Investigating the Impact of Image Quality Acquisition to Deep Object Detection Performance: a Case Study With PCB Damage Detection via Mobile Devices in the Wild

Lucas Cabral; João Pedro Santiago; Lucas Sena; Joaquim Bento Cavalcante Neto; Yuri Lenon; Javam Machado

doi:10.5753/jbcs.2026.5323

Authors

Lucas Cabral Systems and Databases Laboratory, Federal University of Ceará https://orcid.org/0009-0002-9668-6184
João Pedro Santiago Systems and Databases Laboratory, Federal University of Ceará https://orcid.org/0009-0005-2454-3397
Lucas Sena Systems and Databases Laboratory, Federal University of Ceará https://orcid.org/0009-0004-9318-6867
Joaquim Bento Cavalcante Neto Systems and Databases Laboratory, Federal University of Ceará https://orcid.org/0000-0003-1143-6662
Yuri Lenon Systems and Databases Laboratory, Federal University of Ceará https://orcid.org/0000-0003-4778-8133
Javam Machado Systems and Databases Laboratory, Federal University of Ceará https://orcid.org/0000-0002-8430-9421

DOI:

https://doi.org/10.5753/jbcs.2026.5323

Keywords:

Image Quality Assessment, Mobile Image Acquisition, Deep Object Detection, PCB Damage Detection

Abstract

Mobile devices have revolutionized image acquisition, enabling diverse communication and image-processing applications. One promising application is automated damage detection in printed circuit boards (PCBs), crucial for quality control in electronics manufacturing. However, unlike controlled environments, mobile device image acquisition introduces challenges such as non-uniform lighting, background interference, and varying camera resolution, which can affect the accuracy of deep learning models. This paper presents a case study investigating the impact of domain-specific, no-reference image quality metrics on the performance of deep-learning object detection models for PCB damage detection. We evaluate nine metrics, including five novel contributions, using a semantic segmentation approach to measure foreground and background quality. Our study assesses how these metrics influence the performance of deep neural network architectures, determining optimal thresholds that separate high and low-quality images. Experiments are conducted on real-life images captured with smartphones in industrial settings. Our findings indicate that filtering poor-quality images based on these metrics could significantly improve detection performance, offering practical benefits for mobile damage detection applications.

Downloads

Download data is not yet available.

References

Adibhatla, V. A., Chih, H.-C., Hsu, C.-C., Cheng, J., Abbod, M. F., and Shieh, J.-S. (2020). Defect detection in printed circuit boards using you-only-look-once convolutional neural networks. Electronics, 9(9):1547. DOI: 10.3390/electronics9091547.

Al-Rahlawee, A. T. H. and Rahebi, J. (2021). Multilevel thresholding of images with improved otsu thresholding by black widow optimization algorithm. Multimedia Tools and Applications, 80(18):28217-28243. DOI: 10.1007/s11042-021-10860-w.

Alves, D., Farias, V., Chaves, I., Chao, R., Madeiro, J. P., Gomes, J. P., and Machado, J. (2022). Detecting customer induced damages in motherboards with deep neural networks. In 2022 International Joint Conference on Neural Networks (IJCNN), pages 1-8. IEEE. DOI: 10.1109/ijcnn55064.2022.9892047.

Andalibi, M. and Chandler, D. M. (2017). Automatic glare detection via photometric, geometric, and global positioning information. Electronic Imaging, 29:77-82. DOI: 10.2352/issn.2470-1173.2017.19.avm-024.

Bai, Y., Zhang, Y., Ding, M., and Ghanem, B. (2018). Sod-mtgan: Small object detection via multi-task generative adversarial network. In Proceedings of the European conference on computer vision (ECCV), pages 206-221. DOI: 10.1007/978-3-030-01261-8_13.

Bansal, R., Raj, G., and Choudhury, T. (2016). Blur image detection using laplacian operator and open-cv. In 2016 International Conference System Modeling & Advancement in Research Trends (SMART), pages 63-67. IEEE. DOI: 10.1109/sysmart.2016.7894491.

