Oct 22, 2019   6:28 a.m. Sergej
Academic information system

Persons at STU

This page displays all publicly accessible information about the desired person. Some information about the person's occupation and offices may be hidden.

Ing. Marek Jakab
Identification number: 5669
University e-mail: marek.jakab [at] stuba.sk
Výskumný pracovník s VŠ vzdelaním - Institute of Computer Engineering and Applied Informatics (FIIT)
2511V00  Applied Informatics D-AI
FIIT D-AI den [year 3]
Doctoral type of study, full-time, attendance method form
3rd year of study

Contacts     Graduate     Lesson     Final thesis     
Projects     Publications     Supervised theses     

Basic information

Basic information about a final thesis

Type of thesis: Diploma thesis
Thesis title:Object recognition using convolutional neural networks
Written by (author): Ing. Jozef Pazúrik
Department: Institute of Computer Engineering and Applied Informatics (FIIT)
Thesis supervisor: Ing. Marek Jakab
Opponent:Ing. Lukáš Hudec
Final thesis progress:Final thesis was successfully defended.

Additional information

Additional information about the final thesis follows. Click on the language link to display the information in the desired language.

Language of final thesis:English

Slovak        English

Title of the thesis:Object recognition using convolutional neural networks
Summary:Object detection is one of the main tasks in the computer vision field. Object detection has high potential and numerous applications in industry, augmented reality, security systems and robotics field. With the recent advent of machine learning and deep convolutional networks, the new methods for image segmentation and object detection became available. However, despite their huge success in computer vision, there are still many problems, the neural networks are suffering from, which makes them impractical and less usable. This thesis is focused on analyzing existing methods in deep convolutional neural networks for object recognition in effort to combine these different methods to design and create custom prototype model, to possibly achieve better results with one of the common public datasets.
Key words:Object recognition, convolutional neural networks, local feature descriptor

Display and download files

To display the final thesis assignment form click on the Display the final thesis assignment form icon. The following icons - Final thesis, Thesis appendices, Supervisor's review, Opponent's review - relate to the final thesis and can be downloaded. They could be displayed on condition they have been inserted and are available publicly.

Display the assignment form

Parts of thesis with postponed release:

Final thesis (final thesis appendices) unlimited
Reviews for final thesis unlimited