Related papers: PHD: Pixel-Based Language Modeling of Historical D…
Image hallucination and super-resolution have been studied for decades, and many approaches have been proposed to upsample low-resolution images using information from the images themselves, multiple example images, or large image…
Recent advancements in ultra-high-resolution unpaired image-to-image translation have aimed to mitigate the constraints imposed by limited GPU memory through patch-wise inference. Nonetheless, existing methods often compromise between the…
We present a bottom-up differentiable relaxation of the process of drawing points, lines and curves into a pixel raster. Our approach arises from the observation that rasterising a pixel in an image given parameters of a primitive can be…
A novel algorithm for creating a mathematical model of curved shapes is introduced. The core of the algorithm is based on building a graph representation of the contoured image, which occupies less storage space than produced by raster…
Distilling from the feature maps can be fairly effective for dense prediction tasks since both the feature discriminability and localization priors can be well transferred. However, not every pixel contributes equally to the performance,…
Some historical and more recent printed documents have been scanned or stored at very low resolutions, such as 60 dpi. Though such scans are relatively easy for humans to read, they still present significant challenges for optical character…
We present an object detection based approach to localize handwritten regions from documents, which initially aims to enhance the anonymization during the data transmission. The concatenated fusion of original and preprocessed images…
This paper discusses the benefits of including metadata when training language models on historical collections. Using 19th-century newspapers as a case study, we extend the time-masking approach proposed by Rosin et al., 2022 and compare…
While analyzing scanned documents, handwritten text can overlap with printed text. This overlap causes difficulties during the optical character recognition (OCR) and digitization process of documents, and subsequently, hurts downstream NLP…
Binarization plays a key role in the automatic information retrieval from document images. This process is usually performed in the first stages of documents analysis systems, and serves as a basis for subsequent steps. Hence it has to be…
Inpainting-based image compression is a promising alternative to classical transform-based lossy codecs. Typically it stores a carefully selected subset of all pixel locations and their colour values. In the decoding phase the missing…
Persistent homology is a tool that can be employed to summarize the shape of data by quantifying homological features. When the data is an object in $\mathbb{R}^d$, the (augmented) persistent homology transform ((A)PHT) is a family of…
We study the problem of reconstructing an image from information stored at contour locations. We show that high-quality reconstructions with high fidelity to the source image can be obtained from sparse input, e.g., comprising less than…
When digitizing a document into an image, it is common to include a surrounding border region to visually indicate that the entire document is present in the image. However, this border should be removed prior to automated processing. In…
Geometric rectification of images of distorted documents finds wide applications in document digitization and Optical Character Recognition (OCR). Although smoothly curved deformations have been widely investigated by many works, the most…
We present an end-to-end trainable approach for Optical Character Recognition (OCR) on printed documents. Specifically, we propose a model that predicts a) a two-dimensional character grid (\emph{chargrid}) representation of a document…
Language identification describes the task of recognizing the language of written text in documents. This information is crucial because it can be used to support the analysis of a document's vocabulary and context. Supervised learning…
In this paper, we investigate the use of Convolutional Neural Networks for counting the number of records in historical handwritten documents. With this work we demonstrate that training the networks only with synthetic images allows us to…
Historical documents frequently suffer from damage and inconsistencies, including missing or illegible text resulting from issues such as holes, ink problems, and storage damage. These missing portions or gaps are referred to as lacunae. In…
In Document Understanding, the challenge of reconstructing damaged, occluded, or incomplete text remains a critical yet unexplored problem. Subsequent document understanding tasks can benefit from a document reconstruction process. In…