|
|
Neural Networks for Automatic Table Recognition
Piwowarski, Lukáš ; Španěl, Michal (oponent) ; Hradiš, Michal (vedoucí práce)
This thesis introduces the reader to the current table recognition techniques mainly used to extract information from historical handwritten and printed tables. We also introduce a method based on graph neural network, which is inspired by the presented techniques. The method consists of three phases: graph initialization, node/edge classification and graph to text transformation phase. In the graph initialization phase, we use the node visibility algorithm and OCR to create an initial graph representation of the input table. In the node and edge classification phase, the nodes and edges are classified, and in the graph to text transformation phase, we fit the graph's nodes into a grid which is then used to produce the final text representation of the table. The implemented model achieved horizontal neighbours detection precision of 68 %, vertical neighbours detection precision of 71 % and cell detection precision of 85 % on the ABP dataset.
|
|
|
Surveillance Video Search
Piwowarski, Lukáš ; Ali, Anas (oponent) ; Smrž, Pavel (vedoucí práce)
With the growing number of video recordings produced by security cameras, the demand for systems that are able to search them is growing as well. This work examines such systems and methods that are behind them. The introduction of this thesis describes the scheme of surveillance video search systems together with the methods that these systems use to store information they obtain during the video analysis. Algorithms for object detection (YOLO) and object tracking (DeepSort) are also introduced. These algorithms are then used in a system created for the practical part of this thesis. The end of the thesis describes the created system, which uses the trajectories of detected objects in searched video recordings. To specify the searched events, the proposed query language within this work is used. This language consists of so-called search blocks, the composition of which can be used to define situations such as: "a person got out of a car" or "a car stopped in a parking space".
|
|
|
Neural Networks for Automatic Table Recognition
Piwowarski, Lukáš ; Španěl, Michal (oponent) ; Hradiš, Michal (vedoucí práce)
This thesis introduces the reader to the current table recognition techniques mainly used to extract information from historical handwritten and printed tables. We also introduce a method based on graph neural network, which is inspired by the presented techniques. The method consists of three phases: graph initialization, node/edge classification and graph to text transformation phase. In the graph initialization phase, we use the node visibility algorithm and OCR to create an initial graph representation of the input table. In the node and edge classification phase, the nodes and edges are classified, and in the graph to text transformation phase, we fit the graph's nodes into a grid which is then used to produce the final text representation of the table. The implemented model achieved horizontal neighbours detection precision of 68 %, vertical neighbours detection precision of 71 % and cell detection precision of 85 % on the ABP dataset.
|
|
|
Surveillance Video Search
Piwowarski, Lukáš ; Ali, Anas (oponent) ; Smrž, Pavel (vedoucí práce)
With the growing number of video recordings produced by security cameras, the demand for systems that are able to search them is growing as well. This work examines such systems and methods that are behind them. The introduction of this thesis describes the scheme of surveillance video search systems together with the methods that these systems use to store information they obtain during the video analysis. Algorithms for object detection (YOLO) and object tracking (DeepSort) are also introduced. These algorithms are then used in a system created for the practical part of this thesis. The end of the thesis describes the created system, which uses the trajectories of detected objects in searched video recordings. To specify the searched events, the proposed query language within this work is used. This language consists of so-called search blocks, the composition of which can be used to define situations such as: "a person got out of a car" or "a car stopped in a parking space".
|
host ::
RSS.