Analysis of Clothing Image Classification Models: A Comparison Study between Traditional Machine Learning and Deep Learning Models

• Autorzy: Xu Jun , Wei Yumeng , Wang Aichun , Zhao Heng , Lefloch Damien

Identyfikatory

DOI

10.2478/ftee-2022-0046

• Języki publikacji: EN

Abstrakty

EN

Clothing image in the e-commerce industry plays an important role in providing customers with information. This paper divides clothing images into two groups: pure clothing images and dressed clothing images. Targeting small and medium-sized clothing companies or merchants, it compares traditional machine learning and deep learning models to determine suitable models for each group. For pure clothing images, the HOG+SVM algorithm with the Gaussian kernel function obtains the highest classification accuracy of 91.32% as compared to the Small VGG network. For dressed clothing images, the CNN model obtains a higher accuracy than the HOG+SVM algorithm, with the highest accuracy rate of 69.78% for the Small VGG network. Therefore, for end-users with only ordinary computing processors, it is recommended to apply the traditional machine learning algorithm HOG+SVM to classify pure clothing images. The classification of dressed clothing images is performed using a more efficient and less computationally intensive lightweight model, such as the Small VGG network.

Słowa kluczowe

EN

e-commerce; clothing image classification; traditional machine learning; CNN; HOG; SVM; small VGG network

• Wydawca: Sieć Badawcza Łukasiewicz - Łódzki Instytut Technologiczny
• Czasopismo: Fibres & Textiles in Eastern Europe
• Rocznik: 2022
• Tom: Vol. 30, no. 5
• Strony: 66--78
• Opis fizyczny: Bibliogr. 46 poz., rys., tab.

