Spectral Reconstruction from RGB Imagery: A Potential Option for Infinite Spectral Data?
Abstract
:1. Introduction
2. Related Work
2.1. Spectral Image Acquisition
2.2. SR from RGB
3. Methodology
Evaluation Metrics
- Root Mean Square Error:
- Peak Signal-to-Noise Ratio:
- Structural Similarity Index:
- Mean Relative Absolute Error:
- Entropy Similarity Metric:While commonly employed in fields like molecular spectroscopy [50] for its ability to capture the similarity in entropy distributions between spectra, entropy similarity remains relatively underutilised within the spectral imaging community. Unlike conventional metrics, Entropy Similarity provides a comprehensive assessment of the fidelity of spectral reconstruction by quantifying the agreement between the spectral entropy patterns of the reconstructed and ground truth spectra.
- This analysis involved concatenating the reconstructed spectra (from both MST++ and A++) with the ground-truth spectral image. The concatenated data facilitated the generation of clouds of points, enabling a visual comparison of the spectral distributions. By aligning the reconstructed and original spectral data on the same axis, PCA allowed for a comprehensive exploration of the variance within the spectra;
- Also, we performed PCA without concatenation, directly computing the eigenvectors to investigate the spectral distribution of reconstructed data, generated by both models, against original spectral data and their RGB counterpart. This approach provided insights into the underlying structures of the spectral data without the influence of concatenation. Through the computation of eigenvectors, we gained a deeper understanding of the spectral variability and the principal components driving the variance within the spectra.
4. Analysis
4.1. Spectral Analysis
4.2. Colorimetric Analysis
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Backman, V.; Wallace, M.B.; Perelman, L.; Arendt, J.; Gurjar, R.; Müller, M.; Zhang, Q.; Zonios, G.; Kline, E.; McGillican, T.; et al. Detection of preinvasive cancer cells. Nature 2000, 406, 35–36. [Google Scholar] [CrossRef] [PubMed]
- Meng, Z.; Qiao, M.; Ma, J.; Yu, Z.; Xu, K.; Yuan, X. Snapshot multispectral endomicroscopy. Opt. Lett. 2020, 45, 3897–3900. [Google Scholar] [CrossRef] [PubMed]
- Borengasser, M.; Hungate, W.S.; Watkins, R. Hyperspectral Remote Sensing: Principles and Applications; CRC Press: Boca Raton, FL, USA, 2007. [Google Scholar]
- Yuan, Y.; Zheng, X.; Lu, X. Hyperspectral image superresolution by transfer learning. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2017, 10, 1963–1974. [Google Scholar] [CrossRef]
- Kim, M.H.; Harvey, T.A.; Kittle, D.S.; Rushmeier, H.; Dorsey, J.; Prum, R.O.; Brady, D.J. 3D imaging spectroscopy for measuring hyperspectral patterns on solid objects. ACM Trans. Graph. (TOG) 2012, 31, 1–11. [Google Scholar] [CrossRef]
- Glatt, O.; Ater, Y.; Kim, W.S.; Werman, S.; Berby, O.; Zini, Y.; Zelinger, S.; Lee, S.; Choi, H.; Soloveichik, E. Beyond RGB: A Real World Dataset for Multispectral Imaging in Mobile Devices. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, Waikoloa, HI, USA, 3–8 January 2024; pp. 4344–4354. [Google Scholar]
- Arad, B.; Ben-Shahar, O.; Timofte, R.; Van Gool, L.; Zhang, L.; Yang, M.; Xiong, Z.; Chen, C.; Shi, Z.; Liu, D.; et al. NTIRE 2018 challenge on spectral reconstruction from RGB Images. In Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Salt Lake City, UT, USA, 18–22 June 2018; p. 1042. [Google Scholar]