Basu, M. (2002). Gaussian-based edge-detection methods-a survey. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 32(3):252-260. DOI: 10.1109/tsmcc.2002.804448.

Bergstrom, A. C. and Messinger, D. W. (2023). Image quality and object detection performance of convolutional neural networks. In Pattern Recognition and Tracking XXXIV, volume 12527, pages 159-177. SPIE. DOI: 10.1117/12.2663779.

Bosse, S., Maniry, D., Müller, K.-R., Wiegand, T., and Samek, W. (2017). Deep neural networks for no-reference and full-reference image quality assessment. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 4321-4329. DOI: 10.1109/tip.2017.2760518.

Cabral, L., Farias, V., Sena, L., Chaves, I., Pordeus, J. P., Santiago, J. P., Sa, D., Machado, J., and Madeiro, J. P. (2023). An active learning approach for detecting customer induced damages in motherboards with deep neural networks. Learning and Nonlinear Models - Journal of the Brazilian Society on Computational Intelligence (SBIC), 21:29-42. DOI: 10.21528/lnlm-vol21-no2-art3.

Coca, L.-G., Cusmuliuc, C. G., and Iftene, A. (2021). Automatic tarmac crack identification application. Procedia Computer Science, 192:478-486. DOI: 10.1016/j.procs.2021.08.049.

Dallet, C., Kareem, S., and Kale, I. (2014). Real time blood image processing application for malaria diagnosis using mobile phones. In 2014 IEEE International Symposium on Circuits and Systems (ISCAS), pages 2405-2408. IEEE. DOI: 10.1109/iscas.2014.6865657.

Doğan, G. and Ergen, B. (2022). A new mobile convolutional neural network-based approach for pixel-wise road surface crack detection. Measurement, 195:111119. DOI: 10.1016/j.measurement.2022.111119.

Du, B., Wan, F., Lei, G., Xu, L., Xu, C., and Xiong, Y. (2023). Yolo-mbbi: Pcb surface defect detection method based on enhanced yolov5. Electronics, 12(13):2821. DOI: 10.3390/electronics12132821.

Esfahani, M. A. and Wang, H. (2021). Robust glare detection: Review, analysis, and dataset release. arXiv preprint arXiv:2110.06006. DOI: 10.48550/arxiv.2110.06006.

Everingham, M. et al. (2010). The pascal visual object classes (voc) challenge. International journal of computer vision, 88(2):303-338. DOI: 10.1007/s11263-009-0275-4.

Fu, L., Liu, Z., Majeed, Y., and Cui, Y. (2018). Kiwifruit yield estimation using image processing by an android mobile phone. IFAC-PapersOnLine, 51(17):185-190. DOI: 10.1016/j.ifacol.2018.08.137.

Geiger, A., Lenz, P., and Urtasun, R. (2012). Are we ready for autonomous driving? the kitti vision benchmark suite. In 2012 IEEE conference on computer vision and pattern recognition, pages 3354-3361. IEEE. DOI: 10.1109/cvpr.2012.6248074.

Gong, T., Jiang, Y., He, L., Wu, X., and Liu, J. (2023). Pmddnet: A novel one-stage lightweight network for multi-category defect inspection of pc motherboards. Available at SSRN 4403073. DOI: 10.2139/ssrn.4403073.

Grigorescu, S., Trasnea, B., Cocias, A., and Macesanu, G. (2020). A survey of deep learning techniques for autonomous driving. Journal of Field Robotics, 37(3):362-386. DOI: 10.1002/rob.21918.

Gummadi, D., Chan, P. H., Wang, H., and Donzella, V. (2023). Correlating traditional image quality metrics and dnn-based object detection: a case study with compressed camera data. Authorea Preprints. DOI: 10.36227/techrxiv.24566371.

