implement classification for traffic signs using convolutional neural network

Mohamad Abdulrahman

Master's thesis

Abstract:

The ability to classify traffic signs quickly and effectively is great importance for autonomous cars or as a driver’s assistance in some difficult circumstances. many techniques in machine learning were used like Support Vector Machine and Random Forest, on the other hand deep learning techniques reached state of art performance in many image classifications tasks. Convolutional neural networks have proven to be highly capable in many areas of deep learning, particularly in the field of image classification. As this work provides an overview of the most important architectures and techniques, what are the areas other than image classification, and which open-source programs are most used with these architectures. the ability of CNN to treat with real experiments is discussed. and real tests to check the performance of the proposed model is implemented by using an external camera as a test tool with modifying parameters of CNN model to achieve the highest possible accuracy value for prediction process with lowest possible training time.

Keywords

Convolutional Neural Network, Deep learning, ILSVRC

Language used: English

Date on which the thesis was submitted / produced: 31. 3. 2021

Thesis defence

• Supervisor: doc. Ing. Arnošt Veselý, CSc.

Czech University of Life Sciences Prague

Faculty of Economics and Management

Master programme / field:
Systems Engineering and Informatics / Informatics