- Thomas, J.B.; Lapray, P.J.; Derhak, M.; Farup, I. Standard representation space for spectral imaging. In Proceedings of the Color and Imaging Conference, Paris, France, 13–17 November 2023; Volume 31, pp. 1–6. [Google Scholar]
- Deng, J.; Dong, W.; Socher, R.; Li, L.J.; Li, K.; Fei-Fei, L. Imagenet: A large-scale hierarchical image database. In Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA, 20–25 June 2009; IEEE: Piscataway, NJ, USA, 2009; pp. 248–255. [Google Scholar]
- Buzzelli, M.; Tchobanou, M.K.; Schettini, R.; Bianco, S. A general-purpose pipeline for realistic synthetic multispectral image dataset generation. In Proceedings of the Color and Imaging Conference, Paris, France, 13–17 November 2023; Society for Imaging Science and Technology: Springfield, VA, USA, 2023; Volume 31, pp. 155–160. [Google Scholar]
- Chen, Q.; Cheung, T.; Westland, S. Physical modelling of spectral reflectance. In Proceedings of the 10th Congress of the International Color Association, Granada, Spain, 9–13 May 2005; pp. 1151–1154. [Google Scholar]
- Cao, X.; Yue, T.; Lin, X.; Lin, S.; Yuan, X.; Dai, Q.; Carin, L.; Brady, D.J. Computational snapshot multispectral cameras: Toward dynamic capture of the spectral world. IEEE Signal Process. Mag. 2016, 33, 95–108. [Google Scholar] [CrossRef]
- Poli, D.; Toutin, T. Review of developments in geometric modelling for high resolution satellite pushbroom sensors. Photogramm. Rec. 2012, 27, 58–73. [Google Scholar] [CrossRef]
- Du, H.; Tong, X.; Cao, X.; Lin, S. A prism-based system for multispectral video acquisition. In Proceedings of the 2009 IEEE 12th International Conference on Computer Vision, Kyoto, Japan, 29 September–2 October 2009; IEEE: Piscataway, NJ, USA, 2009; pp. 175–182. [Google Scholar]
- Llull, P.; Liao, X.; Yuan, X.; Yang, J.; Kittle, D.; Carin, L.; Sapiro, G.; Brady, D.J. Coded aperture compressive temporal imaging. Opt. Express 2013, 21, 10526–10545. [Google Scholar] [CrossRef] [PubMed]
- Wagadarikar, A.; John, R.; Willett, R.; Brady, D. Single disperser design for coded aperture snapshot spectral imaging. Appl. Opt. 2008, 47, B44–B51. [Google Scholar] [CrossRef] [PubMed]
- Wagadarikar, A.A.; Pitsianis, N.P.; Sun, X.; Brady, D.J. Video rate spectral imaging using a coded aperture snapshot spectral imager. Opt. Express 2009, 17, 6368–6388. [Google Scholar] [CrossRef] [PubMed]
- Meng, Z.; Ma, J.; Yuan, X. End-to-end low cost compressive spectral imaging with spatial-spectral self-attention. In Proceedings of the European Conference on Computer Vision, Glasgow, UK, 23–28 August 2020; Springer: Berlin/Heidelberg, Germany, 2020; pp. 187–204. [Google Scholar]
- Yuan, X.; Brady, D.J.; Katsaggelos, A.K. Snapshot compressive imaging: Theory, algorithms, and applications. IEEE Signal Process. Mag. 2021, 38, 65–88. [Google Scholar] [CrossRef]
- Maloney, L.T.; Wandell, B.A. Color constancy: A method for recovering surface spectral reflectance. In Readings in Computer Vision; Elsevier: Amsterdam, The Netherlands, 1987; pp. 293–297. [Google Scholar]
- Agahian, F.; Amirshahi, S.A.; Amirshahi, S.H. Reconstruction of reflectance spectra using weighted principal component analysis. Color Res. Appl. 2008, 33, 360–371. [Google Scholar] [CrossRef]
- Heikkinen, V.; Lenz, R.; Jetsu, T.; Parkkinen, J.; Hauta-Kasari, M.; Jääskeläinen, T. Evaluation and unification of some methods for estimating reflectance spectra from RGB images. JOSA A 2008, 25, 2444–2458. [Google Scholar] [CrossRef] [PubMed]
