|
|
Music Improvisation
Angelov, Michael ; Hradiš, Michal (referee) ; Fapšo, Michal (advisor)
The thesis deals with problems concerning algorithmic music compositon, especially the domain of musical improvisation. There is an opening presentation of some of existing tools and approaches that are commonly used in domain of computer music. Consenquently there is a proposal of a new system, using main principles of markov chains and prediction suffix trees (PST) with description of its implementation. The main task of developped application is to analyze an external MIDI recording that is proposed to the system by user and create a new and inovative musical material in MIDI format that would sound close to the original recording giving an impression of a computer improvised music to the listener.
|
|
|
Object Detection and Tracking Using Interest Points
Bílý, Vojtěch ; Hradiš, Michal (referee) ; Juránek, Roman (advisor)
This paper deals with object detection and tracking using iterest points. Existing approaches are described here. Inovated method based on Generalized Hough transform and iterative Hough-space searching is proposed in this paper. Generality of proposed detector is shown in various types of objects. Object tracking is designed as frame by frame detection.
|
|
|
Boosting and Evolution
Mrnuštík, Michal ; Juránek, Roman (referee) ; Hradiš, Michal (advisor)
This thesis introduces combination of the AdaBoost and the evolutionary algorithm. The evolutionary algorithm is used to find linear combination of Haar features. This linear combination creates the feature to train weak classifier for AdaBoost. There are described basics of classification, Haar features and the AdaBoost. Next there are basic information about evolutionary algorithms. Theoretical description of combination of the AdaBoost and the evolutionary algorithm is included too. Some implementation details are added too. Implementation is tested on the images as part of the system for face recognition. Results are compared with Haar features.
|
|
|
Search for Duplicities of Photos
Sklenář, Zdeněk ; Hradiš, Michal (referee) ; Zemčík, Pavel (advisor)
This bachelor thesis is about the analysis, design, implementation and testing of an application which is used to find duplicates in photographs according to its Exif metadata. The application also enables preview of photos, including Exif metadata. Additionally it is possible to filter photos, group duplicities with the original photo, and select the best photos to keep it in accordance with a user-defined parameter, then manually adjust this option, and deleting others. It is also a possible to export selected photos to a ZIP archive.
|
|
|
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.
|
|
|
Deep Learning for Image Recognition
Munzar, Milan ; Kolář, Martin (referee) ; Hradiš, Michal (advisor)
Neural networks are one of the state-of-the-art models for machine learning today. One may found them in autonomous robot systems, object and speech recognition, prediction and many others AI tasks. The thesis describes this model and its extension which is used in an object recognition. Then explains an application of a convolutional neural networks(CNNs) in an image recognition on Caltech101 and Cifar10 datasets. Using this exemplar application, the thesis discusses and measures efficiency of techniques used in CNNs. Results show that the convolutional networks without advanced extensions are able to reach a 80\% recognition accuracy on Cifar-10 and a 37\% accuracy on Caltech101.
|
|
|
Vehicle License Plate Detection and Recognition Software
Masaryk, Adam ; Hradiš, Michal (referee) ; Špaňhel, Jakub (advisor)
The aim of this bachelor thesis is to design and develop software that can detect and recognize license plates from images. The software is divided into 3 parts - license plates detection, detector output processing and license plates characters recognition. We decided to implement detection and recognition using modern methods using convolutional neural networks.
|
|
|
Game Environment from Music
Vaněk, Jiří ; Fapšo, Michal (referee) ; Hradiš, Michal (advisor)
The topic of this work is game environment generation from music. The main subject of this work is the music analysis. I am dealing with the problem of finding relevant information in music, which would be useful for game generating. The design of the system for music analysis, presented in this work, is based on the theory of signal processing and statistical classification. The proposed analysis of music is focused mainly on a beat detection, musical genre recognition and song segmentation. The second part of the work deals with the design of a game, which generates its environment from the data obtained in the music analysis. I have implemented the complete system for the music analysis and a prototype of the game, in which it is possible to evaluate the results from the analysis. The implementation and the achieved results are described in the conclusion of this work.
|
|
|
Generating training data with neural networks
Ševčík, Pavel ; Kolář, Martin (referee) ; Hradiš, Michal (advisor)
The aim of this thesis was to prepare a training data set for traffic sign detection using generative neural networks. The solution uses a modified U-Net architecture and several experiments with the application of styles using AdaIN layers as in the StyleGAN model have been conducted. By extending the real GTSDB data set with the generated images, mean average precision of 80.36 % has been achieved, which yields an improvement of 19.27 % compared to the mean average precision of the detection model trained on real data only.
|
|
|
Biologically Inspired Methods of Object Recognition
Vaľko, Tomáš ; Hradiš, Michal (referee) ; Juránek, Roman (advisor)
Object recognition is one of many tasks in which the computer is still behind the human. Therefore, development in this area takes inspiration from nature and especially from the function of the human brain. This work focuses on object recognition based on extracting relevant information from images, features. Features are obtained in a similar way as the human brain processes visual stimuli. Subsequently, these features are used to train classifiers for object recognition (e.g. SVM, k-NN, ANN). This work examines the feature extraction stage. Its aim is to improve the feature extraction and thereby increase performance of object recognition by computer.
|
guest ::