Hao, Y., Pei, H., Lyu, Y., Yuan, Z., Rizzo, J.-R., Wang, Y., and Fang, Y. (2023). Understanding the impact of image quality and distance of objects to object detection performance. In 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 11436-11442. IEEE. DOI: 10.1109/iros55552.2023.10342139.

He, F., Tang, S., Mehrkanoon, S., Huang, X., and Yang, J. (2020). A real-time pcb defect detector based on supervised and semi-supervised learning. In ESANN, pages 527-532. Available at:[link].

He, K., Gkioxari, G., Dollár, P., and Girshick, R. (2017). Mask r-cnn. In Proceedings of the IEEE international conference on computer vision, pages 2961-2969. DOI: 10.1109/iccv.2017.322.

Henning, K.-F., Fritze, A., Gillich, E., Mönks, U., and Lohweg, V. (2015). Stable image acquisition for mobile image processing applications. In Digital Photography XI, volume 9404, pages 177-186. SPIE. DOI: 10.1117/12.2076146.

Hu, B. and Wang, J. (2020). Detection of pcb surface defects with improved faster-rcnn and feature pyramid network. Ieee Access, 8:108335-108345. DOI: 10.1109/access.2020.3001349.

Immerkaer, J. (1996). Fast noise variance estimation. Computer vision and image understanding, 64(2):300-302. Available at:[link].

Jin, C. M., Omar, Z., and Jaward, M. H. (2016). A mobile application of american sign language translation via image processing algorithms. In 2016 IEEE Region 10 Symposium (TENSYMP), pages 104-109. IEEE. DOI: 10.1109/tenconspring.2016.7519386.

Jing, J., Liu, S., Wang, G., Zhang, W., and Sun, C. (2022). Recent advances on image edge detection: A comprehensive review. Neurocomputing, 503:259-271. DOI: 10.1016/j.neucom.2022.06.083.

Kheradmandi, N. and Mehranfar, V. (2022). A critical review and comparative study on image segmentation-based techniques for pavement crack detection. Construction and Building Materials, 321:126162. DOI: 10.1016/j.conbuildmat.2021.126162.

Koik, B. T. and Ibrahim, H. (2013). A literature survey on blur detection algorithms for digital imaging. In 2013 1st International Conference on Artificial Intelligence, Modelling and Simulation, pages 272-277. IEEE. DOI: 10.1109/aims.2013.50.

Kong, L., Ikusan, A., Dai, R., and Zhu, J. (2019). Blind image quality prediction for object detection. In 2019 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR), pages 216-221. DOI: 10.1109/MIPR.2019.00046.

LeCun, Y., Bottou, L., Bengio, Y., and Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278-2324. DOI: 10.1109/5.726791.

Lei, J., Gao, X., Feng, Z., Qiu, H., and Song, M. (2018). Scale insensitive and focus driven mobile screen defect detection in industry. Neurocomputing, 294:72-81. DOI: 10.1016/j.neucom.2018.03.013.

Li, C., Li, L., Jiang, H., Weng, K., Geng, Y., Li, L., Ke, Z., Li, Q., Cheng, M., Nie, W., et al. (2022). Yolov6: A single-stage object detection framework for industrial applications. arXiv preprint arXiv:2209.02976. DOI: 10.48550/arxiv.2209.02976.

Li, Y.-T., Kuo, P., and Guo, J.-I. (2020). Automatic industry pcb board dip process defect detection with deep ensemble method. In 2020 IEEE 29th International Symposium on Industrial Electronics (ISIE), pages 453-459. IEEE. DOI: 10.1109/isie45063.2020.9152533.

Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., and Zitnick, C. L. (2014). Microsoft coco: Common objects in context. In Computer Vision-ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, pages 740-755. Springer. DOI: 10.1007/978-3-319-10602-1_48.

Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., van der Laak, J. A., van Ginneken, B., and Sanchez, C. I. (2017). A survey on deep learning in medical image analysis. Medical image analysis, 42:60-88. DOI: 10.1016/j.media.2017.07.005.