- Lin, Y.T.; Finlayson, G.D. Exposure invariance in spectral reconstruction from rgb images. In Proceedings of the Color and Imaging Conference, Paris, France, 21–25 October 2019; Society for Imaging Science and Technology: Springfield, VA, USA, 2019; Volume 27, pp. 284–289. [Google Scholar]
- Connah, D.R.; Hardeberg, J.Y. Spectral recovery using polynomial models. In Proceedings of the Color Imaging X: Processing, Hardcopy, and Applications, San Jose, CA, USA, 17 January 2005; SPIE: Bellingham, WA, USA, 2005; Volume 5667, pp. 65–75. [Google Scholar]
- Brainard, D.H.; Freeman, W.T. Bayesian color constancy. JOSA A 1997, 14, 1393–1411. [Google Scholar] [CrossRef] [PubMed]
- Morovic, P.; Finlayson, G.D. Metamer-set-based approach to estimating surface reflectance from camera RGB. JOSA A 2006, 23, 1814–1822. [Google Scholar] [CrossRef] [PubMed]
- Hardeberg, J.Y. On the spectral dimensionality of object colours. In Proceedings of the Conference on Colour in Graphics, Imaging, and Vision, Poitiers, France, 2–5 April 2002; Society of Imaging Science and Technology: Springfield, VA, USA, 2002; Volume 1, pp. 480–485. [Google Scholar]
- Chakrabarti, A.; Zickler, T. Statistics of real-world hyperspectral images. In Proceedings of the CVPR 2011, Colorado Springs, CO, USA, 20–25 June 2011; IEEE: Piscataway, NJ, USA, 2011; pp. 193–200. [Google Scholar]
- Arad, B.; Timofte, R.; Ben-Shahar, O.; Lin, Y.T.; Finlayson, G.D. NTIRE 2020 challenge on spectral reconstruction from an RGB image. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Seattle, WA, USA, 14–19 June 2020; pp. 446–447. [Google Scholar]
- Li, J.; Wu, C.; Song, R.; Li, Y.; Liu, F. Adaptive weighted attention network with camera spectral sensitivity prior for spectral reconstruction from RGB images. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Seattle, WA, USA, 14–19 June 2020; pp. 462–463. [Google Scholar]
- Arun, P.V.; Buddhiraju, K.M.; Porwal, A.; Chanussot, J. CNN based spectral super-resolution of remote sensing images. Signal Process. 2020, 169, 107394. [Google Scholar] [CrossRef]
- Fubara, B.J.; Sedky, M.; Dyke, D. RGB to spectral reconstruction via learned basis functions and weights. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Seattle, WA, USA, 14–19 June 2020; pp. 480–481. [Google Scholar]
- Shi, Z.; Chen, C.; Xiong, Z.; Liu, D.; Wu, F. HSCNN+: Advanced CNN-based hyperspectral recovery from RGB images. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Salt Lake City, UT, USA, 18–23 June 2018; pp. 939–947. [Google Scholar]
- Zhao, Y.; Po, L.M.; Yan, Q.; Liu, W.; Lin, T. Hierarchical regression network for spectral reconstruction from RGB images. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Seattle, WA, USA, 14–19 June 2020; pp. 422–423. [Google Scholar]
- Arad, B.; Ben-Shahar, O. Sparse recovery of hyperspectral signal from natural RGB images. In Proceedings of the Computer Vision—ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, 11–14 October 2016; Proceedings, Part VII 14. Springer: Berlin/Heidelberg, Germany, 2016; pp. 19–34. [Google Scholar]
- Nguyen, R.M.; Prasad, D.K.; Brown, M.S. Training-based spectral reconstruction from a single RGB image. In Proceedings of the Computer Vision—ECCV 2014: 13th European Conference, Zurich, Switzerland, 6–12 September 2014; Proceedings, Part VII 13. Springer: Berlin/Heidelberg, Germany, 2014; pp. 186–201. [Google Scholar]
