Glasgow College UESTC Final Year Project
Project Title
A novel face image generation method
Programme
Electronics and Information Engineering Communications Engineering
Source of topic
Scientific research
Industry
Teaching
Others
Project Type:Check the most appropriate boxes below
Engineering Design
Firmware Implementation
Theoretical Study
Software Simulation
Case Study
Hardware Prototyping
Subject Area:Check the most appropriate one box below
Communications
Machine learning
Control
Signal Processing
Embedded Processors/Systems
Electronics
Image Processing
Power
Project Description
The performance of machine learning methods is heavily dependent on the choice of data representation (or features) on which they are applied. For that reason, much of the actual effort in deploying machine learning algorithms goes into the design of data transformations that result in a representation of the data that can support effective machine learning. Due to the labor-intensive of feature engineering, a novel method for the data representation method is deserved to attention. This project will develop a new face image generation method, which is based on the generative adversarial nets. The focus of this project is mainly to understand the relationship data distribution and data representation. And it is also necessary to know the basic knowledge of convolutional neural networks.
Prerequisite Skills
This project would suit the student who is interested in machine learning and neural networks.
The candidate must be capable of program edit of python, mathematical deduction and logic analysis. Moreover, the candidate needs to have experience in running programs under deep learning frameworks such as tensorflow.
Reviews
There are no reviews yet.