Optical Image Processing using Eulerian Amplification

Dominic Wood; Umer Sufan; Cesar Villamil; Dr Richard Wood

doi:10.18535/ijsrm/v12i10.ec03

Abstract

Recent advancements in digital photography, particularly through mobile phone cameras, microscopes, and satellite imaging, have made high-resolution image capture increasingly accessible. However, these captured images often contain subtle changes in color resolution and density that are challenging to observe with the naked eye. This study explores the application of Eulerian amplification as a method to detect and enhance such small-amplitude variations, making them visible for improved analysis. Unlike traditional approaches, Eulerian methods are particularly effective for processing smooth structures and high-quality printed materials where minor amplifications in color can reveal significant grading details.

Using a pixel-by-pixel Eulerian path analysis, this method allows for a detailed comparison of color intensity values on a fine 8-bit scale, which ranges from 0 to 255. Through this analysis, color distribution patterns are visualized across the spatial structure of the image, which is particularly beneficial for identifying specific variations in quality in printed materials, such as highly graded cards. To manage large image structures, spatial decomposition using a multi-level Gaussian pyramid technique is employed. By applying temporal filtering within select frequency bands (0.4–4 Hz) at a coarse pyramid level, the algorithm effectively pools spatial data, enabling the detection of color density shifts that may indicate image defects.

The amplified image data is further processed using a classifier neural network, which provides high sensitivity and specificity in detecting edge defects, image centering issues, scuffs, and breakages. The system demonstrates promising results in identifying true positives while maintaining low false-negative rates, thus confirming the reliability of deep machine learning algorithms in high-sensitivity defect detection. This paper presents the significance of Eulerian amplification in optical image processing, offering a robust tool for precise, automated defect detection across a variety of high-resolution image types.

