| Author: | Wong, Kwun Shing |
| Title: | Evolutionary computing of 2D cartoon character design |
| Advisors: | Chan, Keith (COMP) |
| Degree: | M.Sc. |
| Year: | 2019 |
| Subject: | Hong Kong Polytechnic University -- Dissertations Cartoon characters Cartooning -- Computer-aided design |
| Department: | Department of Computing |
| Pages: | vii, 43 pages : color illustrations |
| Language: | English |
| Abstract: | The cartoon character design problem, which is concerned with the finding of the best appearance among many ones under some constraints. There is a discrepancy of a cartoon character design because there are many constraints and have no conception that can fulfil all of the situations. These constraints maybe are unknown, and it is dependent on the designer need. A designer's requirements can be forming a finite set of solutions, and the ultimate solution is to find the optimal design from these set of designs. Thus, it can be formulated as a combinatorial optimization problem and can solve with evolutionary computing. A cartoon generated system based on Interactive Genetic Algorithm (IGA) proposed in this paper. The solution to a design problem is very subjective. There is no objective measurement of a solution to the design problem. So, the problem-solving process requires the human being to involve. The IGA requested the human's subjective measurements replace the fitness function. Thus, the solution provided by IGA can be better reflect the user preferences. A cartoon figure can separate into various components for conducting evolutionary processes. The system in the experiment divided a cartoon figure into two main parts that are head and body. The head included hair, eyes, nose, mouth, ears, and face shape. The body part covered the upper body and lower body. These components will be applying a binary encoding method to encode. After encoded these components, the elements can go through the standard Genetic Algorithm (GA) procedure. The slight difference with GA is the user selection replaced the fitness function. It can subside the gap between the users' expectation and generated solutions. Experimental results demonstrate the feasibility of the proposed approach to solve the cartoon design problem. |
| Rights: | All rights reserved |
| Access: | restricted access |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 991022268443803411.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 2.07 MB | Adobe PDF | View/Open |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/10155