|
|
Detection and Recognition of License Plates
Tykva, Jiří ; Zemčík, Pavel (referee) ; Juránek, Roman (advisor)
Cílem této bakalářské práce je návrh, implementace a testování systému, který v reálném čase pomocí neuronových sítí bude detekovat a rozpoznávat registrační značky vozidel. Nasbíraná data budou ukládána do databáze. Architektura systému je rozdělena do tří hlavních částí. První část řeší detekci registrační značky v obraze pomocí TensorFlow Object Detection API. Detektor dosahuje přesnosti 98.15 % AP při rychlosti kolem 14 fps. Druhá část se zabývá sledováním značek ve videu pomocí algoritmu SORT. Třetí část systému se věnuje holistickému rozpoznávání textu registrační značky a dosahuje až 0.6% chybovosti při rozpoznávání jednotlivých znaků a 2% chybovosti při rozpoznávání celého textu. Výsledný systém lze použít například pro policejní oddělení za účelem sledování kradených vozidel či automatického vybírání dálničních poplatků.
|
|
|
Vehicle License Plate Detection and Recognition Software
Masaryk, Adam ; Hradiš, Michal (referee) ; Špaňhel, Jakub (advisor)
The aim of this bachelor thesis is to design and develop software that can detect and recognize license plates from images. The software is divided into 3 parts - license plates detection, detector output processing and license plates characters recognition. We decided to implement detection and recognition using modern methods using convolutional neural networks.
|
|
|
Synthetic Dataset Generator for Traffic Analysis
Svoreň, Ondrej ; Sochor, Jakub (referee) ; Herout, Adam (advisor)
This bachelor thesis deals with the creation and customization of synthetic dataset genera tor for traffic analysis. It focuses on traffic analysis by means of computer vision, methods and conditions of creating the generator of synthetic dataset, possible application of achie ved results in machine learning and additional development opportunities. Using available automobile photographs from the Czech Republic, Slovakia, Poland and Hungary, a synthe tic license plate number generator was created, which, after graphical adjustment and after joining with the vehicle photographs creates the resulting dataset for machine learning. The solution itself is divided into the three scripts written in Python using the OpenCV library. The resulting dataset serves as an input for the machine learning system to re-identify the license plate numbers from photographs captured in the flow of traffic.
|
|
|
Holistic License Plate Recognition Based on Convolution Neural Networks
Le, Hoang Anh ; Hradiš, Michal (referee) ; Špaňhel, Jakub (advisor)
Main goal of this work was to create a holistic license plate reader, with an emphasis on achieving the highest possible accuracy on low quality images. Combination of convolutional and recurrent neural networks was designed and implemented, with usage of LSTM and CTC, where the inputs are cut-outs from the entire license plate. Competitive networks were also implemented to compare results. Networks were compared on a total of 4 datasets and the results were, that my design has achieved the best results with a recognition accuracy of 97.6%.
|
|
|
Image-Based Licence Plate Recognition
Vacek, Michal ; Hradiš, Michal (referee) ; Beran, Vítězslav (advisor)
In first part thesis contains known methods of license plate detection. Preprocessing-based methods, AdaBoost-based methods and extremal region detection methods are described.Finally, there is a described and implemented own access using local detectors to creating visual vocabulary, which is used to plate recognition. All measurements are summarized on the end.
|
|
|
License plate recognition
Trkal, Ondřej ; Hynčica, Tomáš (referee) ; Jirsík, Václav (advisor)
This thesis deals with the recognition of license plates using neural networks with backpropagation learning. The theoretical section is a brief summary of the principle of creating a new license plate, computer vision and neural networks with backpropagation learning. The practical part describes the design of methods used to detect single-line license plates of cars in the Czech Republic. In this work has been tested several ways to describe the signs and examined the effect of these descriptions and topology of neural networks for quality license plate recognition.
|
|
|
License Plate Detection and Recognition
Řepka, Michal ; Sochor, Jakub (referee) ; Herout, Adam (advisor)
This paper addresses the problem of object detection and recognition from still images using methods of computer vision. The objects of detection are czech license plates and the goal of this paper was to create an automatic license plate anotation tool. Suggested solution uses edge detection and machine learned cascading classifiers. Created application was then tested on dataset taken by the author.
|
|
|
License Plate Detection and Localization
Šlosár, Peter ; Beran, Vítězslav (referee) ; Herout, Adam (advisor)
This bachelor's thesis deals with the detection and localization of vehicle registration plates. Theoretical part discusses properties and appearance of Czech and Slovak license plates and also methods presently used for detection and localization of license plates. Main part of the thesis consists of design and implementation of new detection and localization method using corner detector, clustering and cascade classification. Final part describes testing of this system using dataset and evaluates its success rate.
|
|
| |
|
|
License Plate Detection and Recognition from Still Image
Janíček, Kryštof ; Sochor, Jakub (referee) ; Špaňhel, Jakub (advisor)
This thesis describes the design and implementation of system for detection and recognition of license plate. This system is divided into three parts which are license plate detection, character segmentation and optical character recognition. License plate detection is done by cascade classifier that achieves hit rate of 95.5% and precision rate of 95.9%. Character segmentation is based on contour finding that achieves hit rate of 93.3% and precision rate of 96.5%. Optical character recognition is done by neural network and achieves hit rate of 98.4% for individual characters. The whole system is able to detect and recognize up to 81.5% of license plates from the test data set.
|
guest ::