Keywords

Optical Image ProcessingEulerian AmplificationDigital PhotographyImage Defect

References

Ce Liu, W.T. Freeman, R. Szeliski, and Sing Bing Kang. Noise estimation from a single image. In IEEE CVPR, volume 1, pages 901 – 908, 2006Google Scholar ↗
M.K. Ozkan, M.I. Sezan, and AM Tekalp. Adaptive motion-compensated filtering of noisy image sequences. volume 3, pages 277–290. IEEE, 2002.Google Scholar ↗
E. P. Simoncelli and W. T. Freeman. The steerable pyramid: a flexible architecture for multi-scale derivative computation. In Proceedings of the 1995 International Conference on Image ProcessingGoogle Scholar ↗
(Vol. 3)-Volume 3 - Volume 3, ICIP ’95, pages 3444–, Washington, DC, USA, 1995. IEEE Computer Society.Google Scholar ↗
R. Szeliski, R. Zabih, D. Scharstein, O. Veksler, V. Kolmogorov, A. Agarwala, M. Tappen, and C. Rother. A comparative study of energy minimization methods for markov random fields with smoothnessbased priors. TPAMI, pages 1068–1080, 2007Google Scholar ↗
M.F. Tappen and W.T. Freeman. Comparison of graph cuts with belief propagation for stereo, using identical MRF parameters. In ICCV, pages 900–907, 2003Google Scholar ↗
Shahadi, H. I., Al-Allaq, Z. J., & Albattat, H. J. (2020). Efficient denoising approach based Eulerian video magnification for colour and motion variations. International Journal of Electrical & Computer Engineering (2088-8708), 10(5).Google Scholar ↗
Zhang, Y., Pintea, S. L., & Van Gemert, J. C. (2017). Video acceleration magnification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 529-537).Google Scholar ↗
Bennett, S., El Harake, T. N., Goubran, R., & Knoefel, F. (2017). Adaptive eulerian video processing of thermal video: An experimental analysis. IEEE Transactions on Instrumentation and Measurement, 66(10), 2516-2524.Google Scholar ↗
Qiu, Q. (2020). Automated defect detection in FRP-bonded structures by Eulerian video magnification and adaptive background mixture model. Automation in Construction, 116, 103244.Google Scholar ↗
Wu, X., Yang, X., Jin, J., & Yang, Z. (2018). Amplitude-based filtering for video magnification in presence of large motion. Sensors, 18(7), 2312.Google Scholar ↗
Valente, N. A., do Cabo, C. T., Mao, Z., & Niezrecki, C. (2022). Quantification of phase-based magnified motion using image enhancement and optical flow techniques. Measurement, 189, 110508.Google Scholar ↗
Le Ngo, A. C., Oh, Y. H., Phan, R. C. W., & See, J. (2016, March). Eulerian emotion magnification for subtle expression recognition. In 2016 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 1243-1247). IEEE.Google Scholar ↗
Abnousi, F., Kang, G., Giacomini, J., Yeung, A., Zarafshar, S., Vesom, N., ... & Yong, C. (2019). A novel noninvasive method for remote heart failure monitoring: the EuleriAn video Magnification apPLications In heart Failure studY (AMPLIFY). NPJ digital medicine, 2(1), 80.Google Scholar ↗
Wang, F., Guo, D., Li, K., & Wang, M. (2024, March). Eulermormer: Robust eulerian motion magnification via dynamic filtering within transformer. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 38, No. 6, pp. 5345-5353).Google Scholar ↗
He, X., Goubran, R. A., & Liu, X. P. (2016, February). Wrist pulse measurement and analysis using Eulerian video magnification. In 2016 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI) (pp. 41-44). IEEE.Google Scholar ↗
Ramya Marie, S., & Anudev, J. (2019). Response Analysis of Eulerian Video Magnification. In Proceedings of the International Conference on ISMAC in Computational Vision and Bio-Engineering 2018 (ISMAC-CVB) (pp. 671-678). Springer International Publishing.Google Scholar ↗
Christensen, K., & Adrian, R. J. (2002). Measurement of instantaneous Eulerian acceleration fields by particle image accelerometry: method and accuracy. Experiments in Fluids, 33(6), 759-769.Google Scholar ↗
Won, J., Huang, P. C., & Boppart, S. A. (2020). Phase-based Eulerian motion magnification reveals eardrum mobility from pneumatic otoscopy without sealing the ear canal. Journal of Physics: Photonics, 2(3), 034004.Google Scholar ↗
Hahn, S., Absil, J., Debeir, O., & Metens, T. (2019). Assessment of cardiac‐driven liver movements with filtered harmonic phase image representation, optical flow quantification, and motion amplification. Magnetic resonance in medicine, 81(4), 2788-2798.Google Scholar ↗
Dosso, Y. S., Bekele, A., & Green, J. R. (2018, June). Eulerian magnification of multi-modal RGB-D video for heart rate estimation. In 2018 IEEE International Symposium on Medical Measurements and Applications (MeMeA) (pp. 1-6). IEEE.Google Scholar ↗

[refR-1] Ce Liu, W.T. Freeman, R. Szeliski, and Sing Bing Kang. Noise estimation from a single image. In IEEE CVPR, volume 1, pages 901 – 908, 2006Google Scholar ↗

[refR-2] M.K. Ozkan, M.I. Sezan, and AM Tekalp. Adaptive motion-compensated filtering of noisy image sequences. volume 3, pages 277–290. IEEE, 2002.Google Scholar ↗

[refR-3] E. P. Simoncelli and W. T. Freeman. The steerable pyramid: a flexible architecture for multi-scale derivative computation. In Proceedings of the 1995 International Conference on Image ProcessingGoogle Scholar ↗

[refR-4] (Vol. 3)-Volume 3 - Volume 3, ICIP ’95, pages 3444–, Washington, DC, USA, 1995. IEEE Computer Society.Google Scholar ↗

[refR-5] R. Szeliski, R. Zabih, D. Scharstein, O. Veksler, V. Kolmogorov, A. Agarwala, M. Tappen, and C. Rother. A comparative study of energy minimization methods for markov random fields with smoothnessbased priors. TPAMI, pages 1068–1080, 2007Google Scholar ↗

