Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Apr 24;25(9):2710.
doi: 10.3390/s25092710.

Automated Quality Control of Cleaning Processes in Automotive Components Using Blob Analysis

Simone Mari  1 , Giovanni Bucci  1 , Fabrizio Ciancetta  1 , Edoardo Fiorucci  1 , Andrea Fioravanti  1
Affiliations

Automated Quality Control of Cleaning Processes in Automotive Components Using Blob Analysis

Simone Mari et al. Sensors (Basel). .

Abstract

This study presents an automated computer vision system for assessing the cleanliness of plastic mirror caps used in the automotive industry after a washing process. These components are highly visible and require optimal surface conditions prior to painting, making the detection of residual contaminants critical for quality assurance. The system acquires high-resolution monochrome images under various lighting configurations, including natural light and infrared (IR) at 850 nm and 940 nm, with different angles of incidence. Four blob detection algorithms-adaptive thresholding, Laplacian of Gaussian (LoG), Difference of Gaussians (DoG), and Determinant of Hessian (DoH)-were implemented and evaluated based on their ability to detect surface impurities. Performance was assessed by comparing the total detected blob area before and after the cleaning process, providing a proxy for both sensitivity and false positive rate. Among the tested methods, adaptive thresholding under 30° natural light produced the best results, with a statistically significant z-score of +2.05 in the pre-wash phase and reduced false detections in post-wash conditions. The LoG and DoG methods were more prone to spurious detections, while DoH demonstrated intermediate performance but struggled with reflective surfaces. The proposed approach offers a cost-effective and scalable solution for real-time quality control in industrial environments, with the potential to improve process reliability and reduce waste due to surface defects.

Keywords: automotive manufacturing; blob analysis; computer vision; quality control; surface inspection.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflicts of interest.

Figures

Figure 1
Figure 1
Schematic representation of the experimental imaging setup used for surface contamination analysis.
Figure 2
Figure 2
Comparison of different lighting configurations for detecting contaminants on clean industrial components. The images in the first row show the component under different natural light conditions, with variations in the angle of incidence and beam width. The images in the second row show the same component under different configurations of infrared illumination (850 nm and 940 nm), highlighting the effect of wavelength and angle of incidence on the visibility of surface defects.
Figure 3
Figure 3
Comparison of different lighting configurations for detecting contaminants on dirty industrial components. The images in the first row show the component under different natural light conditions, with variations in the angle of incidence and beam width. The images in the second row show the same component under different configurations of infrared illumination (850 nm and 940 nm), highlighting the effect of wavelength and angle of incidence on the visibility of surface contaminants.
Figure 4
Figure 4
Example of adaptive thresholding under grazing natural light conditions. Original image after contrast enhancement using CLAHE (left). Output of adaptive thresholding highlighting potential defects and contaminants (center). Final blob detection result, with detected blobs overlaid in red (right).
Figure 5
Figure 5
Example of LoG under grazing natural light conditions. Original image after contrast enhancement using CLAHE (left). Output of the Laplacian operator highlighting intensity changes and potential blob edges (center). Final blob detection result, with detected blobs overlaid in red (right).
Figure 6
Figure 6
Example of DoG under grazing natural light conditions. Original image after contrast enhancement using CLAHE (left). Output of the DoG operator emphasizing regions of intensity difference at different scales (center). Final blob detection result, with detected blobs overlaid in red (right).
Figure 7
Figure 7
Example of DoH under grazing natural light conditions. Original image after contrast enhancement using CLAHE (left). Output of the Hessian matrix determinant highlighting regions of high second-order intensity variation (center). Final blob detection result, with detected blobs overlaid in red (right).
Figure 8
Figure 8
Pre-wash and post-wash blob detection results using adaptive thresholding.
Figure 9
Figure 9
Pre-wash and post-wash blob detection results using the LoG algorithm.
Figure 10
Figure 10
Pre-wash and post-wash blob detection results using the DoG algorithm.
Figure 11
Figure 11
Pre-wash and post-wash blob detection results using the DoH algorithm.
Figure 12
Figure 12
Example of adaptive thresholding under 30° natural light conditions.
Figure 13
Figure 13
Example of LoG under 45° natural light conditions.
Figure 14
Figure 14
Example of DoG under perpendicular natural light conditions.
Figure 15
Figure 15
Example of DoH under 45° natural light conditions.
See this image and copyright information in PMC

References

    1. Friederich J., Lazarova-Molnar S. Reliability Assessment of Manufacturing Systems: A Comprehensive Overview, Challenges and Opportunities. J. Manuf. Syst. 2024;72:38–58. doi: 10.1016/j.jmsy.2023.11.001. - DOI
    1. Mumuni A., Mumuni F. Automated Data Processing and Feature Engineering for Deep Learning and Big Data Applications: A Survey. J. Inf. Intell. 2025;3:113–153. doi: 10.1016/j.jiixd.2024.01.002. - DOI
    1. Khanam R., Hussain M., Hill R., Allen P. A Comprehensive Review of Convolutional Neural Networks for Defect Detection in Industrial Applications. IEEE Access. 2024;12:94250–94295. doi: 10.1109/ACCESS.2024.3425166. - DOI
    1. Halder S., Afsari K. Robots in Inspection and Monitoring of Buildings and Infrastructure: A Systematic Review. Appl. Sci. 2023;13:2304. doi: 10.3390/app13042304. - DOI
    1. Acevedo-Avila R., Gonzalez-Mendoza M., Garcia-Garcia A. A Linked List-Based Algorithm for Blob Detection on Embedded Vision-Based Sensors. Sensors. 2016;16:782. doi: 10.3390/s16060782. - DOI - PMC - PubMed

LinkOut - more resources