Martin Holeček | Charles University, Prague (original) (raw)
Uploads
Papers by Martin Holeček
Title: Efficient methods for visualization of volumetric data Author: Martin Holeček Department: ... more Title: Efficient methods for visualization of volumetric data Author: Martin Holeček Department: Mathematical Institute of Charles University Supervisor: RNDr. Ing. Jaroslav Hron, Ph.D., Mathematical Institute Abstract: The aim is to make an overview of and present implementation usefull for rendering of simulated datasets and CT and MR datasets. We will examine the methods of direct volume rendering of structured and unstructured grids and head to meaningful simultaneous realtime rendering of both types. In the first part, we briefly present the development, problems and targets of the field. Next, based on knowledge about existing algorithms, we choose one solution and present our own implementation and modification of algorithms. In detail, the object of our study will be numerical solutions of volume rendering integral by preintegration and paralelization of the process of projecting tetrahedra and perspective correction. For practical reasons we focus on the efficiency, that me...
ArXiv, 2019
Table detection and extraction has been studied in the context of documents like scientific paper... more Table detection and extraction has been studied in the context of documents like scientific papers, where tables are clearly outlined and stand out from the visual document structure. We study this topic in a rather more challenging domain of layout-heavy business documents, particularly invoices. Invoices present the novel challenges of tables being often without outlines - either in the form of borders or surrounding text flow - with ragged columns and widely varying data content. We will also show, that we can extract different structural information from different table-like structures. We present a comprehensive representation of a page using graph over word boxes, positional embeddings, trainable textual features and rephrase the table detection as a text box labeling problem. We will work on a new dataset of invoices using this representation and propose multiple baselines to solve this labeling problem. We then propose a novel neural network model that achieves strong, pract...
International Journal on Document Analysis and Recognition (IJDAR)
its already known target information improves the information extraction. Furthermore, the experi... more its already known target information improves the information extraction. Furthermore, the experiments confirm that all proposed architecture parts (siamese networks, employing class information, query-answer attention module and skip connections to a similar page) are all required to beat the previous results. The best model improves the previous state-of-theart results by an 8.25 % gain in F 1 score. Qualitative analysis is provided to verify that the new model performs better for all target classes. Additionally, multiple structural observations about the causes of the underperformance of some architectures are revealed. All the source codes, parameters and implementation details are published together with the dataset in the hope to push the research boundaries since all the techniques used in this work are not problem-specific and can be generalized for other tasks and contexts.
Abstract--- Table detection and extraction has been studied in the context of documents like repo... more Abstract--- Table detection and extraction has been studied in the context of documents like reports, where tables are clearly outlined and stand out from the document structure visually. We study this topic in a rather more challenging domain of layout-heavy business documents, particularly invoices. Invoices present the novel challenges of tables being often without outlines - either in the form of borders or surrounding text flow - with ragged columns and widely varying data content. We will also show, that we can extract specific information from structurally different tables or table-like structures with one model. We present a comprehensive representation of a page using graph over word boxes, positional embeddings, trainable textual features and rephrase the table detection as a text box labeling problem. We will work on our newly presented dataset of pro forma invoices, invoices and debit note documents using this representation and propose multiple baselines to solve this l...
Title: Efficient methods for visualization of volumetric data Author: Martin Holeček Department: ... more Title: Efficient methods for visualization of volumetric data Author: Martin Holeček Department: Mathematical Institute of Charles University Supervisor: RNDr. Ing. Jaroslav Hron, Ph.D., Mathematical Institute Abstract: The aim is to make an overview of and present implementation usefull for rendering of simulated datasets and CT and MR datasets. We will examine the methods of direct volume rendering of structured and unstructured grids and head to meaningful simultaneous realtime rendering of both types. In the first part, we briefly present the development, problems and targets of the field. Next, based on knowledge about existing algorithms, we choose one solution and present our own implementation and modification of algorithms. In detail, the object of our study will be numerical solutions of volume rendering integral by preintegration and paralelization of the process of projecting tetrahedra and perspective correction. For practical reasons we focus on the efficiency, that me...
ArXiv, 2019
Table detection and extraction has been studied in the context of documents like scientific paper... more Table detection and extraction has been studied in the context of documents like scientific papers, where tables are clearly outlined and stand out from the visual document structure. We study this topic in a rather more challenging domain of layout-heavy business documents, particularly invoices. Invoices present the novel challenges of tables being often without outlines - either in the form of borders or surrounding text flow - with ragged columns and widely varying data content. We will also show, that we can extract different structural information from different table-like structures. We present a comprehensive representation of a page using graph over word boxes, positional embeddings, trainable textual features and rephrase the table detection as a text box labeling problem. We will work on a new dataset of invoices using this representation and propose multiple baselines to solve this labeling problem. We then propose a novel neural network model that achieves strong, pract...
International Journal on Document Analysis and Recognition (IJDAR)
its already known target information improves the information extraction. Furthermore, the experi... more its already known target information improves the information extraction. Furthermore, the experiments confirm that all proposed architecture parts (siamese networks, employing class information, query-answer attention module and skip connections to a similar page) are all required to beat the previous results. The best model improves the previous state-of-theart results by an 8.25 % gain in F 1 score. Qualitative analysis is provided to verify that the new model performs better for all target classes. Additionally, multiple structural observations about the causes of the underperformance of some architectures are revealed. All the source codes, parameters and implementation details are published together with the dataset in the hope to push the research boundaries since all the techniques used in this work are not problem-specific and can be generalized for other tasks and contexts.
Abstract--- Table detection and extraction has been studied in the context of documents like repo... more Abstract--- Table detection and extraction has been studied in the context of documents like reports, where tables are clearly outlined and stand out from the document structure visually. We study this topic in a rather more challenging domain of layout-heavy business documents, particularly invoices. Invoices present the novel challenges of tables being often without outlines - either in the form of borders or surrounding text flow - with ragged columns and widely varying data content. We will also show, that we can extract specific information from structurally different tables or table-like structures with one model. We present a comprehensive representation of a page using graph over word boxes, positional embeddings, trainable textual features and rephrase the table detection as a text box labeling problem. We will work on our newly presented dataset of pro forma invoices, invoices and debit note documents using this representation and propose multiple baselines to solve this l...