Aristoteles, Aristoteles and Heningtyas, Yunda and Kristiani, Maria (2020) Canny Edge Detection for Goldfish (Carrasius auratus) Identification. In: 3RD INTERNATIONAL CONFERENCE ON APPLIED SCIENCE MATHEMATICS AND INFORMATICS (3RD ICASMI), 3-4 September 2020, FMIPA Universitas Lampung.
|
Text
Abstrak SN-SMIAP V.pdf Download (5MB) | Preview |
Abstract
Goldfish (Carrasius auratus) is one of freshwater ornamental fishes that has interested by community. The uniqueness of goldfish is body shape, scale, and color. goldfish have similar morphology so many goldfish enthusiasts and many goldfish fans and marine and fisheries biologists find it difficult to identify goldfish species. Fantail, Oranda, dan Ranchu are three of 130 strains of goldfish that are difficult to identify. Canny Edge Detection is a feature extraction method that detects the edges of the goldfish image object. This research using 225 images of goldfish with 180 images for training data and 45 images for testing data. Distribution of datasets used 5- fold cross validation. Clasification of goldfish image using PNN with the great greatest accuracy is obtained at the smoothing value (σ) = 1.5 reaching 99.11%.
| Item Type: | Conference or Workshop Item (Speech) |
|---|---|
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
| Divisions: | Fakultas Matematika dan Ilmu Pengetahuan Alam (FMIPA) > Prodi Ilmu Komputer |
| Depositing User: | heningtyas yunda |
| Date Deposited: | 17 Nov 2020 01:43 |
| Last Modified: | 17 Nov 2020 01:43 |
| URI: | http://repository.lppm.unila.ac.id/id/eprint/25670 |
Actions (login required)
 |
View Item |