Twórcy

autor

Xu Jun

• Tiangong University, Tianjin 300387, China

• https://orcid.org/0000-0002-0966-399X

autor

Wei Yumeng

• Tiangong University, Tianjin 300387, China

• https://orcid.org/0000-0003-2025-8888

autor

Wang Aichun

• Tiangong University, Tianjin 300387, China

autor

Zhao Heng

• Shenzhen Technology University, Shenzhen 518118, China

• https://orcid.org/0000-0002-8505-6649

autor

Lefloch Damien

• Tiangong University, Tianjin 300387, China

• https://orcid.org/0000-0002-4812-2790

Bibliografia

• 1. Jing Y, Liu D, Kislyuk D, Zhai A, Xu J, Donahue J, Tavel S. Visual search at Pinterest, In: Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’15. Association for Computing Machinery, New York, NY, USA, 2015; pp. 1889–1898.
• 2. Gao Z, Han L. Clothing image classification based on random erasing and residual network. Journal of Physics: Conference Series 2020; Vol. 1634 No. 1, pp. 012136.
• 3. Feng Y, Du C, Hua A, Jiang M, Wei X, Peng T, Hu X. EnCaps: Clothing Image Classification Based on Enhanced Capsule Network. Applied Sciences 2021; Vol. 11 No. 22, pp.11024.
• 4. Kiapour MH, Han X, Lazebnik S, Berg AC, Berg TL. Where to buy it: Matching street clothing photos in online shops, in: IEEE International Conference on Computer Vision (ICCV), IEEE, Santiago, Chile 2015; pp. 3343-3351.
• 5. Liu KH, Chen TY, Chen CS. MVC: A Dataset for View-Invariant Clothing Retrieval and Attribute Prediction, in: Proceedings of the 2016 ACM on International Conference on Multimedia Retrieval (ICMR ‘16), Association for Computing Machinery, New York, NY, USA 2016; pp. 313–316.
• 6. Deng LL. Pre-detection Technology of Clothing Image Segmentation Based on GrabCut Algorithm. Wireless Pers Commun 2018; Vol. 102 No. 2, pp. 599–610.
• 7. Yue X, Zhang C, Fujita H, Lv Y. Clothing fashion style recognition with design issue graph. Appl Intell 2020 ; Vol 51 No. 10, pp. 1-13.
• 8. Li Y, He Z, Wang S, Huang W. Multideep Feature Fusion Algorithm for Clothing Style Recognition. Wirel Commun Mob Com 2021 ;Vol. 2021 No. 4, pp. 1-14.
• 9. Kashilani D, Damahe LB, Thakur NV. An Overview of Image Recognition and Retrieval of Clothing items, in: IEEE International Conference on Research in Intelligent and Computing in Engineering (RICE), IEEE, San Salvador, El Salvador 2018; pp. 1-6.
• 10. Donati L, Iotti E, Mordonini G, Prati A. Fashion Product Classification through Deep Learning and Computer Vision. Applied Sciences, 2019; Vol. 9 No. 7, pp. 1385.
• 11. Stricker M, Orengo M. Storage and Retrieval for Image and Video Databases Ⅲ. SPIE International Society for Optics and Photonics 1995; Vol. 1995, pp. 381- 392.
• 12. Hu MK. Visual pattern recognition by moment invariants. Information Theory, IRE Transactions on 1962; Vol. 8 No. 2, pp.179-187.
• 13. Li Y, Xu S, Luo X, Lin S. A new algorithm for product image search based on salient edge characterization. Journal of the Association for Information Science & Technology 2014 ; Vol. 65 No. 12, pp. 2534–2551.
• 14. Lowe DG. Distinctive Image Features from Scale-Invariant Keypoints. International Journal of Computer Vision 2004; Vol. 60 No. 2, pp. 91-110.
• 15. Li KL, Liu ZD. Clothing Information System Design Based on Images Retrieval, in: International Conference on Advanced Educational Technology and Information Engineering (AETIE 2015), Computer Information Centre, Beijing Institute of Fashion Technology 2015; Vol. 2015, pp. 677-683.
• 16. Dalal N, Triggs B. Histograms of Oriented Gradients for Human Detection, in: IEEE Computer Society Conference on Computer Vision & Pattern Recognition (CVPR’05), IEEE, San Diego, CA, USA2005; pp. 886-893.
• 17. Thewsuwan S, Horio K. Preprocessing Techniques Based on LBP and Gabor Filters for Clothing Classification, in: 2016 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), IEEE, Phuket, Thailand, Vol. 2016, pp. 1-6.
• 18. Sha D, Wang D, Zhou X, F Shi, Ge Y. An Approach for Clothing Recommendation Based on Multiple Image Attributes, in: Cui, B., Zhang, N., Xu, J., Lian, X., & Liu, D. (Eds.), International Conference on Web-Age Information Management, Springer, Cham 2016; pp. 272-285.
• 19. Surakarin W, Chongstitvatana P. Predicting Types of Clothing Using SURF and LDP based on Bag of Features, in: 2015 12th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON), IEEE, Hua Hin, Thailand 2015; pp. 1-5.
• 20. Li JQ, Shi WM, Yang DH. Clothing Image Classification with a Dragonfly Algorithm Optimised Online Sequential Extreme Learning Machine. Fibres Text East Eur 2021 ; Vol. 29 No. 3, pp. 90-95.
• 21. Tabik S, Peralta D, Herrera-Poyatos A, Herrera F. A snapshot of image preprocessing for convolutional neural networks: case study of MNIST. International Journal of Computational Intelligence Systems 2017 ; Vol. 10 No. 1, pp. 555.
• 22. Bui HM, Lech M, Cheng E, Neville K, Burnett IS. Object Recognition Using Deep Convolutional Features Transformed by a Recursive Network Structure. IEEE Access 2016 ; Vol. 4, pp. 10059–10066.
