DeepLeaf: An Intelligent System for Plant Recognition Using Convolutional Neural Networks
- Version
- Download 9
- File Size 554.58 KB
- File Count 1
- Create Date 16 May 2025
- Last Updated 16 May 2025
DeepLeaf: An Intelligent System for Plant Recognition Using Convolutional Neural Networks
Authors:
Mayank Vaibhav1, Harshit jaiswal2, Srijan Talukdar3, Prof. Jayeeta Ghosh4
1UG Student, Dept. of CSE, JIS College of Engineering, Kalyani, Nadia, WB, India.
2 UG Student, Dept. of CSE, JIS College of Engineering Kalyani, Nadia, WB, India.
3UG Student, Dept. of CSE, JIS College of Engineering Kalyani, Nadia, WB, India.
4 Asst. Professor, Dept. of CSE, JIS College of Engineering Kalyani, WB, India.
Abstract - The identification of plant species is a critical task in various fields such as agriculture, environmental monitoring, and biodiversity conservation. Traditional plant identification methods are often manual, time-consuming, and require specialized expertise. This project presents a machine learning-based solution that automates the process of plant recognition through the use of Convolutional Neural Networks (CNNs). A custom CNN architecture was developed and trained on a dataset of plant images, where images were preprocessed through resizing and normalization to standard dimensions, ensuring consistent input to the model. The dataset was divided into training and testing sets to evaluate model performance. The CNN model, consisting of multiple convolutional and pooling layers followed by dense layers, was optimized using categorical cross-entropy loss and the Adam optimizer. After training, the model demonstrated strong classification accuracy on the testing set, highlighting the capability of CNNs in learning complex patterns and visual features inherent to different plant species. The results validate the effectiveness of deep learning models in solving image classification tasks without requiring handcrafted feature extraction. Furthermore, the model was saved for future deployment or integration into real-time applications. The study suggests that with more extensive datasets and additional techniques such as data augmentation and transfer learning, the performance can be further enhanced. This work provides a foundational approach toward developing intelligent, automated plant identification systems that can assist researchers, farmers, and conservationists alike.
Key Words: Plant Identification, Convolutional Neural Networks (CNN), Image Classification, Machine Learning, Deep Learning, Plant Species Recognition, Automated Plant Detection
Download