FINE-TUNING TRANSFER LEARNING MODEL IN WOVEN FABRIC PATTERN CLASSIFICATION

被引：2
作者：
Noprisson H. [1 ]
Ermatita E. [2 ]
Abdiansah A. [2 ]
Ayumi V. [1 ]
Purba M. [1 ]
Setiawan H. [3 ]
机构：
[1] Program of Doctoral Program in Engineering, Universitas Sriwijaya, Jalan Raya Prabumulih-Inderalaya, Palembang
[2] Faculty of Computer Science, Universitas Sriwijaya, Jalan Raya Prabumulih-Inderalaya, Palembang
[3] Department of Research and Development Stikhafi Academy, Jalan Timur Indah Raya, Bengkulu
来源：
International Journal of Innovative Computing, Information and Control | 2022年 / 18卷 / 06期
关键词：
Hand-woven fabric; Inception-V3; MobileNet; VGG16; VGG19;
D O I：
10.24507/ijicic.18.06.1885
中图分类号：
学科分类号：
摘要：
It is important to figure out the patterns of woven fabrics before producing woven fabric with a machine. Recognition of woven fabric pattern usually with the help of the human eye can understand the fabric pattern. However, this manual checking takes a lot of time, money, and work, which will raise the cost of making woven fabrics. This study uses the VGG16, VGG19, MobileNet, and Inception-V3 methods to classify woven fabric patterns. It also wants to see how fine-tuning method can help algorithms be more accurate at classifying images. The research was divided into four phases, including image acquisition, image preprocessing, image classification and evaluation. A total of 978 pictures of motifs included in the research dataset. There are 351 images for the cotton class, 76 images for linen, 195 images for silk, and 356 images for wool. As the result, the highest testing accuracy was in the Inception-V3 experiment (with fine-tuning) of 72.51%, and the lowest was in the VGG19 experiment (with fine-tuning) of 52.92%. © 2022 ICIC International.
引用
收藏
页码：1885 / 1894
页数：9
相关论文
共 34 条
  • [1] Li X., Lin B., The development and design of artificial intelligence in cultural and creative products, Math. Probl. Eng, 2021
  • [2] Nurhaida I., Ayumi V., Fitrianah D., Zen R. A. M., Noprisson H., Wei H., Implementation of deep neural networks (DNN) with batch normalization for Batik pattern recognition, Int. J. Electr. Comput. Eng, 10, 2, pp. 2045-2053, (2020)
  • [3] Noprisson H., Hidayat E., Zulkarnaim N., A preliminary study of modelling interconnected systems initiatives for preserving indigenous knowledge in Indonesia, 2015 International Conference on Information Technology Systems and Innovation (ICITSI), pp. 1-6, (2015)
  • [4] Puarungroj W., Boonsirisumpun N., Convolutional neural network models for HandWoven fabric motif recognition, 2019 Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering (ECTI DAMT-NCON), pp. 300-303, (2019)
  • [5] Perera Y. S., Muwanwella R. M. H. W., Fernando P. R., Fernando S. K., Jayawardana T. S. S., Evolution of 3D weaving and 3D woven fabric structures, Fash. Text, 8, 1, pp. 1-31, (2021)
  • [6] Makur A. P., Gunur B., Rampung B., Exploring motifs in Towe Songke, Manggaraian Ethnic Woven Fabric, in mathematics perspective, SJME (Supremum J. Math. Educ.), 4, 2, (2020)
  • [7] Hussain M. A. I., Khan B., Wang Z., Ding S., Woven fabric pattern recognition and classification based on deep convolutional neural networks, Electronics, 9, 6, (2020)
  • [8] Manovich L., Automating aesthetics: Artificial intelligence and image culture, Flash Art Int, 316, pp. 1-10, (2017)
  • [9] Noppitak S., Surinta O., Ensemble convolutional neural network architectures for land use classification in economic crops aerial images, ICIC Express Letters, 15, 6, pp. 531-543, (2021)
  • [10] Coe J., Atay M., Evaluating impact of race in facial recognition across machine learning and deep learning algorithms, Computers, 10, 9, (2021)
1234