|
|
Intracranial hemorrhage localization in axial slices of head CT images
Kopečný, Kryštof ; Chmelík, Jiří (referee) ; Nemček, Jakub (advisor)
This thesis is focused on detection of intracranial hemorrhage in CT images using both one-stage and two-stage object detectors based on convolutional neural networks. The fundamentals of intracranial hemorrhage pathology and CT imaging as well as essential insight into computer vision and object detection are listed in this work. The knowledge of these fields of studies is a starting point for the implemenation of hemorrhage detector. The use of open-source CT image datasets is also discussed. The final part of this thesis is a model evaluation on a test dataset and results examination.
|
|
|
Detection of cells in confocal microscopy images
Hubálek, Michal ; Štursa, Dominik (referee) ; Škrabánek, Pavel (advisor)
The goal of the thesis was to create an application that automatically detects healthy cardiomyocytes from images captured by a confocal microscope. The thesis was created based on the specific needs of researchers from the Slovak Academy of Sciences.The application will facilitate and increase the efficiency of their research,because until now they have to evaluate the images and search for suitable cells manually. The RetinaNet convolutional neural network is used for detection and has been implemented in a user-friendly desktop application. The application also automatically records and stores coordinates of detected cells which can be used for capturing cells in higher image quality. Another advantage of the developed application is its versatility, which allows to train detection on other data, making it applicable to other projects. The result of this work is a functional, standalone and intuitive application that is ready to be used by researchers.
|
|
|
Vehicle Counting in Still Image
Vágner, Filip ; Juránek, Roman (referee) ; Špaňhel, Jakub (advisor)
The goal of this work is to compare models of convolutional neural networks designed to count vehicles in a static image using density estimation with a focus on different sizes of objects in the scene. A total of four models were evaluated - Scale Pyramid Network, Scale-adaptive CNN, Multi-scale fusion network and CASA-Crowd. The evaluation was done on three data sets - TRANCOS, CARPK, PUCPR+. Scale Pyramid Network achieved the best results. The model reached 5.44 in the Mean Absolute Error metric and 9.95 in the GAME(3) metric on TRANCOS dataset.
|
|
|
Enhancement of image quality for security forces
Varga, Adam ; Galáž, Zoltán (referee) ; Burget, Radim (advisor)
This bachelor thesis deals with image quality enhancement for security forces. Image quality enhancement in this case means increasing the resolution of image data by using super-resolution techniques using models of deep convolutional neural networks. The thesis in its theoretical part describes the principles of the operation of this technique and in its practical part is presented the work with selected state-of-the-art models in the area of super-resolution.
|
|
|
Evolutionary Design of Image Classifier
Koči, Martin ; Bidlo, Michal (referee) ; Drahošová, Michaela (advisor)
This thesis deals with evolutionary design of image classifier with help of genetic programming, specifically with cartesian genetic programming. Thesis discribes teoretical basics of machine learing, evolutionary algorithms and genetic programming. Part of this thesis is described design of the program and its implementation. Futhermore, experiments are performed on two solved tasks for the classification of handwritten digits and the classification of cube drawings, which can be used to determine the rate of dementia in Parkinson's disease. The best designed solution for digits is with AUC of 0.95 and for cubes 0.86. Designed solutions are compared by other methods, namely convolutional neural networks (CNN) and the support vector machines (SVM). The resulting AUC for the classification of digits for both CNN and SVM is 0.99, for cubes CNN has a final AUC 0.81 and SVM 0.69. The cubes are then compared with existing solution, which resulted in AUC 0.70, so that the results of the experiments show an improvement in the method used in this thesis.
|
|
|
Algorithmic Solution for Determining the Age of a Person Based on 2D Photography Using Artificial Intelligence
Bednář, Pavel ; Goldmann, Tomáš (referee) ; Drahanský, Martin (advisor)
Automated person's age estimation from a facial image is one of the challenges in the field of artificial intelligence and machine learning. Age estimation is often a non-trivial complexity for a person, unlike other biological characteristics such as determining gender or race. Information about an individual's age is very important for certain situations. For example, when committing an offense or crime, the amount of the sentence is co-determined by age. This information can also be used in the analysis of customers of a commercial entity and the subsequent adjustment of the offer. The aim of this work is to be able to extract his age from a photograph of a human face. The algorithm consists of two modules. If the first module says that the person is under 14 years old, the image will go to the second module. Furthermore, another version of the algorithm is proposed with an added module focused on selected facial features. In all modules transformations are performed on the image and their results are averaged. Finally, the algorithm is evaluated on standard datasets for age estimation and compared with state-of-the-art methods in this area.
|
|
|
Position Control With Camera
Ficek, Dominik ; Honec, Peter (referee) ; Richter, Miloslav (advisor)
Thesis focuses on camera’s pose estimation in set world coordinate system. This coordinate system is defined by position of predefined marks. Cursor control is selected as a pose estimation feedback. Aim of this thesis is designing real time cursor control with camera methods. In theoretical part of this thesis is dedicated to explanation of basic theory of image processing, artificial intelligence in computer vision and 3D reconstruction. Following theoretical chapter is a chapter dedicated to the design of two position control with camera methods. First method defines fixed coordinate system and cursor is controlled by camera’s movement. Second method utilizes fixed camera and movable coordinate system. Further chapters are dedicated to realization of designed methods, their evaluation and comparison.
|
|
|
Application of Neural Accelerators on Rapsberry PI
Barna, Kristian ; Sekanina, Lukáš (referee) ; Vašíček, Zdeněk (advisor)
The presented bachelor thesis deals with the statistical evaluation of performance for hardward accelerator of deep neural networks. Describes convolutional neural networks along with mathematical calculations. Explains their acceleration and conversion to a format suitable for the Intel Movidius NCS accelerator. 8 hardware platforms and 22 neural network difficulties were compared experimentally. Up to 105-fold improvement was demonstrated in isolated inference of the MobileNetV2 network for the Raspber Pi platform using an accelerator. Performance between the tested platforms was also evaluated from an energy point of view. The application of facial identity demonstrated the conditions during real use. Possible limits of CNN acceleration on power-limited devices (Raspberry Pi) have been uncovered, especially due to improper selection of input image resolution. All measurements were evaluated by statistical procedures.
|
|
|
Vehicle Counting in Still Image
Jelínek, Zdeněk ; Juránek, Roman (referee) ; Špaňhel, Jakub (advisor)
The main goal of this thesis was to compare different approaches to vehicle counting by density estimation. Four convolutional neural networks were tested - Counting CNN, Hydra CNN, Perspective-Aware CNN and Multi-column CNN. The evaluation of these models was done on three different datasets. The Perspective-aware CNN has achieved the most accurate results across all datasets. This model has reached 2.86 Mean Absolute Error on the PUCPR+ dataset, proving that it is the most suitable for the vehicle counting problem.
|
|
|
Object Detection and Recognition in Image
Muzikářová, Michaela ; Hradiš, Michal (referee) ; Zemčík, Pavel (advisor)
This bachelor's thesis deals with design and implementation of client-server application for object recognition with the use of existing mobile application. Theoretical part describes the differences between human and computer vision, followed by information about object detection and recognition with selected methods. The next section provides a detailed overview of artificial neural networks, which were used for this work, with their qualities for object recognition. Following part examines selected mobile applications for object recognition, followed by existing frameworks and libraries with focus on artificial neural networks. Among these, Caffe Framework was selected for the work. The next section illustrates the progress of design and implementation and describes the system, along with experiments and dataset used to prove its functionality.
|
guest ::
