Search
Now showing items 1-10 of 23
Realtime Pedestrian Recognition Using Siamese Network
(Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií, 2018)
Image similarity measuring has many various applications. Pedestrian recognition is one of them and for the security purposes it is basically required to run in real-time. This paper proposes a deep Siamese neural network ...
Segmentation Of Cartilage Tissue In Micro Ct Images Of Mouse Embryos With Modified U-Net Convolutional Neural Network
(Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií, 2019)
Manual segmentation of cartilage tissue in micro CT images of mouse embryos is a very time-consuming process and significantly increases the time required for the research of mammal facial structure development. It is ...
Augmentation Technique For Artificial Phase-Contrast Microscopy Images Generation For The Training Of Deep Learning Algorithms
(Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií, 2019)
Phase contrast segmentation is crucial for various biological tasks such us quantitative, comparative or single cell level analysis. The popularity of image segmentation using deep learning strategies has been transferred ...
Convolutional Neural Networks For Identification Of Axial 2d Slices In Ct Data
(Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií, 2018)
This thesis deals with the classification of 2D axial slices in CT patient’s data. The classification is realized into six categories. The sphere of convolutional neural networks was used for this purpose and AlexNet network ...
Deep Convolutional Networks For Oct Image Classification
(Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií, 2019)
In this work, OCT (optical coherence tomography) images are classified according to the present pathology into four distinct categories. Three different neural network models are used to classify images, each model is ...
Language-Independent Text Classifier Based On Recurrent Neural Networks
(Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií, 2019)
This paper deals with a proposal of language independent text classifiers based on recurrent neural networks. They work at a character level thus they do not require any text preprocessing. The classifiers have been trained ...
Denoise Pre-Training For Segmentation Neural Networks
(Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií, 2019)
This paper proposes a method for pre-training segmentation neural networks on small datasets using unlabelled training data with added noise. The pre-training process helps the network with initial better weights settings ...
Evaluation Of Cnn And Cldnn Architectures On Radio Modulation Datasets
(Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií, 2021)
This paper presents an evaluation of deep learning architectures designed for modulationrecognition. The evaluation inspects, whether the architectures behave in the same way as they didon the dataset they were designed ...
Atrial Fibrillation Classification Using Deep Convolution Networks
(Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií, 2020)
We propose the usage of three deep convolutional neural networks architectures for classification of a single lead electrocardiogram (ECG) recordings and evaluate them on the atrial fibrillation (AFIB) classification, for ...
Multiclass Segmentation Of 3d Medical Data With Deep Learning
(Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií, 2020)
This paper deals with multiclass image segmentation using convolutional neural networks. The theoretical part of paper focuses on image segmentation. There are basics principles of neural networks and image segmentation ...