Autors: Fernandes A., Cruz P., Goncalves G., Slavov, T. N., Georgieva P.
Title: Blemish Detection Algorithms for Image Sensor Improvement and Qualification during Camera Production
Keywords: Anomaly Detection, Blemish Detection, Image Sensor Quality, Isolation Forest algorithm, RAW images

Abstract: Ensuring the quality of image sensors is critical in modern imaging applications, yet traditional blemish detection methods are time-consuming and struggle to scale with increasing sensor resolutions. This paper proposes the Isolation Forest model for efficient and scalable anomaly detection in image sensors. Using a real-world labeled dataset of RAW images provided by Bosch, we extract basic statistical features from the top 10% of pixel intensities to differentiate between defective and non-defective sensors. Despite the severe class imbalance and limited sample size, the iForest model achieved excellent results, with F1 score of 91.3% and perfect recall of 100% on the test set. The proposed method reduces drastically the inspection time (the anomaly can be detected in a less than a second) offering a promising alternative to traditional inspection techniques in high-throughput manufacturing environments.

References

  1. A. Borgeaud, "Surveillance technology market size worldwide from 2022 to 2027, " Statista, Tech. Rep., 2023. [Online]. Available: Https://www.statista.com/statistics/1251839/surveillancetechnology-market-global/
  2. F. Laricchia, "Video surveillance camera market size worldwide from 2019 to 2027, " Statista, Tech. Rep., 2024. [Online]. Available: Https://www.statista.com/statistics/477917/video-surveillanceequipment-market-worldwide/
  3. L. Liu, "A defect detection scheme for hi-end cmos image sensor, " International Symposium on Photoelectronic Detection and Imaging 2009: Advances in Imaging Detectors and Applications, vol. 7384, 2009.
  4. K. Wang, K.-W. Hung, and J. Jiang, "A novel blemish detection algorithm for camera quality testing, " Springer International Publishing AG 2017, p. 224-236, 2017.
  5. W.-M. Ning, "Blemish detection method-us20140185955a1, " Google Patents, 2014. [Online]. Available: Https://patents.google.com/patent/US20140185955
  6. H. Zhang, S. Shen, and I. A. McAllister, "Camera blemish defects detection-us8797429b2, " Google Patents, 2012. [Online]. Available: Https://patents.google.com/patent/US8797429B2/zh
  7. F.-L. Chen and S.-F. Liu, "A neural-network approach to recognize defect spatial pattern in semiconductor fabrication, " IEEE Transactions on Semiconductor Manufacturing, pp. 366-373, 2000.
  8. C.-F. J. Kuo, W.-C. Lo, Y.-R. Huang, H.-Y. Tsai, C.-L. Lee, and H.-C. Wu, "Automated defect inspection system for cmos image sensor with micro multi-layer non-spherical lens module, " Journal of Manufacturing Systems, vol. 45, pp. 248-259, 2017.
  9. R. A. Sizyakin, V. V. Voronin, N. V. Gapon, A. A. Zelensky, and A. Pi?zurica, "Image defect detection algorithm based on deep learning, " IOP Conference Series: Materials Science and Engineering, 2019.
  10. A. Ferreira, C. Almeida, P. Georgieva, A. Tomé, and F. Silva, "Advances in eeg-based biometry, " in Image Analysis and Recognition: 7th International Conference, ICIAR 2010, Póvoa de Varzin, Portugal, June 21-23, 2010, Proceedings, Part II 7. Springer, 2010, pp. 287-295.
  11. D. Malpetti and L. Azzimonti, "Global outlier detection in a federated learning setting with isolation forest, " 2024 2nd Int Conf on Federated Learning Technologies and Applications (FLTA), pp. 251-258, 2024.

Issue

2025 14th Mediterranean Conference on Embedded Computing, MECO 2025 - Proceedings, 2025, Albania, https://doi.org/10.1109/MECO66322.2025.11049190

Вид: публикация в международен форум, публикация в реферирано издание, индексирана в Scopus и Web of Science