Explore the vast range of titles available.

We present a dataset of close range hyperspectral images of materials that span the visible and near infrared spectrums: HyTexiLa (Hyperspectral Texture images acquired in Laboratory). The data is intended to provide high spectral and spatial resolution reflectance images of 112 materials to study spatial and spectral textures. In this paper we discuss the calibration of the data and the method for addressing the distortions during image acquisition. We provide a spectral analysis based on non-negative matrix factorization to quantify the spectral complexity of the samples and extend local binary pattern operators to the hyperspectral texture analysis. The results demonstrate that although the spectral complexity of each of the textures is generally low, increasing the number of bands permits better texture classification, with the opponent band local binary pattern feature giving the best performance.

The virtual inpainting of artworks provides a nondestructive mode of hypothesis visualization, and it is especially attractive when physical restoration raises too many methodological and ethical concerns. At the same time, in Cultural Heritage applications, the level of details in virtual reconstruction and their accuracy are crucial. We propose an inpainting algorithm that is based on generative adversarial network, with two generators: one for edges and another one for colors. The color generator rebalances chromatically the result by enforcing a loss in the discretized gamut space of the dataset. This way, our method follows the modus operandi of an artist: edges first, then color palette, and, at last, color tones. Moreover, we simulate the stochasticity of the lacunae in artworks with morphological variations of a random walk mask that recreate various degradations, including craquelure. We showcase the performance of our model on a dataset of digital images of wall paintings from the Dunhuang UNESCO heritage site. Our proposals of restored images are visually satisfactory and they are quantitatively comparable to state-of-the-art approaches.

The value of three-dimensional virtual objects are proven in a great variety of applications; their flexibility allowing for a substantial amount of utilization purposes. In cultural heritage this has been used for many years already, and the amount of users continue to grow as acquisition methods and implementations are becoming more approachable. Nonetheless, there are still many apparent issues with making use of all the possible benefits of 3D data in the field, varying from lack of knowledge, infrastructure, or coherent workflows. This review aims to underline the current limitations in implementing 3D workflows for various cultural heritage purposes. 45 projects and institutions are reviewed, along with the most prominent guidelines for workflows and ways of implementing the 3D data on the web. We also cover how each project manage and make their data accessible to the public. Prominent and recurring issues with standardization, interoperability, and implementation is highlighted and scrutinized. The review is concluded with a discussion on the current utilization’s of 3D data for cultural heritage purposes, along with suggestions for future developments.

Complexity is one of the major attributes of the visual perception of texture. However, very little is known about how humans visually interpret texture complexity. A psychophysical experiment was conducted to visually quantify the seven texture attributes of a series of textile fabrics: complexity, color variation, randomness, strongness, regularity, repetitiveness, and homogeneity. It was found that the observers could discriminate between the textures with low and high complexity using some high-level visual cues such as randomness, color variation, strongness, etc. The results of principal component analysis (PCA) on the visual scores of the above attributes suggest that complexity and homogeneity could be essentially the underlying attributes of the same visual texture dimension, with complexity at the negative extreme and homogeneity at the positive extreme of this dimension. We chose to call this dimension visual texture complexity. Several texture measures including the first-order image statistics, co-occurrence matrix, local binary pattern, and Gabor features were computed for images of the textiles in sRGB, and four luminance-chrominance color spaces (i.e., HSV, YCbCr, Ohta’s I1I2I3, and CIELAB). The relationships between the visually quantified texture complexity of the textiles and the corresponding texture measures of the images were investigated. Analyzing the relationships showed that simple standard deviation of the image luminance channel had a strong correlation with the corresponding visual ratings of texture complexity in all five color spaces. Standard deviation of the energy of the image after convolving with an appropriate Gabor filter and entropy of the co-occurrence matrix, both computed for the image luminance channel, also showed high correlations with the visual data. In this comparison, sRGB, YCbCr, and HSV always outperformed the I1I2I3 and CIELAB color spaces. The highest correlations between the visual data and the corresponding image texture features in the luminance-chrominance color spaces were always obtained for the luminance channel of the images, and one of the two chrominance channels always performed better than the other. This result indicates that the arrangement of the image texture elements that impacts the observer’s perception of visual texture complexity cannot be represented properly by the chrominance channels. This must be carefully considered when choosing an image channel to quantify the visual texture complexity. Additionally, the good performance of the luminance channel in the five studied color spaces proves that variations in the luminance of the texture, or as one could call the luminance contrast, plays a crucial role in creating visual texture complexity.

Scene recognition is the task of identifying the environment shown in an image. Spectral filter array cameras allow for fast capture of multispectral images. Scene recognition in multispectral images is usually performed after demosaicing the raw image. Along with adding latency, this makes the classification algorithm limited by the artifacts produced by the demosaicing process. This work explores scene recognition performed on raw spectral filter array images using convolutional neural networks. For this purpose, a new raw image dataset is collected for scene recognition with a spectral filter array camera. The classification is performed using a model constructed based on the pretrained Places-CNN. This model utilizes all nine channels of spectral information in the images. A label mapping scheme is also applied to classify the new dataset. Experiments are conducted with different pre-processing steps applied on the raw images and the results are compared. Higher-resolution images are found to perform better even if they contain mosaic patterns.

