|
|
Pedestrian Attribute Analysis
Studená, Zuzana ; Špaňhel, Jakub (referee) ; Hradiš, Michal (advisor)
This work deals with obtaining pedestrian information, which are captured by static, external cameras located in public, outdoor or indoor spaces. The aim is to obtain as much information as possible. Information such as gender, age and type of clothing, accessories, fashion style, or overall personality are obtained using using convolutional neural networks. One part of the work consists of creating a new dataset that captures pedestrians and includes information about the person's sex, age, and fashion style. Another part of the thesis is the design and implementation of convolutional neural networks, which classify the mentioned pedestrian characteristics. Neural networks evaluate pedestrian input images in PETA, FashionStyle14 and BUT Pedestrian Attributes datasets. Experiments performed over the PETA and FashionStyle datasets compare my results to various convolutional neural networks described in publications. Further experiments are shown on created BUT data set of pedestrian attributes.
|
|
|
Volumetric Segmentation of Dental CT Data
Berezný, Matej ; Kodym, Oldřich (referee) ; Čadík, Martin (advisor)
The main goal of this work was to use neural networks for volumetric segmentation of dental CBCT data. As a byproducts, both new dataset including sparse and dense annotations and automatic preprocessing pipeline were produced. Additionally, the possibility of applying transfer learning and multi-phase training in order to improve segmentation results was tested. From the various tests that were carried out, conclusion can be drawn that both multi-phase training and transfer learning showed substantial improvement in dice score for both sparse and dense annotations compared to the baseline method.
|
|
|
Evolutionary Algorithms in Convolutional Neural Network Design
Badáň, Filip ; Vašíček, Zdeněk (referee) ; Sekanina, Lukáš (advisor)
This work focuses on automatization of neural network design via the so-called neuroevolution, which employs evolutionary algorithms to construct artificial neural networks or optimise their parameters. The goal of the project is to design and implement an evolutionary algorithm which can be used in the process of designing and optimizing topologies of convolutional neural networks. The effectiveness of the proposed framework was experimentally evaluated on tasks of image classification on datasets MNIST and CIFAR10 and compared with relevant solutions. The results showed that neuroevolution has a potential to successfully find accurate and effective convolutional neural network architectures.
|
|
|
Interpretability of Neural Networks in Speech Processing
Sarvaš, Marek ; Mošner, Ladislav (referee) ; Žmolíková, Kateřina (advisor)
S rastúcou popularitou hlbokých neurónových sietí, nedostatok transparentnosti spôsobenejich funkciou čiernej skrinky, zvyšuje dopyt po ich interpretácii. Cieľom tejto práce je získať nový pohľad na hlboké neurónové siete v úlohách spracovania reči. Konkrétne klasifikácia pohlavia z AudioMNIST datasetu a klasifikácia rečníka z filter bánk VoxCeleb datasetu s použitím konvolučnej a reziduálnej neurónovej siete. Na interpretáciu týchto neurónových sietí bola použitá metóda propagácie relevancií cez vrstvy. Táto metóda vytvorí tepelnú mapu, ktorá vyznačí príznaky, ktoré prispeli ku správnej klasifikácii pozitívne a ktoré negatívne. Ako výsledky interpretácie ukazujú, klasifikácie boli založené najmä na nižších frekvenciách v reči a čase. V prípade klasifikácie pohlavia sa mi podarilo nájsť vysokú závislosť modelu na veľmi malom počte príznakov. Pomocou získaných informácií som vytvoril rozšírený trénovací set, ktorý zvýšil robustnosť modelu.
|
|
|
Trainable image segmentation using deep neural networks
Majtán, Martin ; Burget, Radim (referee) ; Harár, Pavol (advisor)
Diploma thesis is aimed to trainable image segmentation using deep neural networks. In the paper is explained the principle of digital image processing and image segmentation. In the paper is also explained the principle of artificial neural network, model of artificial neuron, training and activation of artificial neural network. In practical part of the paper is created an algorithm of sliding window to generate sub-images from image from magnetic rezonance. Generated sub-images are used to train, test and validate of the model of neural network. In practical part of the paper si created the model of the artificial neural network, which is used to trainable image segmentation. Model of the neural network is created using the Deeplearning4j library and it is optimized to parallel training using Spark library.
|
|
|
Presentation Attack Detection on Hand Sensing Technology in Infrared Area
Richtarik, Jakub ; Sakin, Martin (referee) ; Drahanský, Martin (advisor)
When verifying a fingerprint, an attacker can use a counterfeit made of synthetic material. This can be prevented, for example, by using multispectral analysis, when various materials have different reflectance for certain wavelengths. There are several studies that have addressed this, but have always focused on one finger. The aim of this work is liveness detection on the whole palm and fingers, as on a larger object, which will contribute to even higher level of security. In the final solution, a NIR camera was used to capture the dataset, which is used to train a convolutional network to determine whether it is a living hand or a counterfeit.
|
|
|
Deep Learning for Medical Image Analysis
Dronzeková, Michaela ; Kodym, Oldřich (referee) ; Španěl, Michal (advisor)
The purpose of this thesis is to use convolutional neural networks for X-ray image classification of human body. Four different architectures of neural networks have been created. They were trained and tested on three tasks: classification of front and lateral chest, classification of X-ray images into several different categories and classification of diseases in chest X-ray. ResNet and SEResNet architectures achieved the best results. SEResNet scored 99,49% accuracy in the first task, ResNet achieved 94,97% accuracy in the second task and SEResNet reached 31,53% in the third task with F1 measure as metrics for evaluating results.
|
|
|
Deep Neural Network Optimization
Bažík, Martin ; Wiglasz, Michal (referee) ; Sekanina, Lukáš (advisor)
The goal of this thesis was to design, implement and analyze various optimizations of deep neural networks, in order to improve the observed parameters. The optimizations are based on modification of the data representation used by neural network operations and searching for the best combination of its hyper-parameters. The convolutional neural networks used for these optimizations were built on LeNet-5 architecture and trained on MNIST, CIFAR-10, and SVHN datasets. The neural networks and their optimizations were implemented within Tiny-dnn library using C++ programming language.
|
|
|
Command Classification from EMG Using Neural Network
Zauška, Ján ; Šůstek, Martin (referee) ; Szőke, Igor (advisor)
This work deals with classification of 15 commands (short words), from small dataset recorded by sEMG electrodes placed on face and neck of speaker. Two types of speech are differentiated in recordings - audible speech, what is classic speech and silent speech, hence speech, in which sound output is suppressed. This work describes EMG signal processing, feature extraction, classifier design and classification results. The convolutional neural network architecture was used as a classifier. There are a lot of experiments in this work that compare the classification accuracy of silent and audible speech.
|
|
|
Urban Element Detection Using Satellite Imagery
Oravec, Dávid ; Herout, Adam (referee) ; Zlámal, Adam (advisor)
Táto práca sa zameriava na správnu detekciu objektov v satelitných snímkach pomocou konvolučných neuronových sietí. Cieľom práce je pomocou natrénovaného modelu detekovať bazény a tenisové ihriská v satelitných snímkach z rôznych miest. Model pracuje s dátami z 10 rôznych miest. Pri vypracovaní bol využitý model neurónovej siete RetinaNet a knižnica Detectron2. Model, ktorý sa podarilo vytrénovať, dokáže detekovať objekty s priemernou presnosťou (AP50) na úrovni 63,402 %. Práca môže byť prínosom v oblasti automatizovania získavania štatistík o povrchu zeme.
|
guest ::