• 23. Tang P, Wang H, Kwong S. G-MS2F: GoogLeNet based multi-stage feature fusion of deep CNN for scene recognition. Neurocomputing. Neurocomputing 2017 ; Vol. 225 FEB.15, pp. 188-197.
• 24. Ghazi MM, Yanikoglu B, Aptoula E. Plant identification using deep neural networks via optimization of transfer learning parameters. Neurocomputing 2017 ; Vol. 235 APR.26, pp. 228-235.
• 25. Han K, Wang Y, Tian Q, Guo J, Xu C. GhostNet: More Features From Cheap Operations, in: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Seattle, WA, USA 2020 ; pp. 1577-1586.
• 26. Lao B, Jagadeesh K. Convolutional Neural Networks for Fashion Classification and Object Detection.2015.
• 27. Dong C, Shi Y, Tao R. Convolutional Neural Networks for Clothing Image Style Recognition. in: Proceedings of 2018 International Conference on Computational, Modeling, Simulation and Mathematical Statistics (CMSMS), Xi’an, China 2018, pp. 608-613.
• 28. Xiang J, Dong T, Pan R,, Gao W. Clothing Attribute Recognition Based on RCNN Framework Using L-Softmax Loss. IEEE Access 2020 ; Vol. 8, pp. 48299–48313.
• 29. Di W. A comparative research on clothing images classification based on neural network models, in: IEEE 2nd International Conference on Civil Aviation Safety and Information Technology (ICCASIT), IEEE, Weihai, China 2020; pp. 495-499.
• 30. Bossard L, Dantone M, Leistner C, Wengert C, Quack T, Gool LV. Apparel Classification with Style, in: Lee, K.M., Matsushita, Y., Rehg, J. M., Hu, Z.Y. (Ed.s), Asian conference on computer vision (ACCV), Springer-Verlag, Berlin, Heidelberg 2012; pp. 321–335.
• 31. Huo P, Wang Y, Liu Q. A part-based and feature fusion method for clothing classification, in: Pacific Rim Conference on Multimedia, Springer, Xi’an 2016; pp. 231–241.
• 32. Liu S, Feng J, Domokos C, Xu H, Huang J, Hu Z, Yan S. Fashion Parsing with Weak Colour-category Labels. IEEE Transactions on Multimedia 2014; Vol. 16 No. 1, pp. 253-265.
• 33. Liu Z, Luo P, Qiu S, Wang X, Tang X. DeepFashion: Powering ro-bust clothes recognition and retrieval with rich annotations, in: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Las Vegas, NV, USA 2016; pp. 1096–1104.
• 34. Wang J, Yang Y, Mao J, Huang Z, Huang C, Xu W. CNN-RNN: A unified framework for multi-label image classification, in: IEEE conference on computer vision and pattern recognition (CVPR), IEEE, Las Vegas, NV, USA 2016; pp. 2285-2294.
• 35. Nawaz M, Hasan R, Hasan MA, Hassan M, Rahman RM. Automatic Categorization of Traditional Clothing Using Convolutional Neural Network, in: IEEE/ACIS 17th International Conference on Computer and Information Science (ICIS), IEEE, Singapore 2018; pp. 98-103.
• 36. Cychnerski J, Brzeski A, Boguszewski A, Marmolowski M, Trojanowicz M. Clothes detection and classification using convolutional neural networks, in: IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), IEEE, Limassol, Cyprus 2017; pp. 1-8.
• 37. Iandola FN, Han S, Moskewicz MW, Ashraf K, Dally WJ, Keutzer K. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and ＜0.5MB model size. Under Review as a Conference Paper at ICLR. 2016.
• 38. Zhang X, Song C, Yang Y, Zhang Z, Zou Q. Deep learning based human body segmentation for clothing fashion classification”, in: Chinese Automation Congress (CAC), Shanghai, China2020; Vol. 2020 Nov. 6-8, pp. 7544-7549.
• 39. Rohrmanstorfer S, Komarov M, Modritscher F. Image Classification for the Automatic Feature Extraction in Human Worn Fashion Data. Mathematics 2021 ; Vol. 9 No. 6, pp. 624.
• 40. Hodecker A, Fernandes A, Steffens A, Crocker P, Leithardt V. Clothing Classification Using Convolutional Neural Networks, in: 15th IEEE Iberian Conference on Information Systems and Technologies (CISTI), IEEE, Seville, Spain 2020; pp. 1-6.
• 41. Basavanhally AN, Ganesan S, Agner S, Monaco JP, Feldman MD, Tomaszewski JE, Bhanot G, Madabhushi, A. Computerized image-based detection and grading of lymphocytic infiltration in HER2-breast cancer histopathology. IEEE Transactions on Biomedical Engineering 2010; Vol. 57 No. 3, pp. 642-653.
• 42. Adrian R. Multi-label classification with Keras, available at: https://www.pyimagesearch.com/2018/05/07/multilabel-classification-with-keras/ (accessed 7 May 2018)
• 43. Simonyan K, Zisserman A. Very Deep Convolutional Networks for Large-Scale Image Recognition. Computer Science 2014; pp. 1-14.
• 44. Xiao H, Rasul K, Vollgraf R. Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms”.2017.
• 45. Simo-Serra E, Ishikawa H. Fashion Style in 128 Floats: Joint Ranking and Classification Using Weak Data for Feature Extraction, in: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, Las Vegas, NV, USA 2016; pp. 298-307.
• 46. Wang L, Guo S, Huang W, Xiong Y, Qiao Y. Knowledge Guided Disambiguation for Large-Scale Scene Classification with Multi-Resolution CNNs, in: IEEE Transactions on Image Processing, IEEE 2017; Vol. 26 No. 4, pp. 2055-2068.