In the last several years, deep learning has been introduced to recover a hyperspectral image (HSI) from a single RGB image and demonstrated good performance. In particular, attention mechanisms have further strengthened discriminative features, but most of them are learned by convolutions with limited receptive fields or require much computational cost, which hinders the function of attention modules. Furthermore, the performance of these deep learning methods is hampered by tackling multi-level features equally. To this end, in this paper, based on multiple lightweight densely residual modules, we propose a densely residual network with dual attention (DRN-DA), which utilizes advanced attention and adaptive fusion strategy for more efficient feature correlation learning and more powerful feature extraction. Specifically, an SE layer is applied to learn channel-wise dependencies, and dual downsampling spatial attention (DDSA) is developed to capture long-range spatial contextual information. All the intermediate-layer feature maps are adaptively fused. Experimental results on four data sets from the NTIRE 2018 and NTIRE 2020 Spectral Reconstruction Challenges demonstrate the superiority of the proposed DRN-DA over state-of-the-art methods (at least −6.19% and −1.43% on NTIRE 2018 “Clean” track and “Real World” track, −6.85% and −5.30% on NTIRE 2020 “Clean” track and “Real World” track) in terms of mean relative absolute error.

In this study, the results from a round-robin test of hyperspectral imaging systems are presented and analyzed. Fourteen different pushbroom hyperspectral systems from eight different institutions were used to acquire spectral cubes from the visible, near infra-red and short-wave infra-red regions. Each system was used to acquire a common set of targets under their normal operating conditions with the data calibrated and processed using the standard processing pipeline for each system. The test targets consisted of a spectral wavelength standard and of a custom-made pigment panel featuring Renaissance-era pigments frequently found in paintings from that period. The quality and accuracy of the resulting data was assessed with quantitative analyses of the spectral, spatial and colorimetric accuracy of the data. The results provide a valuable insight into the accuracy, reproducibility and precision of hyperspectral imaging equipment when used under routine operating conditions. The distribution and type of error found within the data can provide useful information on the fundamental and practical limits of such equipment when used for applications such as spectral classification, change detection, colorimetry and others.

Archaeological artifacts play important role in understanding the past developments of the humanity. However, the artifacts are often highly fragmented and degraded, with many details and parts missing due to centuries’ long degradation. Archaeologists and conservators attempt to reconstruct the original state of the objects either physically or virtually. This process includes characterizing and matching fragments’ features to identify which ones belong together. However, this process currently requires an extensive and tedious manual labor. Recent development in computational techniques gave rise to computer-assisted ways of virtual reconstruction, where the computer suggests solutions to the puzzle of scattered fragments and supplements or fully replaces manual labor. However, the capabilities of computational techniques remain limited in many aspects. This review summarizes the state-of-the-art computational techniques for puzzle and virtual reconstruction problems in cultural heritage applications, in general – with a particular interest in archaeological textiles. We overview existing computational methods, their applications and limitations. Afterward, based on the current knowledge gaps, we discuss where the field should go next.

The work presented in this paper is part of a wider research project, which aims at documenting and analyzing stained glass windows by means of hyperspectral imaging. This technique shares some similarities with UV-VIS-IR spectroscopy, as they both provide spectral information; however, spectral imaging has the additional advantage of providing spatial information, since a spectrum can be collected in each pixel of the image. Compared to UV-VIS-IR spectroscopy, spectral imaging has rarely been used for the investigation of stained glass windows. One of the objectives of this paper is, thus, to compare the performance of these two instruments to validate the results of hyperspectral imaging. The second objective is to evaluate the potential of analyzing colored-glass pieces in reflectance modality and compare the results with those obtained in transmittance, in order to highlight the differences and similarities between the two approaches. The geometry of the systems and the backing material for the glass, as well as the characteristics of the glass pieces, are discussed. L*a*b* values obtained from the spectra, as well as the calculated color difference ΔE00, are provided, to show the degree of agreement between the instruments and the two measurement modalities.

An important application of imaging spectroscopy or hyperspectral imaging is the classification or discrimination of pigments based on the obtained spectral reflectance information. As opposed to being a point-analysis tool, this non-invasive method captures the entire surface of interest. This means that its potential is not only in the discrimination of pigments but also in their mapping. However, the challenge lies in the fact that in a real painting, there is no clear-cut edge between regions with certain pure pigments or of the exact same mixture. Pigments and other paint materials mix seamlessly and continuously in the physical domain. In this article, we introduce a divergence-based approach to pigment discrimination and mapping. The methodology is then applied to Munch's masterpiece The Scream (1893), whose pigments and materials have been identified for several points in the painting in a previous study. Through the introduced methodology, we have been able to extend the point analyzes of pigments and materials to the entire surface of the painting, recto and verso.