Creating RGB Images from Hyperspectral Images Using a Color Matching Function

Магнуссон, Магнус; Sigurðsson, Jakob; Armansson, Sveinn Eirikur; Ulfarsson, Magnus O.; Deborah, Hilda; Sveinsson, Jóhannes R.

doi:10.1109/igarss39084.2020.9323397

Cited by 35 publications

(21 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…18 To visualization the output hyperspectral datacube, we convert spectral into CIEXYZ color space. 19 We show the results of a simple bicubic interpolation method, denoted as Raw+BIC, our LNC method and the bicubic interpolation method, denoted as LNC+BIC and our LNC method, and the proposed method, donated as our method. Fig.…”

Section: Results Of Simulated Datamentioning

confidence: 99%

An inpainting and super resolution method for image mapping spectrometer

Shao¹,

Su²,

Liu³

et al. 2023

SPIE Future Sensing Technologies 2023

View full text Add to dashboard Cite

Image Mapping Spectrometry (IMS) is a compact snapshot hyperspectral imaging technology. However, the image mapper used in the IMS causes degradation of the reconstructed spectral datacube, such as, low spatial resolution, missing areas and stripe artifacts. In this paper, we propose an end-to-end deep learning method to jointly inpainting and super resolution the restored spectral images of the IMS. The method includes an image inpainting network, which is designed to correct the nonuniform intensity and missing data, and an image super resolution network, which aims to enhance the spatial resolution of images. In addition, a local nonuniformity correction method is proposed to preprocess the IMS images. Simulation and experimental results demonstrate the effectiveness of the proposed method.

show abstract

Section: Results Of Simulated Datamentioning

confidence: 99%

An inpainting and super resolution method for image mapping spectrometer

Shao¹,

Su²,

Liu³

et al. 2023

SPIE Future Sensing Technologies 2023

View full text Add to dashboard Cite

show abstract

“…To compute the RGB and CIELAB images, the spectra are first converted to CIEXYZ 22 using a camera-specific 3×N matrix. The CIEXYZ values can be converted to linear sRGB using a literature matrix corresponding to a standard D65 light source followed by conversion to sRGB using gamma correction to account for standard monitors 23 , 24 …”

Section: Methodsmentioning

confidence: 99%

“…The CIEXYZ values can be converted to linear sRGB using a literature matrix corresponding to a standard D65 light source followed by conversion to sRGB using gamma correction to account for standard monitors. 23,24…”

Section: Tristimulus Color Reconstruction and Perceptual Color Differ...mentioning

confidence: 99%

Synthetic white balancing for intra-operative hyperspectral imaging

Bahl

Horgan

Janatka³

et al. 2023

J. Med. Imag.

View full text Add to dashboard Cite

Hyperspectral imaging shows promise for surgical applications to noninvasively provide spatially resolved, spectral information. For calibration purposes, a white reference image of a highly reflective Lambertian surface should be obtained under the same imaging conditions. Standard white references are not sterilizable and so are unsuitable for surgical environments. We demonstrate the necessity for in situ white references and address this by proposing a novel, sterile, synthetic reference construction algorithm.Approach: The use of references obtained at different distances and lighting conditions to the subject were examined. Spectral and color reconstructions were compared with standard measurements qualitatively and quantitatively, using ΔE and normalized RMSE, respectively. The algorithm forms a composite image from a video of a standard sterile ruler, whose imperfect reflectivity is compensated for. The reference is modeled as the product of independent spatial and spectral components, and a scalar factor accounting for gain, exposure, and light intensity. Evaluation of synthetic references against ideal but non-sterile references is performed using the same metrics alongside pixel-by-pixel errors. Finally, intraoperative integration is assessed though cadaveric experiments.Results: Improper white balancing leads to increases in all quantitative and qualitative errors. Synthetic references achieve median pixel-by-pixel errors lower than 6.5% and produce similar reconstructions and errors to an ideal reference. The algorithm integrated well into surgical workflow, achieving median pixel-by-pixel errors of 4.77% while maintaining good spectral and color reconstruction. Conclusions:We demonstrate the importance of in situ white referencing and present a novel synthetic referencing algorithm. This algorithm is suitable for surgery while maintaining the quality of classical data reconstruction.

show abstract

“…We fuse the captured images to obtain the target HR-HSI without predefining the SRF. We transfer the HR-RGB to CIE XYZ color space in which the spectrum and XYZ’s spectral degradation relationship (i.e., CIE-CMF 21 ) is known. So, we can employ the CMF to reconstruct the spectra from XYZ values, which successfully skips the SRF measurement.…”

Section: Introductionmentioning

confidence: 99%

Universal high spatial resolution hyperspectral imaging using hybrid-resolution image fusion

et al. 2023

View full text Add to dashboard Cite

.By fusing a low spatial resolution hyperspectral image (LR-HSI) and a high spatial resolution RGB image (HR-RGB), hybrid-resolution hyperspectral imaging has been a popular framework for acquiring high spatial resolution hyperspectral images (HR-HSIs). Existing fusion methods always employ a known spectral response function (SRF) of the RGB camera to reconstruct the HR-HSI. The SRF is often limited or unavailable in practice, restricting the performance of existing methods. To address this problem, we propose a color space transfer-based fusion strategy that obtains HR-HSIs based on a hybrid resolution hyperspectral imaging system without measuring the SRF. Specifically, using a clustered-based backpropagation neural network, the HR-RGB is mapped into the CIE XYZ color space, and the HR-XYZ is obtained. In the CIE XYZ color space, its SRF is known; thus, the the SRF measurement is successfully skipped. To efficiently fuse the HR-XYZ and the LR-HSI, we propose a polynomial fusion model that estimates the ratio matrix between the target HR-HSI and the upsampled LR-HSI. Finally, the target HR-HSI is reconstructed by combining the ratio matrix and the unsampled LR-HSI. Experimental results on two public data sets and our real-world data sets show that the proposed method outperforms five state-of-the-art fusion methods.

show abstract

Creating RGB Images from Hyperspectral Images Using a Color Matching Function

Cited by 35 publications

References 10 publications

An inpainting and super resolution method for image mapping spectrometer

An inpainting and super resolution method for image mapping spectrometer

Synthetic white balancing for intra-operative hyperspectral imaging

Universal high spatial resolution hyperspectral imaging using hybrid-resolution image fusion

Contact Info

Product

Resources

About