[refR-6] M.F. Tappen and W.T. Freeman. Comparison of graph cuts with belief propagation for stereo, using identical MRF parameters. In ICCV, pages 900–907, 2003Google Scholar ↗

[refR-7] Shahadi, H. I., Al-Allaq, Z. J., & Albattat, H. J. (2020). Efficient denoising approach based Eulerian video magnification for colour and motion variations. International Journal of Electrical & Computer Engineering (2088-8708), 10(5).Google Scholar ↗

[refR-8] Zhang, Y., Pintea, S. L., & Van Gemert, J. C. (2017). Video acceleration magnification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 529-537).Google Scholar ↗

[refR-9] Bennett, S., El Harake, T. N., Goubran, R., & Knoefel, F. (2017). Adaptive eulerian video processing of thermal video: An experimental analysis. IEEE Transactions on Instrumentation and Measurement, 66(10), 2516-2524.Google Scholar ↗

[refR-10] Qiu, Q. (2020). Automated defect detection in FRP-bonded structures by Eulerian video magnification and adaptive background mixture model. Automation in Construction, 116, 103244.Google Scholar ↗

[refR-11] Wu, X., Yang, X., Jin, J., & Yang, Z. (2018). Amplitude-based filtering for video magnification in presence of large motion. Sensors, 18(7), 2312.Google Scholar ↗

[refR-12] Valente, N. A., do Cabo, C. T., Mao, Z., & Niezrecki, C. (2022). Quantification of phase-based magnified motion using image enhancement and optical flow techniques. Measurement, 189, 110508.Google Scholar ↗

[refR-13] Le Ngo, A. C., Oh, Y. H., Phan, R. C. W., & See, J. (2016, March). Eulerian emotion magnification for subtle expression recognition. In 2016 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 1243-1247). IEEE.Google Scholar ↗

[refR-14] Abnousi, F., Kang, G., Giacomini, J., Yeung, A., Zarafshar, S., Vesom, N., ... & Yong, C. (2019). A novel noninvasive method for remote heart failure monitoring: the EuleriAn video Magnification apPLications In heart Failure studY (AMPLIFY). NPJ digital medicine, 2(1), 80.Google Scholar ↗

[refR-15] Wang, F., Guo, D., Li, K., & Wang, M. (2024, March). Eulermormer: Robust eulerian motion magnification via dynamic filtering within transformer. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 38, No. 6, pp. 5345-5353).Google Scholar ↗

[refR-16] He, X., Goubran, R. A., & Liu, X. P. (2016, February). Wrist pulse measurement and analysis using Eulerian video magnification. In 2016 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI) (pp. 41-44). IEEE.Google Scholar ↗

[refR-17] Ramya Marie, S., & Anudev, J. (2019). Response Analysis of Eulerian Video Magnification. In Proceedings of the International Conference on ISMAC in Computational Vision and Bio-Engineering 2018 (ISMAC-CVB) (pp. 671-678). Springer International Publishing.Google Scholar ↗

[refR-18] Christensen, K., & Adrian, R. J. (2002). Measurement of instantaneous Eulerian acceleration fields by particle image accelerometry: method and accuracy. Experiments in Fluids, 33(6), 759-769.Google Scholar ↗

[refR-19] Won, J., Huang, P. C., & Boppart, S. A. (2020). Phase-based Eulerian motion magnification reveals eardrum mobility from pneumatic otoscopy without sealing the ear canal. Journal of Physics: Photonics, 2(3), 034004.Google Scholar ↗

[refR-20] Hahn, S., Absil, J., Debeir, O., & Metens, T. (2019). Assessment of cardiac‐driven liver movements with filtered harmonic phase image representation, optical flow quantification, and motion amplification. Magnetic resonance in medicine, 81(4), 2788-2798.Google Scholar ↗

[refR-21] Dosso, Y. S., Bekele, A., & Green, J. R. (2018, June). Eulerian magnification of multi-modal RGB-D video for heart rate estimation. In 2018 IEEE International Symposium on Medical Measurements and Applications (MeMeA) (pp. 1-6). IEEE.Google Scholar ↗