Galstyan, “Comparative analysis of viterbi training and maximum likelihood estimation for hmms,†Adv. Neural Inf. Process. Syst., vol. 24, 2011.

S. J. Young, N. H. Russell, and J. H. S. Thornton, “Token Passing: a Simple Conceptual Model for Connected Speech Recognition Systemsâ€.

R. Solera-Ureña, J. Padrell-Sendra, D. Martín-Iglesias, A. Gallardo-Antolín, C. Peláez-Moreno, and F. Díaz-de-María, “SVMs for Automatic Speech Recognition: A Survey,†in Progress in Nonlinear Speech Processing, vol. 4391, Y. Stylianou, M. Faundez-Zanuy, and A. Esposito, Eds., in Lecture Notes in Computer Science, vol. 4391. , Berlin, Heidelberg: Springer Berlin Heidelberg, 2007, pp. 190–216. doi: 10.1007/978-3-540-71505-4_11.

H. Shao, D. Zhong, X. Du, S. Du, and R. N. Veldhuis, “Few-shot learning for palmprint recognition via meta-siamese network,†IEEE Trans. Instrum. Meas., vol. 70, pp. 1–12, 2021.

Y. Lai, “A comparison of traditional machine learning and deep learning in image recognition,†in Journal of Physics: Conference Series, IOP Publishing, 2019, p. 012148.

N. D. Sidiropoulos, L. De Lathauwer, X. Fu, K. Huang, E. E. Papalexakis, and C. Faloutsos, “Tensor decomposition for signal processing and machine learning,†IEEE Trans. Signal Process., vol. 65, no. 13, pp. 3551–3582, 2017.

T. Wiatowski and H. Bölcskei, “A mathematical theory of deep convolutional neural networks for feature extraction,†IEEE Trans. Inf. Theory, vol. 64, no. 3, pp. 1845–1866, 2017.

O. Dürr, B. Sick, and E. Murina, Probabilistic deep learning: With python, keras and tensorflow probability. Manning Publications, 2020.




DOI: http://dx.doi.org/10.30811/jaise.v5i2.6943

Refbacks

  • Saat ini tidak ada refbacks.


Indexing :

Creative Commons License
Journal of Artificial Intelligence and Software Engineering (JAISE) licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.