Liu, L., Ke, C., and Lin, H. (2023). Mobile-deep based pcb image segmentation algorithm research. Computers, Materials & Continua, 77(2). DOI: 10.32604/cmc.2023.042582.

Liu, L., Li, H., and Gruteser, M. (2019). Edge assisted real-time object detection for mobile augmented reality. In The 25th annual international conference on mobile computing and networking, pages 1-16. DOI: 10.1145/3300061.3300116.

Liu, L., Ouyang, W., Wang, X., Fieguth, P., Chen, J., Liu, X., and Pietikäinen, M. (2020). Deep learning for generic object detection: A survey. International journal of computer vision, 128(2):261-318. DOI: 10.1007/s11263-019-01247-4.

Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., and Guo, B. (2021). Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE/CVF international conference on computer vision, pages 10012-10022. DOI: 10.1109/iccv48922.2021.00986.

Marengoni, M. and Stringhini, S. (2009). Tutorial: Introdução à visão computacional usando opencv. Revista de Informática Teórica e Aplicada, 16(1):125-160. Available at:[link].

Mittal, A., Moorthy, A. K., and Bovik, A. C. (2012). No-reference image quality assessment in the spatial domain. IEEE Transactions on Image Processing, 21(12):4695-4708. DOI: 10.1109/tip.2012.2214050.

Morikawa, C., Kobayashi, M., Satoh, M., Kuroda, Y., Inomata, T., Matsuo, H., Miura, T., and Hilaga, M. (2021). Image and video processing on mobile devices: a survey. the visual Computer, 37(12):2931-2949. DOI: 10.1007/s00371-021-02200-8.

Nam, W., Youn, T., and Ha, C. (2025). No-reference image quality assessment with moving spectrum and laplacian filter for autonomous driving environment. Vehicles, 7(1):8. DOI: 10.3390/vehicles7010008.

Nayak, A., Chakraborty, S., and Swain, D. K. (2023). Application of smartphone-image processing and transfer learning for rice disease and nutrient deficiency detection. Smart Agricultural Technology, 4:100195. DOI: 10.1016/j.atech.2023.100195.

Nejati, H., Pomponiu, V., Do, T.-T., Zhou, Y., Iravani, S., and Cheung, N.-M. (2016). Smartphone and mobile image processing for assisted living: Health-monitoring apps powered by advanced mobile imaging algorithms. IEEE Signal Processing Magazine, 33(4):30-48. DOI: 10.1109/msp.2016.2549996.

Noh, J., Bae, W., Lee, W., Seo, J., and Kim, G. (2019). Better to follow, follow to be better: Towards precise supervision of feature super-resolution for small object detection. In Proceedings of the IEEE/CVF international conference on computer vision, pages 9725-9734. DOI: 10.1109/iccv.2019.00982.

Oike, Y. (2022). Expanding human potential through imaging and sensing technologies. In 2022 International Electron Devices Meeting (IEDM), pages 1-2. IEEE. DOI: 10.1109/iedm45625.2022.10019533.

Picon, A., Alvarez-Gila, A., Seitz, M., Ortiz-Barredo, A., Echazarra, J., and Johannes, A. (2019). Deep convolutional neural networks for mobile capture device-based crop disease classification in the wild. Computers and Electronics in Agriculture, 161:280-290. DOI: 10.1016/j.compag.2018.04.002.

Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016). You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 779-788. DOI: 10.1109/cvpr.2016.91.

Ren, S., He, K., Girshick, R., and Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems, 28. DOI: 10.1109/tpami.2016.2577031.

Rong, W., Li, Z., Zhang, W., and Sun, L. (2014). An improved canny edge detection algorithm. In 2014 IEEE international conference on mechatronics and automation, pages 577-582. IEEE. DOI: 10.1109/icma.2014.6885761.

Santiago, J. P., Farias, V., Sena, L., Pordeus, J. P., and Machado, J. (2024). Real-time detection of customer-induced damage in printed circuit boards using mobile devices and yolo detectors. Learning and Nonlinear Models - Journal of the Brazilian Society on Computational Intelligence (SBIC), 22:17-31. DOI: 10.21528/lnlm-vol22-no1-art2.

