Guava fruit classification system design with convolutional neural networks

Buket Toptaş; Sara Altun Güven

Makale detayları

Guava fruit classification system design with convolutional neural networks

Yazarlar:

Buket Toptaş | Sara Altun Güven

Yayıncı:

Gumushane University

Ana Başlıklar:

Görüntü İşleme | Derin Öğrenme | Sınıflandırma algoritmaları

Dergi:

Gümüşhane Üniversitesi Fen Bilimleri Dergisi Vol.14 Issue 4, pp.1247-1258

Belge Tipi:

Makale

Yayın Tarihi:

12/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001333160

pISSN:

2146-538X

Anahtar kelimeler:

Özet:

 For the rapid and precise advancement of agriculture, artificial intelligence applications are of significant importance. Processes such as disease detection in the agricultural field, identification of soil types, and classification of plants and fruits are currently performed manually. Artificial intelligence enables the automation of these processes, leading to cost reduction and the minimization of human errors. In this study, a system for classifying the species of Guava fruit has been proposed. The proposed system is designed using four pre-trained convolutional neural networks. The convolutional neural networks used are GoogLeNet, Vgg19, ResNet50, and DenseNet201 architectures. The Guava fruit dataset was classified by both k-fold-stratified and an 80:20 split. All experimental studies were evaluated using six different performance metrics. The best result was achieved with the DenseNet201 architecture in the proposed method. The performance results for the DenseNet201 architecture in terms of accuracy, sensitivity, specificity, F1-score, MCC, and kappa are as follows: accuracy - 0.9658, sensitivity - 0.9677, specificity - 0.9954, F1-score - 0.9681, MCC - 0.9640, and Kappa - 0.8268.

 For the rapid and precise advancement of agriculture, artificial intelligence applications are of significant importance. Processes such as disease detection in the agricultural field, identification of soil types, and classification of plants and fruits are currently performed manually. Artificial intelligence enables the automation of these processes, leading to cost reduction and the minimization of human errors. In this study, a system for classifying the species of Guava fruit has been proposed. The proposed system is designed using four pre-trained convolutional neural networks. The convolutional neural networks used are GoogLeNet, Vgg19, ResNet50, and DenseNet201 architectures. The Guava fruit dataset was classified by both k-fold-stratified and an 80:20 split. All experimental studies were evaluated using six different performance metrics. The best result was achieved with the DenseNet201 architecture in the proposed method. The performance results for the DenseNet201 architecture in terms of accuracy, sensitivity, specificity, F1-score, MCC, and kappa are as follows: accuracy - 0.9658, sensitivity - 0.9677, specificity - 0.9954, F1-score - 0.9681, MCC - 0.9640, and Kappa - 0.8268.

 For the rapid and precise advancement of agriculture, artificial intelligence applications are of significant importance. Processes such as disease detection in the agricultural field, identification of soil types, and classification of plants and fruits are currently performed manually. Artificial intelligence enables the automation of these processes, leading to cost reduction and the minimization of human errors. In this study, a system for classifying the species of Guava fruit has been proposed. The proposed system is designed using four pre-trained convolutional neural networks. The convolutional neural networks used are GoogLeNet, Vgg19, ResNet50, and DenseNet201 architectures. The Guava fruit dataset was classified by both k-fold-stratified and an 80:20 split. All experimental studies were evaluated using six different performance metrics. The best result was achieved with the DenseNet201 architecture in the proposed method. The performance results for the DenseNet201 architecture in terms of accuracy, sensitivity, specificity, F1-score, MCC, and kappa are as follows: accuracy - 0.9658, sensitivity - 0.9677, specificity - 0.9954, F1-score - 0.9681, MCC - 0.9640, and Kappa - 0.8268.

 Tarımın hızlı ve hassas bir şekilde ilerlemesi için yapay zeka uygulamaları büyük önem taşımaktadır. Tarım alanında hastalık tespiti, toprak türlerinin belirlenmesi ve bitki ile meyvelerin sınıflandırılması gibi süreçler şu anda manuel olarak gerçekleştirilmektedir. Yapay zeka, bu süreçlerin otomasyonunu sağlayarak maliyetleri düşürmekte ve insan hatalarını en aza indirmektedir. Bu çalışmada, Guava meyvesinin türlerini sınıflandıran bir sistem önerilmiştir. Önerilen sistem, dört ön eğitimli evrişimli sinir ağı kullanılarak tasarlanmıştır. Kullanılan evrişimli sinir ağları GoogLeNet, Vgg19, ResNet50 ve DenseNet201 mimarileridir. Guava meyvesi veri seti, hem k-katmanlı stratifiye hem de 80:20 bölme ile sınıflandırılmıştır. Tüm deneysel çalışmalar altı farklı performans metriği kullanılarak değerlendirilmiştir. Önerilen yöntemle en iyi sonuç DenseNet201 mimarisi ile elde edilmiştir. DenseNet201 mimarisinin performans sonuçları şu şekildedir: doğruluk - 0.9658, hassasiyet - 0.9677, özgüllük - 0.9954, F1-puanı - 0.9681, MCC - 0.9640 ve Kappa - 0.8268.

Makale detayları

Guava fruit classification system design with convolutional neural networks

Yazarlar:

Buket Toptaş | Sara Altun Güven

Yayıncı:

Gumushane University

Ana Başlıklar:

Görüntü İşleme | Derin Öğrenme | Sınıflandırma algoritmaları

Dergi:

Gümüşhane Üniversitesi Fen Bilimleri Dergisi Vol.14 Issue 4, pp.1247-1258

Belge Tipi:

Makale

Yayın Tarihi:

12/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001333160

pISSN:

2146-538X

Convolutional neural network

Classification

Guava classificationEvrişimsel sinir ağlar

Sınıflandırma

Guava sınıflandırma

Sayı

Makale detayları

Guava fruit classification system design with convolutional neural networks

Yazarlar: Buket Toptaş | Sara Altun Güven

Yayıncı: Gumushane University

Ana Başlıklar: Görüntü İşleme | Derin Öğrenme | Sınıflandırma algoritmaları

Dergi: Gümüşhane Üniversitesi Fen Bilimleri Dergisi Vol.14 Issue 4, pp.1247-1258

Belge Tipi: Makale

Yayın Tarihi: 12/2024

Belge Dili: İngilizce

Document ID (Org No.): 2001333160

pISSN: 2146-538X

Convolutional neural network

Classification

Guava classificationEvrişimsel sinir ağlar

Sınıflandırma

Guava sınıflandırma

Sayı

Yazarlar:

Buket Toptaş | Sara Altun Güven

Yayıncı:

Gumushane University

Ana Başlıklar:

Görüntü İşleme | Derin Öğrenme | Sınıflandırma algoritmaları

Dergi:

Gümüşhane Üniversitesi Fen Bilimleri Dergisi Vol.14 Issue 4, pp.1247-1258

Belge Tipi:

Makale

Yayın Tarihi:

12/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001333160

pISSN:

2146-538X