A common observation in data-driven applications is that high-dimensional data have a low intrinsic dimension, at least locally. In this work, we consider the problem of point estimation for manifold-valued data. Namely, given a finite set of noisy samples of $\mathcal{M}$, a $d$ dimensional submanifold of $\mathbb{R}^D$, and a point $r$ near the manifold we aim to project $r$ onto the manifold. Assuming that the data was sampled uniformly from a tubular neighborhood of a $k$-times smooth boundaryless and compact manifold, we present an algorithm that takes $r$ from this neighborhood and outputs $\hat p_n\in \mathbb{R}^D$, and $\widehat{T_{\hat p_n}\mathcal{M}}$ an element in the Grassmannian $Gr(d, D)$. We prove that as the number of samples $n\to\infty$, the point $\hat p_n$ converges to $\mathbf{p}\in \mathcal{M}$, the projection of $r$ onto $\mathcal{M}$, and $\widehat{T_{\hat p_n}\mathcal{M}}$ converges to $T_{\mathbf{p}}\mathcal{M}$ (the tangent space at that point) with high probability. Furthermore, we show that $\hat p_n$ approaches the manifold with an asymptotic rate of $n^{-\frac{k}{2k + d}}$, and that $\hat p_n, \widehat{T_{\hat p_n}\mathcal{M}}$ approach $\mathbf{p}$ and $T_{\mathbf{p}}\mathcal{M}$ correspondingly with asymptotic rates of $n^{-\frac{k-1}{2k + d}}$. %While we These rates coincide with the optimal rates for the estimation of function derivatives.

X-radiography (X-ray imaging) is a widely used imaging technique in art investigation. It can provide information about the condition of a painting as well as insights into an artist's techniques and working methods, often revealing hidden information invisible to the naked eye. X-radiograpy of double-sided paintings results in a mixed X-ray image and this paper deals with the problem of separating this mixed image. Using the visible color images (RGB images) from each side of the painting, we propose a new Neural Network architecture, based upon 'connected' auto-encoders, designed to separate the mixed X-ray image into two simulated X-ray images corresponding to each side. This connected auto-encoders architecture is such that the encoders are based on convolutional learned iterative shrinkage thresholding algorithms (CLISTA) designed using algorithm unrolling techniques, whereas the decoders consist of simple linear convolutional layers; the encoders extract sparse codes from the visible image of the front and rear paintings and mixed X-ray image, whereas the decoders reproduce both the original RGB images and the mixed X-ray image. The learning algorithm operates in a totally self-supervised fashion without requiring a sample set that contains both the mixed X-ray images and the separated ones. The methodology was tested on images from the double-sided wing panels of the Ghent Altarpiece, painted in 1432 by the brothers Hubert and Jan van Eyck. These tests show that the proposed approach outperforms other state-of-the-art X-ray image separation methods for art investigation applications.

In the desire to quantify the success of neural networks in deep learning and other applications, there is a great interest in understanding which functions are efficiently approximated by the outputs of neural networks. By now, there exists a variety of results which show that a wide range of functions can be approximated with sometimes surprising accuracy by these outputs. For example, it is known that the set of functions that can be approximated with exponential accuracy (in terms of the number of parameters used) includes, on one hand, very smooth functions such as polynomials and analytic functions and, on the other hand, very rough functions such as the Weierstrass function, which is nowhere differentiable. In this paper, we add to the latter class of rough functions by showing that it also includes refinable functions. Namely, we show that refinable functions are approximated by the outputs of deep ReLU neural networks with a fixed width and increasing depth with accuracy exponential in terms of their number of parameters. Our results apply to functions used in the standard construction of wavelets as well as to functions constructed via subdivision algorithms in Computer Aided Geometric Design.

In this paper, we focus on X-ray images (X-radiographs) of paintings with concealed sub-surface designs (e.g., deriving from reuse of the painting support or revision of a composition by the artist), which therefore include contributions from both the surface painting and the concealed features. In particular, we propose a self-supervised deep learning-based image separation approach that can be applied to the X-ray images from such paintings to separate them into two hypothetical X-ray images. One of these reconstructed images is related to the X-ray image of the concealed painting, while the second one contains only information related to the X-ray image of the visible painting. The proposed separation network consists of two components: the analysis and the synthesis sub-networks. The analysis sub-network is based on learned coupled iterative shrinkage thresholding algorithms (LCISTA) designed using algorithm unrolling techniques, and the synthesis sub-network consists of several linear mappings. The learning algorithm operates in a totally self-supervised fashion without requiring a sample set that contains both the mixed X-ray images and the separated ones. The proposed method is demonstrated on a real painting with concealed content, Do na Isabel de Porcel by Francisco de Goya, to show its effectiveness.

X-radiography is a widely used imaging technique in art investigation, whether to investigate the condition of a painting or provide insights into artists' techniques and working methods. In this paper, we propose a new architecture based on the use of `connected' auto-encoders in order to separate mixed X-ray images acquired from double-sided paintings, where in addition to the mixed X-ray image one can also exploit the two RGB images associated with the front and back of the painting. This proposed architecture uses convolutional auto-encoders that extract features from the RGB images that can be employed to (1) reproduce both of the original RGB images, (2) reconstruct the associated separated X-ray images, and (3) regenerate the mixed X-ray image. It operates in a totally self-supervised fashion without the need for examples containing both the mixed X-ray images and the separated ones. Based on images from the double-sided wing panels from the famous Ghent Altarpiece, painted in 1432 by the brothers Hubert and Jan Van Eyck, the proposed algorithm has been experimentally verified to outperform state-of-the-art X-ray separation methods in art investigation applications.

This article discusses the quality assessment of binary images. The customary, ground truth based methodology, used in the literature is shown to be problematic due to its subjective nature. Several previously suggested alternatives are surveyed and are also found to be inadequate in certain scenarios. A new approach, quantifying the adherence of a binarization to its document image is proposed and tested using six different measures of accuracy. The measures are evaluated experimentally based on datasets from DIBCO and H-DIBCO competitions, with respect to different kinds of binarization degradations.

Document binary images, created by different algorithms, are commonly evaluated based on a pre-existing ground truth. Previous research found several pitfalls in this methodology and suggested various approaches addressing the issue. This article proposes an alternative binarization quality evaluation solution for binarized glyphs, circumventing the ground truth. Our method relies on intrinsic properties of binarized glyphs. The features used for quality assessment are stroke width consistency, presence of small connected components (stains), edge noise, and the average edge curvature. Linear and tree-based combinations of these features are also considered. The new methodology is tested and shown to be nearly as sound as human experts' judgments.