Fish-Health Monitoring System Based on Image Processing

 




 

Sim, Tao Wei (2018) Fish-Health Monitoring System Based on Image Processing. Final Year Project (Bachelor), Tunku Abdul Rahman University College.

[img] Text
Sim Tao Wei.pdf
Restricted to Registered users only

Download (2MB)

Abstract

Image processing is still a great demand for research. Research related to the image processing can be components of color, texture and pattern. This project is focus on identify the disease infected by the pet fish and also allow the user monitor their pet fish through the web browser. According to the research done, beside dog and cat, the pet fish is one of the pet which occupied large amount of pet population. When the pet fish is low resistance to disease, it will be infected by disease easily which may bring it to dead. For the owner who are lack of knowledge in identifying the disease of their pet fish or always busy for their work may need this project to assist them identify the condition of their pet fish. A camera is used to capture the image and send to the internet storage to display on the web browser and also send to the system to process the image. The image will go through pre-processing to filter away the noise, segmentation process to separate the foreground and background of image, post-processing to extract the feature of diseased region and classification to identify the type of infected disease. The result shown that the accuracy of the system will be affected by the brightness and contrast level of the input image. By increasing the contrast level of the image able to increase the accuracy but the change of brightness may cause the drop of 50% of accuracy.

Item Type: Final Year Project
Subjects: Technology > Electrical engineering. Electronics engineering
Faculties: Faculty of Engineering and Technology > Bachelor of Engineering (Honours) Electrical and Electronics
Depositing User: Library Staff
Date Deposited: 10 Oct 2018 08:44
Last Modified: 10 Oct 2018 08:44
URI: https://eprints.tarc.edu.my/id/eprint/293