Search Results - "Seuret, Mathias"

A survey of historical document image datasets by Nikolaidou, Konstantina, Seuret, Mathias, Mokayed, Hamam, Liwicki, Marcus

“…This paper presents a systematic literature review of image datasets for document image analysis, focusing on historical documents, such as handwritten…”
Get full text

Evaluating learned feature aggregators for writer retrieval by Mattick, Alexander, Mayr, Martin, Seuret, Mathias, Kordon, Florian, Wu, Fei, Christlein, Vincent

“…Transformers have emerged as the leading methods in natural language processing, computer vision, and multi-modal applications due to their ability to capture…”
Get full text

Deep learning for terahertz image denoising in nondestructive historical document analysis by Dutta, Balaka, Root, Konstantin, Ullmann, Ingrid, Wagner, Fabian, Mayr, Martin, Seuret, Mathias, Thies, Mareike, Stromer, Daniel, Christlein, Vincent, Schür, Jan, Maier, Andreas, Huang, Yixing

“…Historical documents contain essential information about the past, including places, people, or events. Many of these valuable cultural artifacts cannot be…”
Get full text

Classification of incunable glyphs and out-of-distribution detection with joint energy-based models by Kordon, Florian, Weichselbaumer, Nikolaus, Herz, Randall, Mossman, Stephen, Potten, Edward, Seuret, Mathias, Mayr, Martin, Christlein, Vincent

“…Optical character recognition (OCR) has proved a powerful tool for the digital analysis of printed historical documents. However, its ability to localize and…”
Get full text

Convolutional Neural Networks for Page Segmentation of Historical Document Images by Kai Chen, Seuret, Mathias, Hennebert, Jean, Ingold, Rolf

“…This paper presents a page segmentation method for handwritten historical document images based on a Convolutional Neural Network (CNN). We consider page…”
Get full text

A User-Centered Segmentation Method for Complex Historical Manuscripts Based on Document Graphs by Garz, Angelika, Seuret, Mathias, Fischer, Andreas, Ingold, Rolf

“…In historical manuscripts, humans can detect handwritten words, lines, and decorations with lightness even if they do not know the language or the script. Yet…”
Get full text

Influence of X-Ray Radiation on Historical Paper by Zippert, Patrick, Seuret, Mathias, Maier, Andreas, Hausotte, Tino

“…Historical books are often so fragile that they cannot easily be opened in order to read the contents without damaging them. Current research shows, that…”
Get full text

Using Forestnets for Partial Fine-Tuning Prior to Breast Cancer Detection in Ultrasounds by Rodriguez-Salas, Dalia, Ottl, Mathias, Seuret, Mathias, Packhauser, Kai, Maier, Andreas

“…Ultrasound imaging is the most used technique for first investigating suspicions of breast lesions. In recent years, many deep learning techniques have been…”
Get full text

Trainable Spectrally Initializable Matrix Transformations in Convolutional Neural Networks by Alberti, Michele, Botros, Angela, Schutz, Narayan, Ingold, Rolf, Liwicki, Marcus, Seuret, Mathias

“…In this work, we introduce a new architectural component to Neural Network (NN), i.e., trainable and spectrally initializable matrix transformations on feature…”
Get full text

The use of Gabor features for semi-automatically generated polyon-based ground truth of historical document images by Wei, Hao, Seuret, Mathias, Liwicki, Marcus, Ingold, Rolf

Get full text

Deep Generalized Max Pooling by Christlein, Vincent, Spranger, Lukas, Seuret, Mathias, Nicolaou, Anguelos, Kral, Pavel, Maier, Andreas

“…Global pooling layers are an essential part of Convolutional Neural Networks (CNN). They are used to aggregate activations of spatial locations to produce a…”
Get full text

PCA-Initialized Deep Neural Networks Applied to Document Image Analysis by Seuret, Mathias, Alberti, Michele, Liwicki, Marcus, Ingold, Rolf

“…In this paper, we present a novel approach for initializing deep neural networks, i.e., by using Principal Component Analysis (PCA) to initialize neural…”
Get full text

ICDAR 2019 Competition on Image Retrieval for Historical Handwritten Documents by Christlein, Vincent, Nicolaou, Anguelos, Seuret, Mathias, Stutzmann, Dominique, Maier, Andreas

“…This competition investigates the performance of large-scale retrieval of historical document images based on writing style. Based on large image data sets…”
Get full text

Zero-Shot Paragraph-level Handwriting Imitation with Latent Diffusion Models by Mayr, Martin, Dreier, Marcel, Kordon, Florian, Seuret, Mathias, Zöllner, Jochen, Wu, Fei, Maier, Andreas, Christlein, Vincent

“…The imitation of cursive handwriting is mainly limited to generating handwritten words or lines. Multiple synthetic outputs must be stitched together to create…”
Get full text

DIVA-HisDB: A Precisely Annotated Large Dataset of Challenging Medieval Manuscripts by Simistira, Foteini, Seuret, Mathias, Eichenberger, Nicole, Garz, Angelika, Liwicki, Marcus, Ingold, Rolf

“…This paper introduces a publicly available historical manuscript database DIVA-HisDB for the evaluation of several Document Image Analysis (DIA) tasks. The…”
Get full text

ICFHR 2020 Competition on Image Retrieval for Historical Handwritten Fragments by Seuret, Mathias, Nicolaou, Anguelos, Stutzmann, Dominique, Maier, Andreas, Christlein, Vincent

“…This competition succeeds upon a line of competitions for writer and style analysis of historical document images. In particular, we investigate the…”
Get full text

Deep Generalized Max Pooling by Christlein, Vincent, Spranger, Lukas, Seuret, Mathias, Nicolaou, Anguelos, Král, Pavel, Maier, Andreas

“…2019 International Conference on Document Analysis and Recognition (ICDAR), Sydney, NSW, Australia, 2019, pp. 1090-1096 Global pooling layers are an essential…”
Get full text

A Fair Evaluation of Various Deep Learning-Based Document Image Binarization Approaches by Sukesh, Richin, Seuret, Mathias, Nicolaou, Anguelos, Mayr, Martin, Christlein, Vincent

“…Document Analysis Systems. DAS 2022. Lecture Notes in Computer Science, vol 13237. Springer, Cham Binarization of document images is an important…”
Get full text

A Survey of Historical Document Image Datasets by Nikolaidou, Konstantina, Seuret, Mathias, Mokayed, Hamam, Liwicki, Marcus

“…This paper presents a systematic literature review of image datasets for document image analysis, focusing on historical documents, such as handwritten…”
Get full text

Convolutional Neural Networks for Page Segmentation of Historical Document Images by Chen, Kai, Seuret, Mathias

“…This paper presents a Convolutional Neural Network (CNN) based page segmentation method for handwritten historical document images. We consider page…”
Get full text