A study on the evaluation of screen mesh clogging ratio using difference imaging technique

Min Seok Oh; Ji Hye Lee; Kyung Suk Yoo

doi:10.22702/jkai.2025.15.1.8

All Issue

2025 Vol.15, Issue 1 Preview Page Next Page

Scientific Paper

A study on the evaluation of screen mesh clogging ratio using difference imaging technique 차영상 기법을 활용한 스크린망 망막힘률 평가 연구

4 July 2025. pp. 79-87

PDF XML

Abstract

Mesh clogging during recycled-aggregate production hampers screening efficiency and increases product variability. This study proposes an automated, quantitative assessment of clogging based on a difference-imaging pipeline. A target image is first aligned to a reference background via an Enhanced Correlation Coefficient (ECC) rigid transformation; the resulting difference image is then conservatively thresholded and post-processed with two openings and one dilation using a 3 × 3 structuring element to obtain a binary clog mask. The clogging ratio is defined as the percentage of masked pixels within the effective aperture area derived from the reference image. For three representative cases, comparison with manually generated masks showed that absolute deviations remained within 5%, demonstrating the high consistency of the proposed method. Visual inspection further verified that the automatically generated masks accurately captured major debris distributions. A limitation arose when low-contrast debris failed to exceed the fixed threshold, indicating the need for adaptive thresholding and illumination control. By training on a large‐scale screen-mesh dataset collected under diverse environments and conditions, and by developing a deep-learning-based object-detection model capable of real-time foreign-matter detection and clogging-ratio analysis, the system can be integrated with on-site monitoring equipment to leverage real-time outputs, thereby enhancing the accuracy and efficiency of automated analysis.

Keywords

Screen-mesh Clogging

Difference Imaging

Recycled-aggregate Screening

Object Detection

References

민원･양경택 (2020). 등록특허: 10-2088253, 명칭: 가변추를 이용한 진동제어기능을 갖는 진동 스크린.

윤훈철･윤칠중 (2022). 등록특허: 10-2459522, 명칭: 순환토사 생산시스템 및 이를 이용한 순환토사 생산방법.

Alanazi, T.M., Berriri, K., Albekairi, M., Ben Atitallah, A., Sahbani, A. and Kaaniche, K. (2023). “New Real-Time High-Density Impulsive Noise Removal Method Applied to Medical Images”, Diagnostics, 13(10), p. 1709.

10.3390/diagnostics1310170937238194PMC10217601

Ayubi, G.A., Kowalski, B. and Dubra, A. (2024). “Normalized Weighted Cross-Correlation for Multi-Channel Image Registration”, Optics Continuum, 3(5), pp. 649-665.

10.1364/OPTCON.525065

Bataineh, B., Tounsi, M., Zamzami, N., Janbi, J., Abu-Ain, W.A.K., AbuAin, T. and Elnazer, S. (2025). “A Comprehensive Review on Document Image Binarization”, Journal of Imaging, 11(5), p. 133.

10.3390/jimaging1105013340422990PMC12112497

Evangelidis, G.D. and Psarakis, E.Z. (2008). “Parametric Image Alignment Using Enhanced Correlation Coefficient Maximization”, IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(10), pp. 1858-1865.

10.1109/TPAMI.2008.113

Kim, Y.-T., Lee, T.-H., Park, Y.-H. and Lee, M.-S. (2020). “A Study on Mathematical Morphology for Noise Reduction in Road Crack Detection Process through Image Processing”, Journal of Digital Contents Society, 21(12), pp. 2197-2202.

10.9728/dcs.2020.21.12.2197

Lee, H., Yoo, M.-R. and Lee, H. (2022). “The Screen Efficiency Improving Effect Analysis by the Screen Motion Characteristic Analysis Applying Blockage Prevention Spring”, Resources Recycling, 31(6), pp. 36-43.

10.7844/kirr.2022.31.6.36

Nishidate, Y., Kohira, Y., Takahashi, S. and Yoshioka, R. (2024). “Enhanced Image Differencing for Precise Change Detection in Static Environments”, Information Engineering Express, 10(2), pp. 1-14.

10.52731/iee.v10.i2.829

Yan, M., Bao, S., Xu, K., He, Y. and Wu, Q. (2007). “Pavement Crack Detection and Analysis for High-Grade Highway”, Proc. of the 8^th Int. Conf. on Electron. Meas. and Instrum. ICEMI, pp. 548-552.

Yoo, K.S. (2024). “Evaluation of the Moisture Content of Soil in Recycled Aggregates Using Electrical Conductivity”, Journal of the Korean Asphalt Institute, 14(2), pp. 175-182.

10.22702/JKAI.2024.14.2.16

Zhang, J. and Guo, W. (2023). “A New Regularization for Deep Learning-Based Segmentation of Images with Fine Structures and Low Contrast”, Sensors, 23(4), p. 1887.

10.3390/s2304188736850485PMC9966951

Information

Publisher :KOREAN ASPHALT INSTITUTE
Publisher(Ko) :한국아스팔트학회
Journal Title :Journal of the Korean Asphalt Institute
Journal Title(Ko) :한국아스팔트학회지
Volume : 15
No :1
Pages :79-87
Received Date : 2025-06-11
Revised Date : 2025-06-20
Accepted Date : 2025-06-28
DOI :https://doi.org/10.22702/jkai.2025.15.1.8

Journal of the Korean Asphalt Institute ISSN:2234-0785(Print) 2635-9553(Online) 한국아스팔트학회지

All Issue