|
|
Optical Character Recognition Using Convolutional Networks
Csóka, Pavel ; Behúň, Kamil (referee) ; Hradiš, Michal (advisor)
This thesis aims at creation of new datasets for text recognition machine learning tasks and experiments with convolutional neural networks on these datasets. It describes architecture of convolutional nets, difficulties of recognizing text from photographs and contemporary works using these networks. Next, creation of annotation, using Tesseract OCR, for dataset comprised from photos of document pages, taken by mobile phones, named Mobile Page Photos. From this dataset two additional are created by cropping characters out of its photos formatted as Street View House Numbers dataset. Dataset Mobile Nice Page Photos Characters contains readable characters and Mobile Page Photos Characters adds hardly readable and unreadable ones. Three models of convolutional nets are created and used for text recognition experiments on these datasets, which are also used for estimation of annotation error.
|
|
|
Shooting Range Simulator with Image Processing
Csóka, Pavel ; Drahanský, Martin (referee) ; Marvan, Aleš (advisor)
This thesis is aiming on design and implementation of Shooting range simulator with image processing. It is based on detection of a laser spot on the projection plane where the target is displayed (dataprojector or LCD) by using camera which captures image of this plane. It designs and implements the detection software using C++ language and OpenCV computer vision library and describes gun modification, which consists of design and creation of control unit for this gun and fitting it in. Control unit is based on STM32 microcontroller device, its firmware implementation is done using C language. It describes approaches in computer vision applications used in this thesis and main features of used microcontroller. Practical tests are made to analyze system's function. In the final chapter is the summarization of this thesis and suggestions to further development and improvement of this system.
|
|
|
Optical Character Recognition Using Convolutional Networks
Csóka, Pavel ; Behúň, Kamil (referee) ; Hradiš, Michal (advisor)
This thesis aims at creation of new datasets for text recognition machine learning tasks and experiments with convolutional neural networks on these datasets. It describes architecture of convolutional nets, difficulties of recognizing text from photographs and contemporary works using these networks. Next, creation of annotation, using Tesseract OCR, for dataset comprised from photos of document pages, taken by mobile phones, named Mobile Page Photos. From this dataset two additional are created by cropping characters out of its photos formatted as Street View House Numbers dataset. Dataset Mobile Nice Page Photos Characters contains readable characters and Mobile Page Photos Characters adds hardly readable and unreadable ones. Three models of convolutional nets are created and used for text recognition experiments on these datasets, which are also used for estimation of annotation error.
|
|
|
Shooting Range Simulator with Image Processing
Csóka, Pavel ; Drahanský, Martin (referee) ; Marvan, Aleš (advisor)
This thesis is aiming on design and implementation of Shooting range simulator with image processing. It is based on detection of a laser spot on the projection plane where the target is displayed (dataprojector or LCD) by using camera which captures image of this plane. It designs and implements the detection software using C++ language and OpenCV computer vision library and describes gun modification, which consists of design and creation of control unit for this gun and fitting it in. Control unit is based on STM32 microcontroller device, its firmware implementation is done using C language. It describes approaches in computer vision applications used in this thesis and main features of used microcontroller. Practical tests are made to analyze system's function. In the final chapter is the summarization of this thesis and suggestions to further development and improvement of this system.
|
guest ::
