
Rice Leaf Nutrient Deficiency Detection System based on Leaf Image using Deep Learning
Rice Leaf Nutrient Deficiency Detection System based on Leaf Image using Deep Learning
IEEE BASE PAPER TITLE:
Rice Leaf Nutrient Deficiency Classification System Using CAR-Capsule Network
IEEE BASE PAPER ABSTRACT:
Rice, a worldwide grown grain, frequently suffers production issues caused by nutrient imbalances, particularly potassium, nitrogen, and phosphorus. Identifying nutrient deficiencies in rice plants proves challenging due to variations in leaf colour and form. Visually classifying nutritional shortages based on leaf characteristics, such as colour and shape, becomes a complex and resource-intensive task. The intricacies involved make the identification of nutrient deficiencies in rice both time-consuming and expensive. This study presents a computer vision-based deep learning system termed CAR-CapsNet, an upgraded capsule network (CapsNet) that uses contextual attention routing (CAR) to classify rice crop nutrient deficiencies. CAR-Capsnet’s innovative use of contextual attention routing significantly enhances the model’s ability to navigate and interpret complex visual features and patterns, leading to improved classification accuracy compared to previous routing methods. The training and evaluation datasets are sourced from Kaggle, a freely accessible data platform. The dataset consists of 1,155 images of rice leaves, divided into three distinct classes representing deficiencies in nitrogen, phosphorus, and potassium. The dataset undergoes pre-processing using a Wiener filter and adaptive Otsu segmentation. The proposed model was evaluated against CNN and the original CapsNet. CAR-CapsNet outperformed both baseline models in the experiments. CAR-CapsNet classifies rice crop nutrient deficiencies with 97.1% accuracy. Additionally, the model exhibits an impressive recall of 96.9%, an exceptional Kappa score of 95.4%, and an F1-score of 96.9%, highlighting its overall effectiveness. The classifier’s performance was compared with three prior approaches, including Random Forest Regression with an accuracy of 81.82%, SVM with C-means clustering at 92%, and VGG19 at 91.8%. The results demonstrate that the proposed method more effectively classifies rice crop nutrient deficiencies than these methods.
PROJECT OUTPUT VIDEO:
ALGORITHM / MODEL USED:
Fine-tuned ResNet50 model.
OUR PROPOSED ABSTRACT:
Nutrient deficiencies in rice plants, such as Nitrogen (N), Phosphorus (P), and Potassium (K), significantly affect plant growth, productivity, and overall yield, posing significant challenges to agricultural productivity. Early identification and diagnosis of these deficiencies are crucial for timely intervention and improved crop management.
The proposed “Rice Leaf Nutrient Deficiency Detection System based on Leaf Image using Deep Learning” is an advanced system designed to identify and diagnose nutrient deficiencies in rice plants through image-based analysis. The system leverages the power of deep learning and is developed using MATLAB as the implementation platform. A fine-tuned ResNet50 model serves as the backbone of the detection algorithm, enabling precise classification of nutrient deficiencies.
The existing methods for identifying these deficiencies often rely on manual inspection, which is time-consuming and prone to errors. This work proposes an automated solution using deep learning techniques to accurately classify nutrient deficiencies in rice plants. The methodology involves preprocessing rice plant images through resizing and augmentation, followed by training a fine-tuned ResNet50 model to extract deep features specific to nutrient deficiencies.
The dataset employed for this project comprises 706 high-resolution images, categorized into three nutrient deficiency classes: Nitrogen (N) Deficiency with 240 images, Phosphorus (P) Deficiency with 233 images, and Potassium (K) Deficiency with 233 images. The fine-tuned ResNet50 model is trained to extract discriminative features and classify the images into the respective categories with high accuracy.
Performance evaluation of the system is conducted using standard metrics, including accuracy, precision, sensitivity, and F1-score, ensuring a comprehensive assessment of its effectiveness. This system offers a cost-effective and efficient tool for farmers and agricultural professionals, enabling early detection of nutrient deficiencies, thereby promoting timely intervention and improved crop yield.
OJECTIVES:
- To create a robust and efficient system using deep learning techniques that can accurately identify and classify nutrient deficiencies in rice plants from images.
- To implement effective preprocessing steps, including image resizing and augmentation, and fine-tuned pre-trained ResNet50 model to improve the accuracy and generalization capabilities of the deficiency classification.
SYSTEM REQUIREMENTS:
HARDWARE REQUIREMENTS:
- System : Pentium i3 Processor.
- Hard Disk : 500 GB.
- Monitor : 15’’ LED.
- Input Devices : Keyboard, Mouse.
- Ram : 8 GB.
SOFTWARE REQUIREMENTS:
- Operating system : Windows 10 / 11.
- Coding Language : MATLAB
- Tool : MATLABR2024B
REFERENCE:
AMUDHA AND K. BRINDHA, “Rice Leaf Nutrient Deficiency Classification System Using CAR-Capsule Network”, in IEEE Access, vol. 12, pp. 169518-169532, 2024.