Recovering spectral reflectance based on natural neighbor interpolation with model‐based metameric spectra of extreme points

Chou, Tzren Ru; Hsieh, Chi Heng; Chen, En

doi:10.1002/col.22366

Cited by 7 publications

(22 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, direct spectral measurements are expensive. Indirect measurements using the spectrum reconstruction technique are of interest [6][7][8][9][10][11][12][13][14]. The spectrum of the image pixel is reconstructed from the channel outputs of the image acquisition device.…”

Section: Introductionmentioning

confidence: 99%

“…Orthogonal projection [6], principal component analysis (PCA) [7,8], Gaussian mixture [9], non-negative matrix transformation (NMT) [10,11] and interpolation [11][12][13][14] have been proposed for spectrum reconstruction. Indirect methods that require training spectra are also known as learning-based methods, such as orthogonal projection, PCA and NMT.…”

Section: Introductionmentioning

confidence: 99%

“…The interpolation method uses reference spectra to reconstruct a spectrum interpolated from input values, e.g., XYZ tristimulus values [11][12][13] and RGB signal values [14]. Due to the use of a look-up table (LUT) to store the reference spectra, this method is often referred to as the LUT method.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Auxiliary Reference Samples for Extrapolating Spectral Reflectance from Camera RGB Signals

Wen

Hsu

et al. 2022

Sensors

View full text Add to dashboard Cite

Surface spectral reflectance is useful for color reproduction. In this study, the reconstruction of spectral reflectance using a conventional camera was investigated. The spectrum reconstruction error could be reduced by interpolating camera RGB signals, in contrast to methods based on basis spectra, such as principal component analysis (PCA). The disadvantage of the interpolation method is that it cannot interpolate samples outside the convex hull of reference samples in the RGB signal space. An interpolation method utilizing auxiliary reference samples (ARSs) to extrapolate the outside samples is proposed in this paper. The ARSs were created using reference samples and color filters. The convex hull of the reference samples and ARSs was expanded to enclose outside samples for extrapolation. A commercially available camera was taken as an example. The results show that with the proposed method, the extrapolation error was smaller than that of the computationally time-consuming weighted PCA method. A low cost and fast detection speed for spectral reflectance recovery can be achieved using a conventional camera.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Auxiliary Reference Samples for Extrapolating Spectral Reflectance from Camera RGB Signals

Wen

Hsu

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…A new transformation is conducted on the verification sample by the adaptive selection of training depending on the spectral similarity of the sample to calculate the reflectance matrix. The natural neighborhood interpolation method [ 10 ] is used to reconstruct spectra from different samples, which expands the range of sample selection. However, the local interpolation method [ 11 ] estimates the reflectance curve of n-dimensional space from the corresponding tristimulus value, namely, the CIEXYZ or CIELAB sample value, which is also the earliest low-channel to multi-channel spectral study.…”

Section: Introductionmentioning

confidence: 99%

Double Ghost Convolution Attention Mechanism Network: A Framework for Hyperspectral Reconstruction of a Single RGB Image

Wang

Jiangwei

2021

Sensors

View full text Add to dashboard Cite

Current research on the reconstruction of hyperspectral images from RGB images using deep learning mainly focuses on learning complex mappings through deeper and wider convolutional neural networks (CNNs). However, the reconstruction accuracy of the hyperspectral image is not high and among other issues the model for generating these images takes up too much storage space. In this study, we propose the double ghost convolution attention mechanism network (DGCAMN) framework for the reconstruction of a single RGB image to improve the accuracy of spectral reconstruction and reduce the storage occupied by the model. The proposed DGCAMN consists of a double ghost residual attention block (DGRAB) module and optimal nonlocal block (ONB). DGRAB module uses GhostNet and PRELU activation functions to reduce the calculation parameters of the data and reduce the storage size of the generative model. At the same time, the proposed double output feature Convolutional Block Attention Module (DOFCBAM) is used to capture the texture details on the feature map to maximize the content of the reconstructed hyperspectral image. In the proposed ONB, the Argmax activation function is used to obtain the region with the most abundant feature information and maximize the most useful feature parameters. This helps to improve the accuracy of spectral reconstruction. These contributions enable the DGCAMN framework to achieve the highest spectral accuracy with minimal storage consumption. The proposed method has been applied to the NTIRE 2020 dataset. Experimental results show that the proposed DGCAMN method outperforms the spectral accuracy reconstructed by advanced deep learning methods and greatly reduces storage consumption.

