13.05.2018 Views

merged

Create successful ePaper yourself

Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.

Detection Area of Disease on Hybrid Grouper Fish Body Using Image<br />

Processing Techniques<br />

Ku Norsyaziema Ku Harith<br />

Supervisor: Dr. Ezmahamrul Afreen bin Awalludin<br />

Bachelor of Applied Science (Fisheries)<br />

School of Fisheries and Aquaculture Sciences<br />

Fish disease is one of the important parts in fisheries study to determine status of fish<br />

health. In the manual approach, to detect fish disease on its body is challenging task<br />

and labor-intensive as well as time consuming. Therefore, an image processing<br />

technique based on edge detection and blob processing is proposed to segment the<br />

disease area on fish body automatically. This proposed method is an alternative<br />

approach solution to the manual approach system specifically to determine disease<br />

area on hybrid grouper. The total number of 20 samples dataset has been collected<br />

from Pusat Pembenihan dan Asuhan Ikan Marin. Based on the experimental results,<br />

there was a significant difference in the scores for health area (M=25.11, SD=8.59)<br />

and unhealthy area (M=4.55, SD=2.14) conditions; t(2)=10.382, p=0.05. The<br />

proposed method is capable to estimate the fish disease area with less labor intensive<br />

and less time consuming.<br />

589 | UMT UNDERGRADUATE RESEARCH DAY 2018

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!