A systematic review of deep learning techniques for apple leaf diseases classification and detection

Area of Science:

• Agricultural Science
• Computer Vision
• Machine Learning

Background:

• Apple production is vital for global food security and economies, but diseases significantly reduce yield and quality.
• Accurate and timely diagnosis of apple leaf diseases is challenging for farmers due to similar symptom presentation.
• Economic losses from apple diseases necessitate efficient diagnostic tools to support targeted crop management strategies.

Purpose of the Study:

• To systematically analyze and evaluate existing datasets, deep learning (DL) methods, and frameworks for apple leaf disease detection and classification.
• To identify the latest developments, prevalent approaches, and research gaps in automated apple disease identification.
• To provide insights into the effectiveness of computer vision applications in addressing agricultural challenges in apple cultivation.

Main Methods:

• Conducted a systematic literature review of 45 articles published between 2016 and 2024.
• Focused on research concerning datasets, deep learning algorithms, and frameworks applied to apple leaf disease detection.
• Evaluated the performance and applicability of various computer vision techniques in agricultural diagnostics.

Main Results:

• Deep learning models demonstrate high accuracy in detecting and classifying various apple leaf diseases from images.
• The review highlights a growing trend in utilizing convolutional neural networks (CNNs) and transfer learning for improved performance.
• Identified key datasets and frameworks that are foundational for developing robust automated disease identification systems.

Conclusions:

• Computer vision, particularly deep learning, offers a powerful and accurate solution for diagnosing apple leaf diseases.
• Continued research is needed to address challenges related to dataset diversity, real-world deployment, and model interpretability.
• Automated systems can significantly aid farmers in minimizing yield loss and enhancing the economic viability of apple farming.