An Improved Approach to Detection of Rice Leaf Disease with GAN-Based Data Augmentation Pipeline

Haruna, Yunusa; Qin, Shiyin; Kiki, Mesmin J. Mbyamm

doi:10.2139/ssrn.4135061

Cited by 2 publications

(1 citation statement)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The improved scheme corresponding to the algorithm detection process is shown in Figure 4. Reference (Multimedia, Agriculture and Remote sensing) Method description (Haruna et al, 2022) To improve the accuracy of deep learning models for identifying rice leaf disease, we built a GAN-based data augmentation pipeline with the state-of-the-art StyleGAN2-ADA and the variance of Laplace filter to generate high-quality synthetic rice leaf disease images. (Bhakta et al, 2022) Using state-of-the-art Generative Adversarial Network (GAN) technology, we can simulate thermal images of a rice plant with bacterial leaf blight.…”

Section: Deep Learning-based Object Detection Algorithm Improvementmentioning

confidence: 99%

AI-based object detection latest trends in remote sensing, multimedia and agriculture applications

Nawaz

Bhatti

et al. 2022

Front. Plant Sci.

View full text Add to dashboard Cite

Object detection is a vital research direction in machine vision and deep learning. The object detection technique based on deep understanding has achieved tremendous progress in feature extraction, image representation, classification, and recognition in recent years, due to this rapid growth of deep learning theory and technology. Scholars have proposed a series of methods for the object detection algorithm as well as improvements in data processing, network structure, loss function, and so on. In this paper, we introduce the characteristics of standard datasets and critical parameters of performance index evaluation, as well as the network structure and implementation methods of two-stage, single-stage, and other improved algorithms that are compared and analyzed. The latest improvement ideas of typical object detection algorithms based on deep learning are discussed and reached, from data enhancement, a priori box selection, network model construction, prediction box selection, and loss calculation. Finally, combined with the existing challenges, the future research direction of typical object detection algorithms is surveyed.

show abstract

Section: Deep Learning-based Object Detection Algorithm Improvementmentioning

confidence: 99%