Abstract: The development of automatic fish counters had been driven by the need for accurate, long-term and cost-effective counting and recognition for the advancement of aquaculture in the Philippines. Non-invasive methods of fish counting are ultimately limited by the properties of the immerging technologies like when candidates for counting are transparent and or small (Bangus Fry). Image processing is one of the most modern approaches in automating the counting process. The main objective of the study is to evaluate three image segmentation algorithms namely (1) Watershed Algorithm, (2) Hough Transform, (3) Concavity Analysis, in 2D image, whether or not they are capable of segmenting two-weeks old bangus fry’s’ in an image. The basic steps involved in the conduct of this study are the following; Image acquisition, Image Pre-Processing, Image segmentation, and Object counting. Result shows that the first method of the Concavity Analysis which locates the contours or curve points edges of the objects in an image performs best with the other algorithm with an accuracy rate of 94.36% with 7 false positive detections, and 154 False Negative, in an experimental data of four sets of 2D image ranging from 100, 200, 300, and 400 bangus fry per test image.
Keywords: Aquaculture, Image Segmentation Algorithms, Watershed Algorithm, Hough Transform, Concavity Analysis, Evaluation
| DOI: 10.17148/IJARCCE.2022.11103