Related Experiment Video
Updated: Jun 10, 2025
13:19
Deep Neural Networks for Image-Based Dietary Assessment
Published on: March 13, 2021
9.0K
Fruit and vegetable leaf disease recognition based on a novel custom convolutional neural network and shallow
Syeda Aimal Fatima Naqvi1, Muhammad Attique Khan2, Ameer Hamza1
1Department of Computer Science, HITEC University, Taxila, Pakistan.
Frontiers in Plant Science
|October 15, 2024
Summary
This study introduces a deep learning framework for classifying apple and cucumber leaf diseases, achieving high accuracy. The novel approach enhances image analysis and optimizes feature selection for efficient and accurate plant disease identification.
Area of Science:
- Agricultural Science
- Computer Science
- Artificial Intelligence
Background:
- Accurate diagnosis of fruit and vegetable plant diseases is crucial for crop yield and quality.
- Manual disease identification is challenging due to visual similarities, time constraints, and the need for expert knowledge.
- Existing methods often struggle with subtle disease indicators and require significant expert input.
Purpose of the Study:
- To develop an automated deep learning framework for classifying apple and cucumber leaf diseases.
- To address the limitations of manual disease identification, including time consumption and subjectivity.
- To improve the accuracy and efficiency of plant disease detection in agriculture.
Main Methods:
- A hybrid contrast enhancement technique using Bi-LSTM and Haze reduction was employed.
- Two custom deep learning models, Bottleneck Residual with Self-Attention (BRwSA) and Inverted Bottleneck Residual with Self-Attention (IBRwSA), were developed and trained.
- Feature extraction, fusion, and optimization using an improved human learning optimization algorithm, followed by classification with a shallow wide neural network (SWNN).
- Explainable AI (LIME) was used for model interpretability.
Main Results:
- The proposed framework achieved high classification accuracies of 94.8% for apple and 94.9% for cucumber leaf datasets.
- The hybrid enhancement and custom attention-based models effectively highlighted diseased plant areas.
- The optimization algorithm successfully reduced testing time while improving classification performance.
- Explainable AI provided insights into the decision-making process of the classification models.
Conclusions:
- The developed deep learning framework offers a robust and accurate solution for automated plant disease classification.
- The integration of attention mechanisms and optimization algorithms enhances the performance of leaf disease identification systems.
- The approach demonstrates significant potential for practical application in precision agriculture, aiding farmers in early disease detection.
Related Concept Videos
02:16Light Acquisition
8.4K
In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.
8.4K
02:35Key Elements for Plant Nutrition
18.7K
Like all living organisms, plants require organic and inorganic nutrients to survive, reproduce, grow and maintain homeostasis. To identify nutrients that are essential for plant functioning, researchers have leveraged a technique called hydroponics. In hydroponic culture systems, plants are grown—without soil—in water-based solutions containing nutrients. At least 17 nutrients have been identified as essential elements required by plants. Plants acquire these elements from the...
18.7K