Improving Generalizability of Spectral Reflectance Reconstruction Using L1-Norm Penalization

Yao, Pengpeng; Wu, H. C.; Xin, John Haozhong

doi:10.3390/s23020689

Cited by 2 publications

(2 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Through various image processing and machine learning techniques, MSI can measure colour in minute regions, such as yarns. 1,[8][9][10][11] Whiteness measurement has remained a critical endeavour across dentistry, 12,13 textiles, 14,15 paper, [16][17][18] and detergents. 19 For instance, inconsistent whiteness in large fabric batches risks rejection and financial losses.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fluorescent whiteness measurement of textiles by multispectral imaging system

Yao,

Wu,

et al. 2023

Coloration Technology

Self Cite

View full text Add to dashboard Cite

Accurate whiteness measurement is critical across various industries including textiles, paper, and detergents. With the advent of fluorescent whitening agents (FWAs), the assessment of whiteness has evolved from simply measuring reflectance to determining the spectral radiance factor (SRF) of materials. While multispectral imaging (MSI) can effectively measure object reflectance and colour, its accuracy is compromised by FWAs that significantly augment spectral reflectance. Thus, reliable whiteness measurement requires the determination of both reflectance and SRF. This article presents the design of a specialised light source equipped with an ultraviolet (UV) filter to provide adjustable illumination within an integrating sphere system. By tuning the position of the UV filter, multispectral images are captured of a fabric under varying UV exposures. These images are subsequently processed and combined to reconstruct full‐range visible spectrum information. This approach is shown to achieve high accuracy and spatial uniformity in quantifying the whiteness of textiles using MSI.

show abstract

Section: Introductionmentioning

confidence: 99%

“…MSI holds enormous potential for colour metrology, as it provides both spectral and spatial information. Through various image processing and machine learning techniques, MSI can measure colour in minute regions, such as yarns 1,8–11 …”

Section: Introductionmentioning

confidence: 99%

Fluorescent whiteness measurement of textiles by multispectral imaging system

Yao,

Wu,

et al. 2023

Coloration Technology

Self Cite

View full text Add to dashboard Cite

show abstract

Automatic Reconstruction of Reservoir Geological Bodies Based on Improved Conditioning Spectral Normalization Generative Adversarial Network

Wang,

Liu,

Weng

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

For reservoir structural models with obvious nonstationary and heterogeneous characteristics, traditional geostatistical simulation methods tend to produce suboptimal results. Additionally, these methods are computationally resource-intensive in consecutive simulation processes. Thanks to the feature extraction capability of deep learning, the generative adversarial network-based method can overcome the limitations of geostatistical simulation and effectively portray the structural attributes of the reservoir models. However, the fixed receptive fields may restrict the extraction of local geospatial multiscale features, while the gradient anomalies and mode collapse during the training process can cause poor reconstruction. Moreover, the sparsely distributed conditioning data lead to possible noise and artifacts in the simulation results due to its weak constraint ability. Therefore, this paper proposes an improved conditioning spectral normalization generation adversarial network framework (CSNGAN-ASPP) to achieve efficient and automatic reconstruction of reservoir geological bodies under sparse hard data constraints. Specifically, CSNGAN-ASPP features an encoder-decoder type generator with an atrous spatial pyramid pooling (ASPP) structure, which effectively identifies and extracts multi-scale geological features. A spectral normalization strategy is integrated into the discriminator to enhance the network stability. Attention mechanisms are incorporated to focus on the critical features. In addition, a joint loss function is defined to optimize the network parameters and thereby ensure the realism and accuracy of the simulation results. Three types of reservoir model were introduced to validate the reconstruction performance of CSNGAN-ASPP. The results show that they not only accurately conform to conditioning data constraints but also closely match the reference model in terms of spatial variance, channel connectivity, and facies attribute distribution. For the trained CSNGAN-ASPP, multiple corresponding simulation results can be obtained quickly through inputting conditioning data, thus achieving efficient and automatic reservoir geological model reconstruction.

show abstract

Improving Generalizability of Spectral Reflectance Reconstruction Using L1-Norm Penalization

Cited by 2 publications

References 27 publications

Fluorescent whiteness measurement of textiles by multispectral imaging system

Fluorescent whiteness measurement of textiles by multispectral imaging system

Automatic Reconstruction of Reservoir Geological Bodies Based on Improved Conditioning Spectral Normalization Generative Adversarial Network

Contact Info

Product

Resources

About