Open Access

ARTICLE

Weed Classification Using Particle Swarm Optimization and Deep Learning Models

M. Manikandakumar^1,*, P. Karthikeyan²

1 Department of Computer Science and Engineering, Thiagarajar College of Engineering, Tamil Nadu, India
2 Department of Information Technology, Thiagarajar College of Engineering, Tamil Nadu, India

* Corresponding Author: M. Manikandakumar. Email:

Computer Systems Science and Engineering 2023, 44(1), 913-927. https://doi.org/10.32604/csse.2023.025434

Received 23 November 2021; Accepted 10 January 2022; Issue published 01 June 2022

Abstract

Weed is a plant that grows along with nearly all field crops, including rice, wheat, cotton, millets and sugar cane, affecting crop yield and quality. Classification and accurate identification of all types of weeds is a challenging task for farmers in earlier stage of crop growth because of similarity. To address this issue, an efficient weed classification model is proposed with the Deep Convolutional Neural Network (CNN) that implements automatic feature extraction and performs complex feature learning for image classification. Throughout this work, weed images were trained using the proposed CNN model with evolutionary computing approach to classify the weeds based on the two publicly available weed datasets. The Tamil Nadu Agricultural University (TNAU) dataset used as a first dataset that consists of 40 classes of weed images and the other dataset is from Indian Council of Agriculture Research – Directorate of Weed Research (ICAR-DWR) which contains 50 classes of weed images. An effective Particle Swarm Optimization (PSO) technique is applied in the proposed CNN to automatically evolve and improve its classification accuracy. The proposed model was evaluated and compared with pre-trained transfer learning models such as GoogLeNet, AlexNet, Residual neural Network (ResNet) and Visual Geometry Group Network (VGGNet) for weed classification. This work shows that the performance of the PSO assisted proposed CNN model is significantly improved the success rate by 98.58% for TNAU and 97.79% for ICAR-DWR weed datasets.

---

Keywords

---