- Sharma, G.; Wang, S. Spectrum recovery from colorimetric data for color reproductions. In Proceedings of the Color Imaging: Device-Independent Color, Color Hardcopy, and Applications VII, San Jose, CA, USA, 19–25 January 2002; SPIE: Bellingham, WA, USA, 2001; Volume 4663, pp. 8–14. [Google Scholar]
- Ribés, A.; Schmit, F. Reconstructing spectral reflectances with mixture density networks. In Proceedings of the Conference on Colour in Graphics, Imaging, and Vision, Poitiers, France, 2–5 April 2002; Society of Imaging Science and Technology: Springfield, VA, USA, 2002; Volume 1, pp. 486–491. [Google Scholar]
- Lin, Y.T.; Finlayson, G.D. On the optimization of regression-based spectral reconstruction. Sensors 2021, 21, 5586. [Google Scholar] [CrossRef] [PubMed]
- Aeschbacher, J.; Wu, J.; Timofte, R. In defense of shallow learned spectral reconstruction from RGB images. In Proceedings of the IEEE International Conference on Computer Vision Workshops, Venice, Italy, 22–29 October 2017; pp. 471–479. [Google Scholar]
- Stiebel, T.; Merhof, D. Brightness invariant deep spectral super-resolution. Sensors 2020, 20, 5789. [Google Scholar] [CrossRef]
- Uzair, M.; Mahmood, A.; Mian, A. Hyperspectral face recognition with spatiospectral information fusion and PLS regression. IEEE Trans. Image Process. 2015, 24, 1127–1137. [Google Scholar] [CrossRef] [PubMed]
- Parmar, M.; Lansel, S.; Wandell, B.A. Spatio-spectral reconstruction of the multispectral datacube using sparse recovery. In Proceedings of the 2008 15th IEEE International Conference on Image Processing, San Diego, CA, USA, 12–15 October 2008; IEEE: Piscataway, NJ, USA, 2008; pp. 473–476. [Google Scholar]
- Zhang, J.; Su, R.; Fu, Q.; Ren, W.; Heide, F.; Nie, Y. A survey on computational spectral reconstruction methods from RGB to hyperspectral imaging. Sci. Rep. 2022, 12, 11905. [Google Scholar] [CrossRef] [PubMed]
- Lin, Y.-T.; Finlayson, G.D. Physically plausible spectral reconstruction. Sensors 2020, 20, 6399. [Google Scholar] [CrossRef]
- Cai, Y.; Lin, J.; Lin, Z.; Wang, H.; Zhang, Y.; Pfister, H.; Timofte, R.; Van Gool, L. MST++: Multi-stage spectral-wise transformer for efficient spectral reconstruction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA, 18–24 June 2022; pp. 745–755. [Google Scholar]
- Lin, Y.T.; Finlayson, G.D. A rehabilitation of pixel-based spectral reconstruction from RGB images. Sensors 2023, 23, 4155. [Google Scholar] [CrossRef] [PubMed]
- Le Moan, S.; George, S.T.; Pedersen, M.; Blahová, J.; Hardeberg, J.Y. A database for spectral image quality. In Proceedings of the Image Quality and System Performance XII, San Francisco, CA, USA, 8–12 February 2015; SPIE: Bellingham, WA, USA, 2015; Volume 9396, pp. 225–232. [Google Scholar]
- Yasuma, F.; Mitsunaga, T.; Iso, D.; Nayar, S. Generalized Assorted Pixel Camera: Post-Capture Control of Resolution, Dynamic Range and Spectrum. IEEE Trans. Image Process. 2010, 19, 2241–2253, Technical Report, 2008. [Google Scholar] [CrossRef] [PubMed]
- Li, Y.; Kind, T.; Folz, J.; Vaniya, A.; Mehta, S.S.; Fiehn, O. Spectral entropy outperforms MS/MS dot product similarity for small-molecule compound identification. Nat. Methods 2021, 18, 1524–1531. [Google Scholar] [CrossRef] [PubMed]
- CIE. Technical Report 3rd Edition. 2004. Available online: https://cielab.xyz/pdf/cie.15.2004%20colorimetry.pdf (accessed on 9 May 2024).
