Classification of Hazelnut Species with Pre-Trained Deep Learning Models
Yazarlar (3)
| Makale Türü |
Özgün Makale
(Diğer hakemli uluslarası dergilerde yayınlanan tam makale)
|
||
| Dergi Adı | intelligent methods in engineering sciences | ||
| Dergi ISSN | 2979-9236 | ||
| Dergi Tarandığı Indeksler | Academic Resource Index | ||
| Makale Dili | İngilizce | Basım Tarihi | 02-2023 |
| Kabul Tarihi | 01-06-2023 | Yayınlanma Tarihi | 01-06-2023 |
| Cilt / Sayı / Sayfa | 2 / 2 / 58–66 | DOI | 10.58190/imiens.2023.14 |
| Makale Linki | https://www.imiens.org/index.php/imiens/article/view/34/18 | ||
| UAK Araştırma Alanları |
Görüntü İşleme
Makine Öğrenmesi
Yapay Zeka
|
||
| Özet |
| A form of shelled nut in the Betulaceae family is the hazelnut. The majority of it is grown in Türkiye internationally. It grows in the provinces of Türkiye's Black Sea region, which is a significant global production hub. Hazelnuts can be eaten in a variety of ways and are a great source of protein, fat, fiber, vitamins, and minerals. There are numerous applications for hazelnuts in the food business. This study uses pre-trained networks to categorize eight of the most popular hazelnut kinds farmed in Türkiye. In this study, locally named hazelnut varieties grown in Türkiye were examined. An automated computer vision system was used to capture the images of the different hazelnut kinds. Our dataset includes a total of 2722 images, consisting of 155 palaz, 340 yagli, 399 deve disi, 236 tombul, 399 damat, 354 cakildak, 437 kara findik, and 402 sivri hazelnuts. Using transfer learning, the DenseNet121 and InceptionV3 models of convolutional neural networks were employed to categorize these images. The dataset was split into training and testing portions, respectively. With InceptionV3 and DenseNet121, respectively, the research revealed classification accuracy of 96.99% and 96.18%. |
| Anahtar Kelimeler |
BM Sürdürülebilir Kalkınma Amaçları
| Atıf Sayıları | |
| Google Scholar | 7 |