Classification of Three Different Fish Species by Artificial Neural Networks Using Shape, Color and Texture Properties
Yazarlar (3)
Dr. Öğr. Üyesi Esra Kaya Selçuk Üniversitesi, Türkiye
Prof. Dr. İsmail Sarıtaş Selçuk Üniversitesi, Türkiye
Prof. Dr. Şakir TAŞDEMİR Selçuk Üniversitesi, Türkiye
| Bildiri Türü | Tebliğ/Bildiri | Bildiri Dili | İngilizce |
| Bildiri Alt Türü | Tam Metin Olarak Yayınlanan Tebliğ (Uluslararası Kongre/Sempozyum) | ||
| Bildiri Niteliği | Alanında Hakemli Uluslararası Kongre/Sempozyum | ||
| Kongre Adı | 7th International Conference on Advanced Technologies | ||
| Kongre Tarihi | 28-04-2018 / 01-05-2018 | ||
| Basıldığı Ülke | Türkiye | Basıldığı Şehir | Antalya |
| Bildiri Linki | https://www.icatsconf.org/ICAT18/antalya | ||
| UAK Araştırma Alanları |
Yapay Zeka
|
||
| Özet |
| Long term surveillance of underwater environments is a job which is possible to encounter many hardships due to the environment being unlimited along with being a job that requires great labour and time. Underwater surveillance has the potential to be more efficient and effortless with the help of underwater observation cameras. By recording the obtained image data, studies about underwater can be repeated and improved. In this study, 130 colour and mask images belonging to Amphiprion clarkii, Neoniphon sammara, and Pomacentrus moluccensis fish species were used which were obtained for Fish4Knowledge project supported by FP7 European Commission. These 3 different kinds of fish were classified using Artificial Neural Network based on shape, colour and texture features extracted. It can be seen from the classification accuracy of 98.88% that the study was successful. |
| Anahtar Kelimeler |
