INTEGRATED OPTIMIZED DEEP LEARNING AND REINFORCEMENT LEARNING FOR FIBER FLAWS DETECTION

Vinothini B.

doi:10.29121/shodhkosh.v5.i6.2024.3319

Authors

Dr. B. Vinothini Assistant Professor and Head, Department of Computer Applications, St.Joseph's College For Women, Tirupur

DOI:

https://doi.org/10.29121/shodhkosh.v5.i6.2024.3319

Keywords:

Fabric Faults, Defect Detection, EPPAL-OMCCNN, Multi-Objective Sampling, Deep Reinforcement Learning

Abstract [English]

The most challenging task in the cotton business is finding Fabric Faults (FFs) and refining material durability appropriately. To alleviate this, an Enhanced Pairwise-Potential Activation Layer in Optimized Multi-Criteria Convolutional Neural Network (EPPAL-OMCCNN) model was created, which considers a multi-objective active sampling strategy for annotation and tuning CNN for FF detection. But, it needs to predict historical and new kinds of unknown FF patterns accurately. So, this article introduces a deep Reinforcement Learning (RL) scheme into the EPPAL-OMCCNN model to predict new unknown FFs with the help of prior knowledge. At first, the multi-objective sampling strategy is applied to the fabric image database to label more influential images. Then, these images are used to construct the Optimized CNN (OCNN) with the RL model, which is trained by the fabric defect characteristics to predict the new unknown fabric pattern defects precisely. Finally, the experimental results exhibit that the EPPAL-OMCCNN-RL model on the TILDA set accomplishes 97.58% accuracy contrasted with the different deep learning-based FF detection models.

References

Wu, R., Zhang, J. X., Leaf, J., Hua, X., Qu, A., Harvey, C., ... & Marschner, S. (2020). Weavecraft: an interactive design and simulation tool for 3D weaving. ACM Transactions on Graphs, 39(6), 210-216. DOI: https://doi.org/10.1145/3414685.3417865

Negm, M., & Sanad, S. (2020). Cotton fibres, picking, ginning, spinning and weaving. In Handbook of Natural Fibres, Woodhead Publishing, pp. 3-48. DOI: https://doi.org/10.1016/B978-0-12-818782-1.00001-8

Atkar, A., Pabba, M., Sekhar, S. C., & Sridhar, S. (2021). Current limitations and challenges in the global textile sector. In Fundamentals of Natural Fibres and Textiles, Woodhead Publishing, pp. 741-764. DOI: https://doi.org/10.1016/B978-0-12-821483-1.00004-8

Dils, C., Kalas, D., Reboun, J., Suchy, S., Soukup, R., Moravcova, D., ... & Schneider-Ramelow, M. (2022). Interconnecting embroidered hybrid conductive yarns by ultrasonic plastic welding for e-textiles. Textile Research Journal, 1-20. DOI: https://doi.org/10.1177/00405175221101015

Rubino, F., Nisticò, A., Tucci, F., & Carlone, P. (2020). Marine application of fiber reinforced composites: a review. Journal of Marine Science and Engineering, 8(1), 1-28. DOI: https://doi.org/10.3390/jmse8010026

Karuppannan Gopalraj, S., & Kärki, T. (2020). A review on the recycling of waste carbon fibre/glass fibre-reinforced composites: fibre recovery, properties and life-cycle analysis. SN Applied Sciences, 2(3), 1-21. DOI: https://doi.org/10.1007/s42452-020-2195-4

Amor, N., Noman, M. T., & Petru, M. (2021). Classification of textile polymer composites: recent trends and challenges. Polymers, 13(16), 1-27. DOI: https://doi.org/10.3390/polym13162592

Gadri, S., & Neuhold, E. (2020). Building best predictive models using ML and DL approaches to categorize fashion clothes. In International Conference on Artificial Intelligence and Soft Computing, Springer, Cham, pp. 90-102. DOI: https://doi.org/10.1007/978-3-030-61401-0_9

Ghosh, A., Sufian, A., Sultana, F., Chakrabarti, A., & De, D. (2020). Fundamental concepts of convolutional neural network. In Recent trends and advances in artificial intelligence and Internet of Things, Springer, Cham, pp. 519-567. DOI: https://doi.org/10.1007/978-3-030-32644-9_36