show abstract

“…The main techniques can be summarized as Weiner estimation (Hubelet al, 1994), pseudo-inverse or direct mapping (Valero et al, 2007, Babaei et al, 2011, basis functions (García-Beltrán et al, 1998), single value decomposition (SVD) (Shimano et al, 2007), R-matrix (Zhao and Berns, 2007), and PCA Brill, 2004, Cao et al, 2018). Also, more recently, research is focused on optimized methods to improve the results (Liang and Wan, 2017, Cao et al, 2017, Heikkinen, 2018, Chou et al, 2019, Liang et al, 2019.…”

Section: Spectral Recoverymentioning

confidence: 99%

Colorimetric and spectral analysis of rock art by means of the characterization of digital sensors

Tebar¹

View full text Add to dashboard Cite

We could live in black and white, but fortunately, life is in color. Color is a source of emotion, of memories, of sensations. Color makes us happy. It's the same with people. Like colors, there are people who calm you down, evoke memories, embrace you, smile at you. My gratitude goes first of all to these people, who, like colors, have brought fullness to my life. Especially, to my parents, my sister and my friends, who have always been there, and will always be.During my PhD, I had to go through moments of light and darkness. It has been a long, hard road, but it was worth it. I have learned a lot. Thank you, José Luis andÁngel, for guiding me through these years. Your contributions have been essential in bringing color to this thesis. Thanks also to a simple email. An email that changed my life. Thank you Stephen for responding positively to my request, and allowing me to take six amazing months in Leeds (UK), collaborating in the Colour Research Group at the School of Design. A dream come true! Thanks also to Zeynep, for the month stay at Mimar Sinan Fine Arts University (Istanbul, Turkey). I enjoyed the amazing sights and monuments. When I think of Istanbul, I remember colors. Thanks to all of you! Finally, thank you very much to my colleagues in GIFLE. We have laughed, we have cried (haven't we, Inés?), but most of all we have enjoyed ourselves. Thanks Silvia and Berta. "Our meetings in Switzerland" were always the best. Thanks to my University, the Universitat Politècnica de València for the FPI scholarship that allowed me to fulfill my dream. And of course, thanks to my Department, the DICGF, which for the last years has been my second home. III AgradecimientosPodríamos vivir en blanco y negro, pero afortunadamente la vida es en color. El color es fuente de emoción, de recuerdos, de sensaciones. Nos hace felices. Lo mismo sucede con las personas. Como los colores, hay personas que te calman, te evocan recuerdos, te abrazan, te sonríen. Mi agradecimiento va en primer lugar a estas personas, que como los colores, han dado plenitud a mi vida. Especialmente a mis padres, mi hermana y mis amigos, que siempre han estado ahí, y siguen haciéndolo.Durante el doctorado, han habido momentos de luz y oscuridad. Ha sido un camino largo y arduo, pero ha merecido la pena. He aprendido mucho. Gracias José Luis yÁngel por haberme guiado durante estos años. Vuestras contribuciones han sido esenciales para llenar de color esta tesis. Gracias también a un simple mail. Un mail que cambiaría mi vida. Gracias Stephen por responder afirmativamente a mi petición, y permitirme seis meses asombrosos en Leeds, UK, colaborando en el Colour Research Group de la School of Design. ¡Un sueño hecho realidad! Gracias también a Zeynep, por la estancia de un mes en Mimar Sinan Fine Arts University, Estambul, Turquía. He disfrutado de vistas y monumentos asombrosos. Cuando pienso en Estambul, pienso en colores. ¡Gracias a todos! Porúltimo, muchas gracias a mis compañeros en GIFLE. Hemos reído, hemos llorado (¿verdad Inés?), pero sobre todo he...

show abstract

Recovering spectral reflectance based on natural neighbor interpolation with model‐based metameric spectra of extreme points

Cited by 7 publications

References 22 publications

Auxiliary Reference Samples for Extrapolating Spectral Reflectance from Camera RGB Signals

Auxiliary Reference Samples for Extrapolating Spectral Reflectance from Camera RGB Signals

Double Ghost Convolution Attention Mechanism Network: A Framework for Hyperspectral Reconstruction of a Single RGB Image

Colorimetric and spectral analysis of rock art by means of the characterization of digital sensors

Contact Info

Product

Resources

About