A Lightweight Machine Vision Pipeline for Screen-Printing Defect Detection in MSMEs Using Low-Cost Image Acquisition

Galih Mahardika Munandar; Tiyan Fatkhurrohman; Lazuardi Fatahilah Hamdi

doi:10.24014/jti.v12i1.39516

A Lightweight Machine Vision Pipeline for Screen-Printing Defect Detection in MSMEs Using Low-Cost Image Acquisition

Galih Mahardika Munandar, Tiyan Fatkhurrohman, Lazuardi Fatahilah Hamdi

Abstract

This study addresses the need for affordable visual inspection support in micro, small, and medium enterprises (MSMEs) engaged in screen-printing production. Although machine vision and deep learning have been widely applied in manufacturing quality control, many existing systems are designed for relatively controlled industrial settings and require stable cameras, lighting, computing resources, and technical expertise. This condition limits direct adoption by small MSMEs, where image acquisition is often performed with operator-level devices under variable lighting and background conditions. This study designed and evaluated an initial low-resource visual inspection pipeline consisting of low-cost image acquisition, five-class defect labeling, MobileNetV3-based transfer learning, performance evaluation, and TensorFlow Lite conversion. The dataset consisted of 160 screen-printing images grouped into five classes: good, misalignment, bleeding, pinholes, and ghosting. The preliminary evaluation yielded 24.38% multiclass accuracy and a loss of 2.5635, indicating that the model could not yet reliably distinguish detailed defect categories. The converted TensorFlow Lite model was 5.43 MB, indicating that the technical conversion path was feasible. A binary quality-control interpretation produced 75.63% accuracy, but 27 defective images were still predicted as pass QC. Therefore, the pipeline cannot be treated as a final quality-control decision system. The main contribution of this study is empirical evidence that image-acquisition quality, dataset sufficiency, class separability, and training configuration are critical bottlenecks in developing lightweight deep-learning-based inspection for low-resource MSME environments.

Full Text:

PDF

References

L. Setiyani and Y. Rostiani, “Analysis of E-Commerce Adoption by SMEs Using the Technology-Organization-Environment (TOE) Model: A Case Study in Karawang, Indonesia,” Int. J. Sci., 2024, [Online]. Available: http://ijstm.inarah.co.id

G. M. Munandar and A. Dicasani, “Hubungan Pelanggan dengan Pelaku UMKM Konveksi di Kebumen dengan Pendekatan e-CRM,” J. Teknol. dan Manaj. Ind. Terap., vol. 4, no. 3, pp. 855–860, 2025, doi: 10.55826/jtmit.v4i3.792.

T. Coito, M. S. E. Martins, B. Firme, J. Figueiredo, S. M. Vieira, and J. M. C. Sousa, “Assessing the impact of automation in pharmaceutical quality control labs using a digital twin,” J. Manuf. Syst., vol. 62, no. December 2021, pp. 270–285, 2022, doi: 10.1016/j.jmsy.2021.11.014.

C. El Hachem, G. Perrot, L. Painvin, and R. Couturier, “Automation of Quality Control in the Automotive Industry Using Deep Learning Algorithms,” 2021 Int. Conf. Comput. Control Robot. ICCCR 2021, pp. 123–127, 2021, doi: 10.1109/ICCCR49711.2021.9349273.

A. Akundi and M. Reyna, “A Machine Vision Based Automated Quality Control System for Product Dimensional Analysis,” Procedia Comput. Sci., vol. 185, no. June, pp. 127–134, 2021, doi: 10.1016/j.procs.2021.05.014.

S. Kim, T. P. Nguyen, and J. Yoon, “A Systematic Review of Machine Vision Applications in Factory and Manufacturing Processes: From Quality Control to Predictive Diagnostics,” Int. J. Precis. Eng. Manuf. - Green Technol., 2025, doi: 10.1007/s40684-025-00769-2.

A. V. Gurjanov, V. I. Babenkov, A. V. Shukalov, I. O. Zharinov, and O. O. Zharinov, “Total quality control of the cyber-physical production using machine vision technologies,” J. Phys. Conf. Ser., vol. 1889, no. 5, 2021, doi: 10.1088/1742-6596/1889/5/052014.

M. Cinal, A. Sioma, and B. Lenty, “The Quality Control System of Planks Using Machine Vision,” Appl. Sci., vol. 13, no. 16, 2023, doi: 10.3390/app13169187.

I. Karacan, I. Erdogan, M. C. Igdil, and U. Cebeci, “Machine Vision Supported Quality Control Applications in Rotary Switch Production by Using Both Process FMEA and Design FMEA,” Nat. Appl. Sci. J., vol. 4, no. 2, pp. 16–31, 2021, doi: 10.38061/idunas.850545.