Hu, Y., Long, Z., Sundaresan, A., Alfarraj, M., AlRegib, G., Park, S., & Jayaraman, S. (2021). Fabric surface characterization: assessment of deep learning-based texture representations using a challenging dataset. The Journal of the Textile Institute, 112(2), 293-305. DOI: https://doi.org/10.1080/00405000.2020.1757296

Ouyang, W., Xu, B., Hou, J., & Yuan, X. (2019). Fabric defect detection using activation layer embedded convolutional neural network. IEEE Access, 7, 70130-70140. DOI: https://doi.org/10.1109/ACCESS.2019.2913620

Vinothini, B., & Sheeja, S. (2021). Memory enhanced dynamic conditional random fields embedded pairwise potential CNN for fabric defects identification. International Journal of Engineering Trends and Technology, 69, 227-234. DOI: https://doi.org/10.14445/22315381/IJETT-V69I10P229

Vinothini, B., & Sheeja, S. (2022). Optimizing gradients weight of enhanced pairwise-potential activation layer in CNN for fabric defect detection. Indian Journal of Computer Science and Engineering, 13(3), 688-696. DOI: https://doi.org/10.21817/indjcse/2022/v13i3/221303014

Vinothini, B., & Sheeja, S. (). Optimized multi-objective deep learning with enhanced pairwise-potential activation layer for fiber faults identification.

Mo, D., Wong, W. K., Lai, Z., & Zhou, J. (2020). Weighted double-low-rank decomposition with application to fabric defect detection. IEEE Transactions on Automation Science and Engineering, 18(3), 1170-1190. DOI: https://doi.org/10.1109/TASE.2020.2997718

Peng, P., Wang, Y., Hao, C., Zhu, Z., Liu, T., & Zhou, W. (2020). Automatic fabric defect detection method using PRAN-net. Applied Sciences, 10(23), 1-13. DOI: https://doi.org/10.3390/app10238434

Liu, Z., Huo, Z., Li, C., Dong, Y., & Li, B. (2021). DLSE-Net: a robust weakly supervised network for fabric defect detection. Displays, 68, 1-10. DOI: https://doi.org/10.1016/j.displa.2021.102008

Jun, X., Wang, J., Zhou, J., Meng, S., Pan, R., & Gao, W. (2021). Fabric defect detection based on a deep convolutional neural network using a two-stage strategy. Textile Research Journal, 91(1-2), 130-142. DOI: https://doi.org/10.1177/0040517520935984

Almeida, T., Moutinho, F., & Matos-Carvalho, J. P. (2021). Fabric defect detection with deep learning and false negative reduction. IEEE Access, 9, 81936-81945. DOI: https://doi.org/10.1109/ACCESS.2021.3086028

Hu, X., Fu, M., Zhu, Z., Xiang, Z., Qian, M., & Wang, J. (2021). Unsupervised defect detection algorithm for printed fabrics using content-based image retrieval techniques. Textile Research Journal, 91(21-22), 2551-2566. DOI: https://doi.org/10.1177/00405175211008614

Wu, J., Le, J., Xiao, Z., Zhang, F., Geng, L., Liu, Y., & Wang, W. (2021). Automatic fabric defect detection using a wide-and-light network. Applied Intelligence, 51(7), 4945-4961. DOI: https://doi.org/10.1007/s10489-020-02084-6

Liu, Q., Wang, C., Li, Y., Gao, M., & Li, J. (2022). A fabric defect detection method based on deep learning. IEEE Access, 10, 4284-4296. DOI: https://doi.org/10.1109/ACCESS.2021.3140118

Xiang, J., Pan, R., & Gao, W. (2022). Online detection of fabric defects based on improved CenterNet with deformable convolution. Sensors, 22(13), 1-18. DOI: https://doi.org/10.3390/s22134718

Huang, Y., & Xiang, Z. (2022). RPDNet: automatic fabric defect detection based on a convolutional neural network and repeated pattern Analysis. Sensors, 22(16), 1-17. DOI: https://doi.org/10.3390/s22166226

Jing, J., Wang, Z., Rätsch, M., & Zhang, H. (2022). Mobile-Unet: An efficient convolutional neural network for fabric defect detection. Textile Research Journal, 92(1-2), 30-42. DOI: https://doi.org/10.1177/0040517520928604

Workgroup on texture analysis of DFG’s. TILDA textile texture database. Available online: https://lmb.informatik.unifreiburg.de/resources/datasets/tilda.en.html (accessed on 15 September 2022)