Affiliation:
1. Democritus University of Thrace, Department of Electrical and Computer Engineering Xanthi, 67100 GREECE
2. Democritus University of Thrace, Department of Production Engineering and Management Xanthi, 67100 GREECE
Abstract
The purpose of the study is to analyse and compare the most common machine learning and deep learning techniques used for computer vision 2D object classification tasks. Firstly, we will present the theoretical background of the Bag of Visual words model and Deep Convolutional Neural Networks (DCNN). Secondly, we will implement a Bag of Visual Words model, the VGG16 CNN Architecture. Thirdly, we will present our custom and novice DCNN in which we test the aforementioned implementations on a modified version of the Belgium Traffic Sign dataset. Our results showcase the effects of hyperparameters on traditional machine learning and the advantage in terms of accuracy of DCNNs compared to classical machine learning methods. As our tests indicate, our proposed solution can achieve similar - and in some cases better - results than existing DCNNs architectures. Finally, the technical merit of this article lies in the presented computationally simpler DCNN architecture, which we believe can pave the way towards using more efficient architectures for basic tasks.
Publisher
World Scientific and Engineering Academy and Society (WSEAS)
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Supervised Machine Learning Models for the Prediction of Renal Failure in Senegal;2023 International Conference on Control, Artificial Intelligence, Robotics & Optimization (ICCAIRO);2023-04
2. Anomaly Detection Using Deep CNN-ELM in Semiconductor Manufacturing;2022 6th European Conference on Electrical Engineering & Computer Science (ELECS);2022-12
3. Peculiarities of the Hybrid Model Built Using Parallel Data;2022 7th International Conference on Mathematics and Computers in Sciences and Industry (MCSI);2022-08