- Burns, S.A. Chromatic adaptation transform by spectral reconstruction. Color Res. Appl. 2019, 44, 682–693. [Google Scholar] [CrossRef]
Scene | PSNR ↑ | SSIM ↑ | MRAE ↓ | ES ↑ | ||||
---|---|---|---|---|---|---|---|---|
A++ | MST++ | A++ | MST++ | A++ | MST++ | A++ | MST++ | |
Cork | 33.46 | 38.21 | 0.9907 | 0.9982 | 0.153 | 0.063 | 0.967 | 0.952 |
Hat | 27.03 | 30.13 | 0.9829 | 0.9954 | 0.234 | 0.109 | 0.899 | 0.962 |
Leaves | 36.34 | 37.96 | 0.9932 | 0.9946 | 0.132 | 0.076 | 0.988 | 0.915 |
Orange | 30.38 | 34.27 | 0.9367 | 0.9971 | 0.266 | 0.090 | 0.937 | 0.931 |
Painting | 34.36 | 36.54 | 0.9919 | 0.9979 | 0.094 | 0.075 | 0.969 | 0.939 |
Paper 1 | 22.37 | 28.42 | 0.9658 | 0.9836 | 0.230 | 0.163 | 0.950 | 0.974 |
Skin 1 | 31.63 | 40.95 | 0.9881 | 0.9987 | 0.197 | 0.061 | 0.939 | 0.984 |
Skin 2 | 25.84 | 29.17 | 0.9877 | 0.9939 | 0.202 | 0.123 | 0.943 | 0.917 |
Wood | 35.93 | 39.31 | 0.9947 | 0.9984 | 0.1313 | 0.076 | 0.937 | 0.864 |
Average | 30.70 | 34.65 | 0.9831 | 0.9953 | 0.182 | 0.092 | 0.943 | 0.936 |
Scene | PSNR ↑ | SSIM ↑ | MRAE ↓ | ES ↑ | ||||
---|---|---|---|---|---|---|---|---|
A++ | MST++ | A++ | MST++ | A++ | MST++ | A++ | MST++ | |
Balloons | 24.89 | 26.10 | 0.9674 | 0.9927 | 0.4119 | 0.146 | 0.902 | 0.913 |
Beads | 25.07 | 28.76 | 0.9855 | 0.9952 | 0.2776 | 0.0968 | 0.9457 | 0.7791 |
CD | 28.49 | 35.15 | 0.946 | 0.997 | 0.575 | 0.072 | 0.9373 | 0.7997 |
Chart | 22.89 | 27.26 | 0.9674 | 0.9806 | 0.415 | 0.227 | 0.9561 | 0.8665 |
Clay | 29.94 | 33.46 | 0.9850 | 0.9968 | 0.294 | 0.063 | 0.8992 | 0.8949 |
Cloth | 25.85 | 29.98 | 0.9771 | 0.9960 | 0.3364 | 0.1208 | 0.9307 | 0.8461 |
Egyptian Statue | 26.16 | 28.18 | 0.9676 | 0.9942 | 0.4478 | 0.1144 | 0.8114 | 0.6485 |
Face | 21.66 | 24.59 | 0.9845 | 0.9913 | 0.2943 | 0.1648 | 0.8806 | 0.7649 |
Beers | 25.86 | 28.75 | 0.9908 | 0.9883 | 0.1749 | 0.1996 | 0.8050 | 0.9753 |
Food | 29.09 | 32.00 | 0.9906 | 0.9963 | 0.2297 | 0.0854 | 0.8676 | 0.8477 |
Lemon Slices | 31.85 | 34.14 | 0.9915 | 0.9971 | 0.2195 | 0.092 | 0.8336 | 0.8066 |
Lemon | 24.36 | 27.79 | 0.9909 | 0.9939 | 0.2224 | 0.1319 | 0.8643 | 0.7872 |
Peppers | 26.31 | 28.76 | 0.9909 | 0.9945 | 0.2231 | 0.1119 | 0.9549 | 0.8100 |
Strawberries | 29.65 | 31.59 | 0.9620 | 0.9961 | 0.4762 | 0.1035 | 0.8961 | 0.7992 |
Sushi | 34.70 | 39.97 | 0.9756 | 0.9985 | 0.3892 | 0.0465 | 0.8892 | 0.8674 |
Tomatoes | 35.09 | 39.25 | 0.9708 | 0.9984 | 0.4267 | 0.0472 | 0.8034 | 0.8144 |
