|
|
Deep Learning for Object Detection
Paníček, Andrej ; Herout, Adam (referee) ; Teuer, Lukáš (advisor)
This work deals with the object detection using deep neural networks. As part of the solution, I modified, implemented and trained the well-known model of cascade neural networks MTCNN so that it could perform the detection of traffic signs. The training data was generated from GTSRB and GTSDB data sets. MTCNN showed solid performance on the evaluation data, where the detection accuracy reached 97.8 %.
|
|
|
Landmark Detection in Medical Images Using Deep Neural Networks
Škandera, Juraj ; Španěl, Michal (referee) ; Kodym, Oldřich (advisor)
This thesis deals with detection of anatomical landmarks from cephalometric X-ray images using convolutional neural networks. Program works with public available dataset, which consists of side X-ray images of skull. There are two architectures of convolutional neural networks proposed in this thesis. The best architecture achieves accuracy of 73.22% for detection within 5 mm. Program is created in Python language with use of Tensorflow framework.
|
|
|
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.
|
|
|
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.
|
|
|
Convolutional Neural Networks
Lietavcová, Zuzana ; Zbořil, František (referee) ; Zbořil, František (advisor)
This thesis deals with convolutional neural networks. It is a kind of deep neural networks that are presently widely used mainly for image recognition and natural language processing. The thesis describes specifics of convolutional neural networks in comparison with traditional neural networks and is focused on inner computations in the process of learning. Convolutional neural networks typically consist of a different types of layers of neurons and the core part of this thesis is to demonstrate computations of individual types of layers. Learning demonstrating program of a simple convolutional network was designed and implemented using own implementation of neural network. Validity of the implementation was tested by training models for solving a classification task. Experiments with different types of architectures were conducted and their performance was compared.
|
|
| |
|
|
Apparent Personality Analysis from Video
Čigáš, Patrik ; Sochor, Jakub (referee) ; Hradiš, Michal (advisor)
This bachelor thesis deals with experiments with systems for apparent personality analysis from video, and compares accuracy of these systems. Systems from the experiments are created by linear regression and convolutional neural networks. Experiments compare accuracy of linear regressors processing visual and audial modality of video. On spectograms made from audial modality of video, thesis evaluates results of convolutional neural networks with varying number of convolutional and fully connected layers nad subsequently compares accuracy of regression solution and classification solution of the problem. For visual modality of video the thesis compares information values of gaze movement and face landmarks movement. System processing face landmarks movement reaches the best results in the experiments.
|
|
|
Disparity Map Estimation from Stereo Image
Tábi, Roman ; Maršík, Lukáš (referee) ; Španěl, Michal (advisor)
The master thesis focuses on disparity map estimation using convolutional neural network. It discusses the problem of using convolutional neural networks for image comparison and disparity computation from stereo image as well as existing approaches of solutions for given problem. It also proposes and implements system that consists of convolutional neural network that measures the similarity between two image patches, and filtering and smoothing methods to improve the result disparity map. Experiments and results show, that the most quality disparity maps are computed using CNN on input patches with the size of 9x9 pixels combined with matching cost agregation and correction algorithm and bilateral filter.
|
|
|
Depth Estimation by Convolutional Neural Networks
Ivanecký, Ján ; Španěl, Michal (referee) ; Hradiš, Michal (advisor)
This thesis deals with depth estimation using convolutional neural networks. I propose a three-part model as a solution to this problem. The model contains a global context network which estimates coarse depth structure of the scene, a gradient network which estimates depth gradients and a refining network which utilizes the outputs of previous two networks to produce the final depth map. Additionally, I present a normalized loss function for training neural networks. Applying normalized loss function results in better estimates of the scene's relative depth structure, however it results in a loss of information about the absolute scale of the scene.
|
|
|
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.
|
guest ::
