Image Processing
Since we often work with scanned documents and other image materials such as historical texts or maps, we employ methods of image processing. We successfuly work with modern deep convolutional and fully-convolutional neural networks as well as standard computer vision algorithms (binarization, connected component analysis, edge detection and many others). We have also experience with OCR models based on convolutional and recurrent neural networks.
Publications
Historical Map Toponym Extraction for Efficient Information Retrieval
Ladislav Lenc and Jiří Martínek and Josef Baloun and Martin Prantl and Pavel Král15th IAPR International Workshop on Document Analysis Systems (2022)
Neural Networks | Image Processing
Robust Grid Detection in Historical Map Images
Josef Baloun and Ladislav Lenc and Pavel Král2022 IEEE International Conference on Image Processing (ICIP) (2022)
Image Processing
Text Line Segmentation in Historical Newspapers
Ladislav Lenc and Jiří Martínek and Pavel Král21th International Conference on Artificial Intelligence and Soft Computing (ICAISC 2022) (2022)
Neural Networks | Image Processing
How to Segment Handwritten Historical Chronicles Using Fully Convolutional Networks?
Josef Baloun and Pavel Král and Ladislav LencAgents and Artificial Intelligence, Revised Selected Papers, 13th International Conference, ICAART 2021 (2022)
Neural Networks | Image Processing
ICDAR 2021 Competition on Historical Map Segmentation
Josef Baloun and Ladislav Lenc and Pavel KrálICDAR 2021 (2021)
Neural Networks | Image Processing
ChronSeg: Novel Dataset for Segmentation of Handwritten Historical Chronicles
Josef Baloun and Pavel Král and Ladislav Lenc13th International Conference on Agents and Artificial Intelligence (2021)
Neural Networks | Image Processing
Dialogue Act Recognition Using Visual Information
Jiří Martínek and Pavel Král and Ladislav LencInternational Conference on Document Analysis and Recognition - ICDAR 2021 (2021)
Dialogue Act Recognition | Neural Networks | Image Processing
Border Detection for Seamless Connection of Historical Cadastral Maps
Ladislav Lenc and Martin Prantl and Jiří Martínek and Pavel Král16th International Conference on Document Analysis and Recognition (ICDAR 2021) - Workshop on Graphics Recognition (GREC) (2021)
Neural Networks | Image Processing
Improving Face Recognition Methods based on POEM Features
Ladislav Lenc and Pavel Král12th International Conference on Agents and Artificial Intelligence (2020)
Neural Networks | Image Processing
Re-Ranking for Writer Identification and Writer Retrieval
Simon Jordan and Mathias Seuret and Pavel Král and Ladislav Lenc and Jiří Martínek and Barbara Wiermann and Tobias Schwinger and Andreas Maier and Vincent Christlein14th IAPR International Workshop on Document Analysis Systems (2020)
Neural Networks | Image Processing
Building an efficient OCR system for historical documents with little training data
Jiří Martínek and Ladislav Lenc and Pavel KrálNeural Computing and Applications (2020)
Neural Networks | Image Processing
HDPA: Historical document processing and analysis framework
Ladislav Lenc and Jiří Martínek and Pavel Král and Vincent ChristleinEvolving Systems (2020)
Neural Networks | Image Processing