Shukurov, J. (2024). Improve accessibility for low vision and blind people using machine learning and computer vision. arXiv preprint arXiv:2404.00043. DOI: 10.48550/arxiv.2404.00043.

Siddiqui, S. A., Agne, S., Dengel, A., Ahmed, S., et al. (2022). Are deep models robust against real distortions? a case study on document image classification. In 2022 26th International Conference on Pattern Recognition (ICPR), pages 1628-1635. IEEE. DOI: 10.1109/icpr56361.2022.9956167.

Szeliski, R. (2022). Computer vision: algorithms and applications. Springer Nature. DOI: 10.5860/choice.48-5140.

Talebi, H. and Milanfar, P. (2018). Nima: Neural image assessment. IEEE Transactions on Image Processing, 27(8):3998-4011. DOI: 10.1109/tip.2018.2831899.

Tarvainen, A. and Valpola, H. (2017). Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. Advances in neural information processing systems, 30. DOI: 10.48550/arxiv.1703.01780.

Voulodimos, A., Doulamis, N., Doulamis, A., and Protopapadakis, E. (2018). Deep learning for computer vision: A brief review. Computational intelligence and neuroscience, 2018. DOI: 10.1155/2018/7068349.

Wang, Y., Huang, H., Xu, Q., Liu, J., Liu, Y., and Wang, J. (2020). Practical deep raw image denoising on mobile devices. In European Conference on Computer Vision, pages 1-16. Springer. DOI: 10.1007/978-3-030-58539-6_1.

Wang, Z., Bovik, A. C., Sheikh, H. R., and Simoncelli, E. P. (2004). Image quality assessment: from error visibility to structural similarity. IEEE Transactions on Image Processing, 13(4):600-612. DOI: 10.1109/tip.2003.819861.

Xu, M., Zhang, Z., Hu, H., Wang, J., Wang, L., Wei, F., Bai, X., and Liu, Z. (2021). End-to-end semi-supervised object detection with soft teacher. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 3060-3069. DOI: 10.1109/iccv48922.2021.00305.

Zhai, G. and Min, X. (2020). Perceptual image quality assessment: a survey. Science China Information Sciences, 63:1-52. DOI: 10.1007/s11432-019-2757-1.

Zhai, G., Min, X., Gu, K., and Yang, X. (2021). Perceptual image quality assessment: A survey. arXiv preprint arXiv:2109.04380. DOI: 10.1007/s11432-019-2757-1.

Zhang, L., Zhang, L., Mou, X., and Zhang, D. (2011). Fsim: A feature similarity index for image quality assessment. IEEE Transactions on Image Processing, 20(8):2378-2386. DOI: 10.1109/tip.2011.2109730.

Zhou, Y., Yuan, M., Zhang, J., Ding, G., and Qin, S. (2023). Review of vision-based defect detection research and its perspectives for printed circuit board. Journal of Manufacturing Systems, 70:557-578. DOI: 10.1016/j.jmsy.2023.08.019.

Zhou, Z., Rahman Siddiquee, M. M., Tajbakhsh, N., and Liang, J. (2018). Unet++: A nested u-net architecture for medical image segmentation. In Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support: 4th International Workshop, DLMIA 2018, and 8th International Workshop, ML-CDS 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 20, 2018, Proceedings 4, pages 3-11. Springer. DOI: 10.1007/978-3-030-00889-5_1.

Zhu, P., Zhai, G., Min, X., Gu, K., and Liu, Z. (2020). Metaiqa: Deep meta-learning for no-reference image quality assessment. IEEE Transactions on Image Processing, 29:6080-6095. DOI: 10.1109/cvpr42600.2020.01415.

Zou, Z., Shi, Z., Guo, Y., Ye, J., and Others (2019). Object detection in 20 years: A survey. arXiv preprint arXiv:1905.05055. DOI: 10.1109/jproc.2023.3238524.