Research Article

Classification of Walnut Leaf Images Using a Hybrid CNN-Based Deep Learning Approach

Volume: 15 Number: 1 March 30, 2026
EN TR

Classification of Walnut Leaf Images Using a Hybrid CNN-Based Deep Learning Approach

Abstract

Walnut is a widely cultivated crop with various types and qualities, offering significant health benefits. However, its long production cycle and high cultivation costs necessitate the selection of appropriate varieties for specific ecological conditions. Due to morphological and color similarities, differentiating walnut varieties remains challenging, even for experts. Existing studies on walnut classification are limited and mostly confined to laboratory-based experiments. In this study, a novel hybrid computer-based approach is proposed for the automatic classification of walnut varieties using leaf images. A dataset consisting of 1,751 images from 18 different walnut varieties was collected from the Atatürk Horticultural Central Research Institute in Yalova, Turkey. The proposed model integrates deep features extracted from lightweight Convolutional Neural Network (CNN) architectures, namely SqueezeNet and MobileNetV2, with textural features obtained through the Gray-Level Co-occurrence Matrix (GLCM). The most significant features were selected using the Chi-square test, and classification was performed with Support Vector Machines (SVM). Experimental results demonstrate that the proposed hybrid model achieved an accuracy of 84.75% in classifying walnut varieties. These findings indicate that the proposed method can provide a reliable, fast, and cost-effective solution for walnut variety identification, with potential benefits for agricultural standardization and precision farming practices.

Keywords

References

  1. K. Kulkarni, Z. Zhang, L. Chang, J. Yang, P. C. A. da Fonseca, and D. Barford, “Building a pseudo-atomic model of the anaphase-promoting complex,” Acta Crystallogr. Sect. D Biol. Crystallogr., vol. 69, no. 11, pp. 2236–2243, 2013.
  2. T. Karadeniz and E. Güler, “Cumhuriyetin İlk Yıllarından Günümüze Ceviz Yetiştiriciliği,” Bahçe, 2017.
  3. T. Karadeniz, “Ordu Yöresinde yetiştirilen ceviz genotiplerinin (Juglans regia L.) seleksiyonu,” Ordu Üniversitesi Bilim ve Teknol. Derg., vol. 1, no. 1, pp. 65–74, 2011.
  4. F. Doğan and İ. Türkoğlu, “Derin öğrenme algoritmalarının yaprak sınıflandırma başarımlarının karşılaştırılması,” Sak. Univ. J. Comput. Inf. Sci., vol. 1, no. 1, pp. 10–21, 2018.
  5. S. Solak and U. Altınışık, “Görüntü işleme teknikleri ve kümeleme yöntemleri kullanılarak fındık meyvesinin tespit ve sınıflandırılması,” Sak. Univ. J. Sci., vol. 22, no. 1, pp. 56–65, 2018.
  6. J. Liu, S. Yang, Y. Cheng, and Z. Song, “Plant leaf classification based on deep learning,” in 2018 Chinese Automation Congress (CAC), 2018, pp. 3165–3169.
  7. D. K. Nkemelu, D. Omeiza, and N. Lubalo, “Deep convolutional neural network for plant seedlings classification,” arXiv Prepr. arXiv1811.08404, 2018.
  8. S. Khalesi, A. Mahmoudi, A. Hosainpour, and A. Alipour, “Detection of walnut varieties using impact acoustics and artificial neural networks (ANNs),” Mod. Appl. Sci., vol. 6, no. 1, p. 43, 2012.

Details

Primary Language

English

Subjects

Precision Agriculture Technologies

Journal Section

Research Article

Publication Date

March 30, 2026

Submission Date

October 1, 2025

Acceptance Date

March 13, 2026

Published in Issue

Year 2026 Volume: 15 Number: 1

APA
Karadeniz, A. T., Başaran, E., & Çelik, Y. (2026). Classification of Walnut Leaf Images Using a Hybrid CNN-Based Deep Learning Approach. Türk Doğa Ve Fen Dergisi, 15(1), 192-201. https://doi.org/10.46810/tdfd.1794846
AMA
1.Karadeniz AT, Başaran E, Çelik Y. Classification of Walnut Leaf Images Using a Hybrid CNN-Based Deep Learning Approach. TJNS. 2026;15(1):192-201. doi:10.46810/tdfd.1794846
Chicago
Karadeniz, Alper Talha, Erdal Başaran, and Yüksel Çelik. 2026. “Classification of Walnut Leaf Images Using a Hybrid CNN-Based Deep Learning Approach”. Türk Doğa Ve Fen Dergisi 15 (1): 192-201. https://doi.org/10.46810/tdfd.1794846.
EndNote
Karadeniz AT, Başaran E, Çelik Y (March 1, 2026) Classification of Walnut Leaf Images Using a Hybrid CNN-Based Deep Learning Approach. Türk Doğa ve Fen Dergisi 15 1 192–201.
IEEE
[1]A. T. Karadeniz, E. Başaran, and Y. Çelik, “Classification of Walnut Leaf Images Using a Hybrid CNN-Based Deep Learning Approach”, TJNS, vol. 15, no. 1, pp. 192–201, Mar. 2026, doi: 10.46810/tdfd.1794846.
ISNAD
Karadeniz, Alper Talha - Başaran, Erdal - Çelik, Yüksel. “Classification of Walnut Leaf Images Using a Hybrid CNN-Based Deep Learning Approach”. Türk Doğa ve Fen Dergisi 15/1 (March 1, 2026): 192-201. https://doi.org/10.46810/tdfd.1794846.
JAMA
1.Karadeniz AT, Başaran E, Çelik Y. Classification of Walnut Leaf Images Using a Hybrid CNN-Based Deep Learning Approach. TJNS. 2026;15:192–201.
MLA
Karadeniz, Alper Talha, et al. “Classification of Walnut Leaf Images Using a Hybrid CNN-Based Deep Learning Approach”. Türk Doğa Ve Fen Dergisi, vol. 15, no. 1, Mar. 2026, pp. 192-01, doi:10.46810/tdfd.1794846.
Vancouver
1.Alper Talha Karadeniz, Erdal Başaran, Yüksel Çelik. Classification of Walnut Leaf Images Using a Hybrid CNN-Based Deep Learning Approach. TJNS. 2026 Mar. 1;15(1):192-201. doi:10.46810/tdfd.1794846

This work is licensed under the Creative Commons Attribution-Non-Commercial-Non-Derivable 4.0 International License.