|
|
Automatic image annotation
Hegmon, Jiří ; Karásek, Jan (referee) ; Burget, Radim (advisor)
Recognition and comparison of image is one of the main problems and area of the field of computer vision. This thesis adds to these two issues the third, the recognition image semantics, so called annotations or labels. This work uses the knowledge of methods of recognizing the similarity of images to create a tool that is able based on training dataset of images and annotations, create a group most likely annotation for the test set of images. This work presents several types of test datasets suitable for the detection of annotation information for images. Subsequently, best set with the necessary training dataset size and enough information about annotations is selected. Based on this training dataset algorithm is designed for easy loading test set without large demands on computer performance. Evaluation of annotation information is done based on different similarity algorithms. At the beginning of this work was to use a simple, but not very effective method of MSE and comparison of color histograms, but gradually it was necessary to move to using more advanced methods (such as Tamura, Gabor, CEDD nebo různé druhy hostistogramů). The results of this comparison are then taken to evaluate the likelihood of the annotation for the image specified test set. The last part is an evaluation of the accuracy of annotation based on information from the test set.
|
|
|
Face detection and recognition with use of Raspberry Pi
Rozhoňová, Andrea ; Mézl, Martin (referee) ; Hesko, Branislav (advisor)
The following bachelor thesis is focused on the face detection and recognition in an image. The theoretical part divides methods of detection and recognition into several groups and there is better description and explanation of these methods in this part. At the end of the theoretical part is summarized the current utilization of person recognition on the bases of its face in practice. In the practical part is first implemented method for face detection. It is combination of two approaches - approach using haar features and approach using templates of eye. The face recognition is provided by the convolutional neural network. In conclusion there are summarized principles and problems associated with implementation on microcomputer Raspberry Pi and there is also evaluated the success of implemented methods.
|
|
|
Face detection and recognition methods
Zbranek, Miroslav ; Horák, Karel (referee) ; Honec, Peter (advisor)
The aim of this diploma thesis is to explore methods of face detection and recognition in the picture. The method for face detection and the method for face recognition will be chosen according to literature survey. Both methods will be implemented using the OpenCV library and a program language C/C++. The result of this project is creation of graphic interface which use programmed function for face detection and recognition from a picture and also a camcorder.
|
|
|
Paralinguistic signals recognition in spoken dialogs
Mašek, Jan ; Míča, Ivan (referee) ; Atassi, Hicham (advisor)
This document describes the three methods for the detection and classification of paralinguistic expressions such as laughing and crying from usual speech by analysis of the audio signal. The database of records was originally designed for this purpose. When analyzing everyday dialogs, music might be included, so the database was extended by four new classes as speech, music, singing with music and usual speech with background music. Feature extraction, feature reduction and classification are common steps in recognizing for all three methods. Difference of the methods is given by classification process in detail. One classification of all six classes at once is proposed in the first method called straight approach. In the second method called decision tree oriented approach we are using five intuitive sub classifiers in the tree structure and the final method uses for classification emotion coupling approach. The best features were reduced by feature evaluation using F-ratio and GMM classifiers were used for the each classification part.
|
|
|
Detection and Recognition of Matrix Code in Real Time
Dobrovolný, Martin ; Juránková, Markéta (referee) ; Herout, Adam (advisor)
This work is dealing with detecting and recongnizing matrix codes. It is experimenting use of PCLines algorithm. PCLines is using Hough transform and parallel coordinates for fast detection of lines. Suggested algorithm with double use PCLines detects sets of parallels and problem with image distorted by with parallel projection is solved by cross-ratio equation. We did some optimizations for realtime running and created experimental implementation. Test results shows, that use PCLines one way to detect matrix codes.
|
|
|
The identification of objects in an image
Štěpán, Filip ; Malach, Tobiáš (referee) ; Boleček, Libor (advisor)
The aim of this paper is the creation of an algorithm for identification of objects in an image. The resulting programme will be able to process real visual data. This is the reason why the emphasis is put mainly on the complexity of the environment in which the objects are found, reliable segmentation and quality of the object identification. The paper is further focused on the detection and the identification of vertical traffic signs in an image that are found alongside road communication on the territory of the Czech Republic.
|
|
|
Self-Supervised Learning for Recognition of Sports Poses in Image
Konečný, Daniel ; Beran, Vítězslav (referee) ; Herout, Adam (advisor)
Cílem této práce je rozpoznání sportovních pozic v obrazových datech za pomocí přístupu self-supervised learning pro docílení vyšší úspěšnosti klasifikace s použitím malého množství anotovaných vzorků. Učení za pomocí self-supervision je docíleno snímky stejné scény z různých úhlů ve stejných a různých časech. Konvoluční neuronová síť naučená s pomocí funkce triplet loss zakóduje sportovní pozice do latentních vektorů a plně propojená neuronová síť tyto vektory klasifikuje. Model natrénovaný pomocí self-supervised learning dosahuje o 30-40 % vyšší úspěšnosti než supervised model, když je trénovaný pouze na desítkách či jednotkách označených snímků z každé třídy. Hlavními přínosy této práce jsou nástroje pro přípravu datové sady pro tento specifický typ učení, dvě datové sady s více anotacemi a implementované modely využívající self-supervised learning. Výsledky ukazují, že učení za pomocí self-supervision je vhodný přístup pro řešení klasifikace za použití velmi malého množství označených snímků.
|
|
| |
|
| |
|
|
Automated recognition of selected terrain features from their cartographic representation
Sykora, Matúš ; Bayer, Tomáš (advisor) ; Brodský, Lukáš (referee)
Automated recognition of selected terrain features from their cartographic representation. This diploma thesis is dedicated to automatic classification of selected terrain shapes and their cartographic representation. The main aim of this thesis is to design methodological approach for automatic recognition of terrain shapes (hills and valleys) with the use of Machine Learning (Deep Learning). The first part of suggested method divides rough terrain segmentation into two categories, which will be then classified with convolutional neural network. The second part of the thesis is dedicated to the very classification of pre-segmented terrain shapes using Machine Learning. Both parts of the processing are using photos SRTM30 as an input data. The whole proposed method was developed in Python programming language with the usage of Arcpy, TensorFlow and Keras libraries. Keywords: Digital cartography, GIS, terrain shapes, Machine Learning, Deep Learning, recognition, classification, segmentation
|
guest ::
