Please use this identifier to cite or link to this item:
http://dspace.cityu.edu.hk/handle/2031/9050| Title: | Traffic Sign Recognition by Deep Learning |
| Authors: | Chau, Kwan Yin |
| Department: | Department of Electronic Engineering |
| Issue Date: | 2017 |
| Supervisor: | Supervisor: Mr. Ting, Van C W; Assessor: Mr. Ng, Kai Tat |
| Abstract: | Convolutional Neural Network is a common way to address image recognition problems in recent years. Among these years, some new ideas which related to CNN is found, such as dropout and batch normalization. In this project, CNN models are built based on two famous model architecture. Initialization of parameters are chosen carefully. Experiments were done on different architectures and parameters. Results are found which match the mathematical and statistical theories supported behind. |
| Appears in Collections: | Electrical Engineering - Undergraduate Final Year Projects |
Files in This Item:
| File | Size | Format | |
|---|---|---|---|
| fulltext.html | 148 B | HTML | View/Open |
Items in Digital CityU Collections are protected by copyright, with all rights reserved, unless otherwise indicated.