Feathers | 22.24 | 26.31 | 0.9800 | 0.9930 | 0.3276 | 0.1273 | 0.8974 | 0.7680 |
Flowers | 22.93 | 25.62 | 0.9632 | 0.9924 | 0.4645 | 0.1375 | 0.8779 | 0.7484 |
Glass Tiles | 26.48 | 28.84 | 0.9864 | 0.9950 | 0.2685 | 0.1153 | 0.9486 | 0.7792 |
Hairs | 24.24 | 25.04 | 0.9909 | 0.99179 | 0.2167 | 0.1490 | 0.8960 | 0.8563 |
Jelly Beans | 24.42 | 25.21 | 0.9864 | 0.9925 | 0.2645 | 0.1492 | 0.9040 | 0.7114 |
Oil Painting | 25.08 | 27.05 | 0.9920 | 0.9935 | 0.2004 | 0.1420 | 0.9532 | 0.9113 |
Paints | 21.26 | 22.23 | 0.9617 | 0.9889 | 0.4419 | 0.1780 | 0.9485 | 0.8869 |
Photo and Face | 20.48 | 25.73 | 0.9858 | 0.9923 | 0.2865 | 0.1497 | 0.9125 | 0.7178 |
Pompoms | 23.95 | 25.18 | 0.9600 | 0.9919 | 0.4554 | 0.1491 | 0.9575 | 0.8082 |
Apples | 29.88 | 31.28 | 0.9639 | 0.9959 | 0.4711 | 0.0973 | 0.8320 | 0.7155 |
Peppers | 21.66 | 23.93 | 0.9759 | 0.9906 | 0.3579 | 0.1679 | 0.9196 | 0.7983 |
Sponges | 21.63 | 22.43 | 0.9635 | 0.9828 | 0.4141 | 0.1967 | 0.9675 | 0.8429 |
Stuffed Toys | 25.08 | 26.87 | 0.9743 | 0.9933 | 0.3747 | 0.1237 | 0.9291 | 0.8464 |
Superballs | 33.04 | 34.96 | 0.9791 | 0.9973 | 0.3532 | 0.0596 | 0.8943 | 0.8665 |
Thread Spools | 25.19 | 28.28 | 0.9885 | 0.9942 | 0.2506 | 0.1273 | 0.8529 | 0.7596 |
Average | 26.45 | 29.12 | 0.9826 | 0.9901 | 0.3521 | 0.1298 | 0.9289 | 0.8874 |
Scene | CIE D65 | CIE A | LED B1 | |||
---|---|---|---|---|---|---|
A++ | MST++ | A++ | MST++ | A++ | MST++ | |
Cork | 0.440 | 0.203 | 0.455 | 0.229 | 0.484 | 0.2 |
Hat | 0.650 | 0.764 | 0.795 | 0.604 | 0.950 | 0.703 |
Leaves | 0.503 | 0.310 | 0.578 | 0.365 | 0.523 | 0.346 |
Orange | 0.306 | 0.654 | 0.569 | 0.462 | 0.481 | 0.599 |
Painting | 0.287 | 0.293 | 0.301 | 0.305 | 0.310 | 0.287 |
Paper 1 | 0.592 | 0.547 | 0.785 | 0.497 | 0.599 | 0.516 |
Skin 1 | 0.385 | 0.240 | 0.812 | 0.254 | 0.874 | 0.226 |
Skin 2 | 0.270 | 0.217 | 0.737 | 0.256 | 0.721 | 0.217 |
Wood | 0.370 | 0.299 | 0.683 | 0.334 | 0.614 | 0.303 |
Average | 0.635 | 0.617 |
Scene | CIE D65 | CIE A | LED B1 | |||
---|---|---|---|---|---|---|
A++ | MST++ | A++ | MST++ | A++ | MST++ | |
Balloons | 0.58 | 0.27 | 0.680 | 0.27 | 0.633 | 0.263 |
Beads | 0.73 | 0.33 | 0.907 | 0.29 | 0.760 | 0.334 |
CD | 0.46 | 0.22 | 0.603 | 0.26 | 0.449 | 0.247 |
Chart | 0.32 | 0.21 | 0.419 | 0.24 | 0.354 | 0.229 |
Clay | 0.68 | 0.28 | 0.929 | 0.25 | 0.731 | 0.279 |
Cloth | 0.44 | 0.24 | 0.392 | 0.21 | 0.481 | 0.253 |
