|
|
Text Layout Analysis in Historical Documents
Palacková, Bianca ; Hradiš, Michal (referee) ; Kodym, Oldřich (advisor)
The goal of this thesis is to design and implement algorithm for text layout analysis in historical documents. Neural network was used to solve this problem, specifically architecture Faster-RCNN. Dataset of 6 135 images with historical newspaper was used for training and testing. For purpose of the thesis four models of neural networks were trained: model for detection of words, headings, text regions and model for words detection based on position in line. Outputs from these models were processed in order to determine text layout in input image. A modified F-score metric was used for the evaluation. Based on this metric, the algorithm reached an accuracy almost 80 %.
|
|
|
Comparison of Retinal Images with Pathological Findings
Palacková, Bianca ; Semerád, Lukáš (referee) ; Drahanský, Martin (advisor)
The goal of this thesis is to design and implement software for comparison of retinal images with pathological findings. The most common diseases affecting the retina are diabetic retinopathy and age related macular degeneration. Detection of main components such as optic disc and fovea, need to be detected for proper comparison and detection of diseases. 570 images was used for evaluation of detection of these main components. In both cases, algorithm achieved success over 90\%. 120 images were analysed by 3 ophthalmologists for evaluation of ability to locate pathological findings. Automatic comparison of retinal images can be useful for determination of disease progression.
|
|
|
Text Layout Analysis in Historical Documents
Palacková, Bianca ; Hradiš, Michal (referee) ; Kodym, Oldřich (advisor)
The goal of this thesis is to design and implement algorithm for text layout analysis in historical documents. Neural network was used to solve this problem, specifically architecture Faster-RCNN. Dataset of 6 135 images with historical newspaper was used for training and testing. For purpose of the thesis four models of neural networks were trained: model for detection of words, headings, text regions and model for words detection based on position in line. Outputs from these models were processed in order to determine text layout in input image. A modified F-score metric was used for the evaluation. Based on this metric, the algorithm reached an accuracy almost 80 %.
|
|
|
Comparison of Retinal Images with Pathological Findings
Palacková, Bianca ; Semerád, Lukáš (referee) ; Drahanský, Martin (advisor)
The goal of this thesis is to design and implement software for comparison of retinal images with pathological findings. The most common diseases affecting the retina are diabetic retinopathy and age related macular degeneration. Detection of main components such as optic disc and fovea, need to be detected for proper comparison and detection of diseases. 570 images was used for evaluation of detection of these main components. In both cases, algorithm achieved success over 90\%. 120 images were analysed by 3 ophthalmologists for evaluation of ability to locate pathological findings. Automatic comparison of retinal images can be useful for determination of disease progression.
|
guest ::