J. Jaramillo, J. Vanden Heuvel, and K. H. Petersen, “Low-Cost, Computer Vision-Based, Prebloom Cluster Count Prediction in Vineyards,” Front. Agron., vol. 3, no. April, pp. 1–10, 2021, doi: 10.3389/fagro.2021.648080.

J. M. G. P. Isidoro, R. Martins, R. F. Carvalho, and J. L. M. P. de Lima, “A high-frequency low-cost technique for measuring small-scale water level fluctuations using computer vision,” Meas. J. Int. Meas. Confed., vol. 180, no. February, 2021, doi: 10.1016/j.measurement.2021.109477.

G. Bortolotti et al., “A computer vision system for apple fruit sizing by means of low-cost depth camera and neural network application,” Precis. Agric., vol. 25, no. 6, pp. 2740–2757, 2024, doi: 10.1007/s11119-024-10139-8.

L. D. Ortega, E. S. Loyaga, P. J. Cruz, H. P. Lema, J. Abad, and E. A. Valencia, “Low-Cost Computer-Vision-Based Embedded Systems for UAVs,” Robotics, vol. 12, no. 6, pp. 1–20, 2023, doi: 10.3390/robotics12060145.

H. E. Kim, A. Cosa-Linan, N. Santhanam, M. Jannesari, M. E. Maros, and T. Ganslandt, “Transfer learning for medical image classification: a literature review,” BMC Med. Imaging, vol. 22, no. 1, pp. 1–13, 2022, doi: 10.1186/s12880-022-00793-7.

M. A. Chandra and S. S. Bedi, “Survey on SVM and their application in image classification,” Int. J. Inf. Technol., vol. 13, no. 5, 2021, doi: 10.1007/s41870-017-0080-1.

L. Chen, S. Li, Q. Bai, J. Yang, S. Jiang, and Y. Miao, “Review of Image Classification Algorithms Based on Convolutional Neural Networks,” Remote Sens, pp. 1–50, 2021, doi: https://doi.org/10.3390/rs13224712.

M. Mehmood, A. Shahzad, B. Zafar, A. Shabbir, and N. Ali, “Remote Sensing Image Classification: A Comprehensive Review and Applications,” Math. Probl. Eng., vol. 2022, 2022, doi: 10.1155/2022/5880959.

S. Qian, Y. Hu, and C. Ning, “MobileNetV3 for Image Classification,” 6th Int. Conf. I-SMAC (IoT Soc. Mobile, Anal. Cloud), I-SMAC 2022 - Proc., pp. 490–497, 2022, doi: 10.3390/proceedings2021072002.

X. Kong and Z. Ge, “Deep PLS: A Lightweight Deep Learning Model for Interpretable and Efficient Data Analytics,” IEEE Trans. Neural Networks Learn. Syst., vol. 34, no. 11, pp. 8923–8937, 2023, doi: 10.1109/TNNLS.2022.3154090.

Z. Y. Deng, H. H. Chiang, L. W. Kang, and H. C. Li, “A lightweight deep learning model for real-time face recognition,” IET Image Process., vol. 17, no. 13, pp. 3869–3883, 2023, doi: 10.1049/ipr2.12903.

A. A. A. El-Latif, S. A. Chelloug, M. Alabdulhafith, and M. Hammad, “Accurate Detection of Alzheimer’s Disease Using Lightweight Deep Learning Model on MRI Data,” Diagnostics, vol. 13, no. 7, pp. 1–21, 2023, doi: 10.3390/diagnostics13071216.

Z. Li, X. Lei, and S. Liu, “A lightweight deep learning model for cattle face recognition,” Comput. Electron. Agric., vol. 195, no. January, p. 106848, 2022, doi: 10.1016/j.compag.2022.106848.

S. O. Bursa, O. D. Incel, and G. I. Alptekin, “Building lightweight deep learning models with TensorFlow Lite for human activity recognition on mobile devices,” Ann. des Telecommun, vol. 78, no. 11–12, pp. 687–702, 2023, doi: 10.1007/s12243-023-00962-x.

I. N. K. Wardana, J. W. Gardner, and S. A. Fahmy, “Optimising deep learning at the edge for accurate hourly air quality prediction,” Sensors, vol. 21, no. 4, 2021, doi: 10.3390/s21041064.

M. H. Akhtar, I. Eksheir, and T. Shanableh, “Edge-optimized deep learning architectures for classification of agricultural insects with mobile deployment,” Information, vol. 16, no. 5, 2025, doi: 10.3390/info16050348.

E. Cumbajin et al., “A systematic review on deep learning with CNNs applied to surface defect detection,” J. Imagin, vol. 9, no. 10, 2023, doi: 10.3390/jimaging9100193.

DOI: http://dx.doi.org/10.24014/jti.v12i1.39516