Egyptian Statue | 0.31 | 0.21 | 0.422 | 0.23 | 0.329 | 0.204 |
Face | 0.32 | 0.25 | 0.426 | 0.26 | 0.368 | 0.246 |
Beers | 0.31 | 0.21 | 0.361 | 0.21 | 0.355 | 0.205 |
Food | 0.54 | 0.23 | 0.677 | 0.19 | 0.581 | 0.215 |
Lemon Slices | 0.37 | 0.25 | 0.472 | 0.26 | 0.395 | 0.253 |
Lemon | 0.52 | 0.28 | 0.804 | 0.27 | 0.523 | 0.285 |
Peppers | 0.63 | 0.27 | 0.835 | 0.275 | 0.679 | 0.287 |
Strawberries | 0.43 | 0.29 | 0.541 | 0.271 | 0.456 | 0.268 |
Sushi | 0.37 | 0.19 | 0.515 | 0.214 | 0.407 | 0.217 |
Tomatoes | 0.36 | 0.21 | 0.506 | 0.201 | 0.390 | 0.205 |
Feathers | 0.52 | 0.27 | 0.720 | 0.225 | 0.569 | 0.249 |
Flowers | 0.43 | 0.27 | 0.583 | 0.245 | 0.501 | 0.249 |
Glass Tiles | 0.60 | 0.22 | 0.713 | 0.237 | 0.627 | 0.247 |
Hairs | 0.33 | 0.22 | 0.378 | 0.236 | 0.311 | 0.221 |
Jelly Beans | 0.51 | 0.26 | 0.571 | 0.264 | 0.521 | 0.261 |
Oil Painting | 0.47 | 0.26 | 0.601 | 0.261 | 0.474 | 0.259 |
Paints | 0.39 | 0.20 | 0.498 | 0.212 | 0.445 | 0.212 |
Photo and Face | 0.29 | 0.26 | 0.398 | 0.274 | 0.327 | 0.255 |
Pompoms | 0.65 | 0.29 | 0.845 | 0.209 | 0.744 | 0.236 |
Apples | 0.45 | 0.23 | 0.580 | 0.242 | 0.492 | 0.249 |
Peppers | 0.60 | 0.30 | 0.999 | 0.287 | 0.669 | 0.306 |
Sponges | 0.81 | 0.29 | 0.130 | 0.240 | 0.925 | 0.265 |
Stuffed Toys | 0.45 | 0.24 | 0.545 | 0.202 | 0.474 | 0.242 |
Superballs | 0.53 | 0.28 | 0.660 | 0.243 | 0.531 | 0.272 |
Thread Spools | 0.41 | 0.24 | 0.573 | 0.271 | 0.413 | 0.275 |
Average | 0.477 | 0.259 | 0.589 | 0.243 | 0.513 | 0.251 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Fsian, A.N.; Thomas, J.-B.; Hardeberg, J.Y.; Gouton, P. Spectral Reconstruction from RGB Imagery: A Potential Option for Infinite Spectral Data? Sensors 2024, 24, 3666. https://doi.org/10.3390/s24113666
Fsian AN, Thomas J-B, Hardeberg JY, Gouton P. Spectral Reconstruction from RGB Imagery: A Potential Option for Infinite Spectral Data? Sensors. 2024; 24(11):3666. https://doi.org/10.3390/s24113666
Chicago/Turabian StyleFsian, Abdelhamid N., Jean-Baptiste Thomas, Jon Y. Hardeberg, and Pierre Gouton. 2024. "Spectral Reconstruction from RGB Imagery: A Potential Option for Infinite Spectral Data?" Sensors 24, no. 11: 3666. https://doi.org/10.3390/s24113666
APA StyleFsian, A. N., Thomas, J.-B., Hardeberg, J. Y., & Gouton, P. (2024). Spectral Reconstruction from RGB Imagery: A Potential Option for Infinite Spectral Data? Sensors, 24(11), 3666. https://doi.org/10.3390/s24113666