Affiliation:
1. China, Hangzhou, Zhejiang Sci-Tech University, Key Laboratory of Modern Textile Machinery & Technology of Zhejiang Province
2. China, Hangzhou, Zhejiang Sci-Tech University, School of Information Science and Technology
Abstract
This study proposes a solution for the issue of the low classification accuracy of clothing images. Using Fashion-MNIST as the clothing image dataset, we propose a clothing image classification technology based on an online sequential extreme learning machine (OSELM) optimised by the dragonfly algorithm (DA). First, we transform the Fashion-MNIST dataset into a data set that we extract from the corresponding grey image. Then, considering that the input weight and hidden layer bias of an OSELM are generated randomly, a DA is proposed to optimise the input weight and hidden layer bias of the OSELM to reduce the influence of random generation on the classification results. Finally, the optimised OSELM is applied to the clothing image classification. Compared to the other seven types of classification algorithms, the proposed clothing image classification model with the DA-optimised OSELM reached 93.98% accuracy when it contained 350 hidden nodes. Its performance was superior to other algorithms that were configured with the same number of hidden nodes. From a stability analysis of the box-plot, it was found that there were no outliers exhibited by the DA-OSELM model, whereas some other models had outliers or had lower stability compared to the model proposed, thereby validating the efficacy of the solution proposed.
Subject
Industrial and Manufacturing Engineering,General Environmental Science,Materials Science (miscellaneous),Business and International Management
Reference21 articles.
1. Liu S, Song Z, Liu GC, et al. Street-to-shop: Cross-Scenario Clothing Retrieval ViaParts Alignment and Auxiliary Set. Proceedings of the IEEE Computer SocietyConference on Computer Vision and Pattern Recognition 2012; 3330-3337.
2. Bossard L, Dantone M, Leistner C, et al. Apparel Classification with Style.Proceedings of Asian Conference on Computer Vision 2012; 321-335.
3. Simo-Serra E, Ishikawa H. Fashion Style in 128 Floats: Joint Ranking andClassification Using Weak Data for Feature Extraction. Proceedings of the IEEEInternational Conference on Computer Vision and Pattern Recognition 2016; 298-307.
4. Hidayati SC, You CW, Cheng WH, et al. Learning and Recognition of ClothingGenres from Full-Body Images. IEEE Transactions on Cybernetics 2018; 48(5):1647-1659.
5. Yamazaki K, Inaba M. Clothing Classification Using Image Features Derived fromClothing Fabrics, Wrinkles and Cloth Overlaps. IEEE International Conference onIntelligent Robots and Systems 2013; 2710-2717.
Cited by
16 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献