Plants

Research

21 pages, 9194 KiB

Open AccessArticle

An Optimization Method of Deep Transfer Learning for Vegetation Segmentation under Rainy and Dry Season Differences in a Dry Thermal Valley

by Yayong Chen, Beibei Zhou, Dapeng Ye, Lei Cui, Lei Feng and Xiaojie Han

Plants 2023, 12(19), 3383; https://doi.org/10.3390/plants12193383 - 25 Sep 2023

Viewed by 787

Abstract

Deep learning networks might require re-training for different datasets, consuming significant manual labeling and training time. Transfer learning uses little new data and training time to enable pre-trained network segmentation in relevant scenarios (e.g., different vegetation images in rainy and dry seasons); however, [...] Read more.

Deep learning networks might require re-training for different datasets, consuming significant manual labeling and training time. Transfer learning uses little new data and training time to enable pre-trained network segmentation in relevant scenarios (e.g., different vegetation images in rainy and dry seasons); however, existing transfer learning methods lack systematicity and controllability. So, an MTPI method (Maximum Transfer Potential Index method) was proposed to find the optimal conditions in data and feature quantity for transfer learning (MTPI conditions) in this study. The four pre-trained deep networks (Seg-Net (Semantic Segmentation Networks), FCN (Fully Convolutional Networks), Mobile net v2, and Res-Net 50 (Residual Network)) using the rainy season dataset showed that Res-Net 50 had the best accuracy with 93.58% and an WIoU (weight Intersection over Union) of 88.14%, most worthy to transfer training in vegetation segmentation. By obtaining each layer’s TPI performance (Transfer Potential Index) of the pre-trained Res-Net 50, the MTPI method results show that the 1000-TDS and 37-TP were estimated as the best training speed with the smallest dataset and a small error risk. The MTPI transfer learning results show 91.56% accuracy and 84.86% WIoU with 90% new dataset reduction and 90% iteration reduction, which is informative for deep networks in segmentation tasks between complex vegetation scenes. Full article

(This article belongs to the Special Issue Deep Learning in Plant Sciences)

► Show Figures

Figure 1

22 pages, 15928 KiB

Open AccessArticle

An Interpretable High-Accuracy Method for Rice Disease Detection Based on Multisource Data and Transfer Learning

by Jiaqi Li, Xinyan Zhao, Hening Xu, Liman Zhang, Boyu Xie, Jin Yan, Longchuang Zhang, Dongchen Fan and Lin Li

Plants 2023, 12(18), 3273; https://doi.org/10.3390/plants12183273 - 15 Sep 2023

Cited by 2 | Viewed by 975

Abstract

With the evolution of modern agriculture and precision farming, the efficient and accurate detection of crop diseases has emerged as a pivotal research focus. In this study, an interpretative high-precision rice disease detection method, integrating multisource data and transfer learning, is introduced. This [...] Read more.

With the evolution of modern agriculture and precision farming, the efficient and accurate detection of crop diseases has emerged as a pivotal research focus. In this study, an interpretative high-precision rice disease detection method, integrating multisource data and transfer learning, is introduced. This approach harnesses diverse data types, including imagery, climatic conditions, and soil attributes, facilitating enriched information extraction and enhanced detection accuracy. The incorporation of transfer learning bestows the model with robust generalization capabilities, enabling rapid adaptation to varying agricultural environments. Moreover, the interpretability of the model ensures transparency in its decision-making processes, garnering trust for real-world applications. Experimental outcomes demonstrate superior performance of the proposed method on multiple datasets when juxtaposed against advanced deep learning models and traditional machine learning techniques. Collectively, this research offers a novel perspective and toolkit for agricultural disease detection, laying a solid foundation for the future advancement of agriculture. Full article

(This article belongs to the Special Issue Deep Learning in Plant Sciences)

► Show Figures

Figure 1

19 pages, 30196 KiB

Open AccessArticle

High-Accuracy Maize Disease Detection Based on Attention Generative Adversarial Network and Few-Shot Learning

by Yihong Song, Haoyan Zhang, Jiaqi Li, Ran Ye, Xincan Zhou, Bowen Dong, Dongchen Fan and Lin Li

Plants 2023, 12(17), 3105; https://doi.org/10.3390/plants12173105 - 29 Aug 2023

Cited by 2 | Viewed by 1145

Abstract

This study addresses the problem of maize disease detection in agricultural production, proposing a high-accuracy detection method based on Attention Generative Adversarial Network (Attention-GAN) and few-shot learning. The method introduces an attention mechanism, enabling the model to focus more on the significant parts [...] Read more.

This study addresses the problem of maize disease detection in agricultural production, proposing a high-accuracy detection method based on Attention Generative Adversarial Network (Attention-GAN) and few-shot learning. The method introduces an attention mechanism, enabling the model to focus more on the significant parts of the image, thereby enhancing model performance. Concurrently, data augmentation is performed through Generative Adversarial Network (GAN) to generate more training samples, overcoming the difficulties of few-shot learning. Experimental results demonstrate that this method surpasses other baseline models in accuracy, recall, and mean average precision (mAP), achieving 0.97, 0.92, and 0.95, respectively. These results validate the high accuracy and stability of the method in handling maize disease detection tasks. This research provides a new approach to solving the problem of few samples in practical applications and offers valuable references for subsequent research, contributing to the advancement of agricultural informatization and intelligence. Full article

(This article belongs to the Special Issue Deep Learning in Plant Sciences)

► Show Figures

Figure 1

21 pages, 11858 KiB

Open AccessArticle

Testing a Method Based on an Improved UNet and Skeleton Thinning Algorithm to Obtain Branch Phenotypes of Tall and Valuable Trees Using Abies beshanzuensis as the Research Sample

by Jiahui Shen, Lihong Zhang, Laibang Yang, Hao Xu, Sheng Chen, Jingyong Ji, Siqi Huang, Hao Liang, Chen Dong and Xiongwei Lou

Plants 2023, 12(13), 2444; https://doi.org/10.3390/plants12132444 - 25 Jun 2023

Viewed by 1097

Abstract

Sudden changes in the morphological characteristics of trees are closely related to plant health, and automated phenotypic measurements can help improve the efficiency of plant health monitoring, and thus aid in the conservation of old and valuable tress. The irregular distribution of branches [...] Read more.

Sudden changes in the morphological characteristics of trees are closely related to plant health, and automated phenotypic measurements can help improve the efficiency of plant health monitoring, and thus aid in the conservation of old and valuable tress. The irregular distribution of branches and the influence of the natural environment make it very difficult to monitor the status of branches in the field. In order to solve the problem of branch phenotype monitoring of tall and valuable plants in the field environment, this paper proposes an improved UNet model to achieve accurate extraction of trunk and branches. This paper also proposes an algorithm that can measure the branch length and inclination angle by using the main trunk and branches separated in the previous stage, finding the skeleton line of a single branch via digital image morphological processing and the Zhang–Suen thinning algorithm, obtaining the number of pixel points as the branch length, and then using Euclidean distance to fit a straight line to calculate the inclination angle of each branch. These were carried out in order to monitor the change in branch length and inclination angle and to determine whether plant branch breakage or external stress events had occurred. We evaluated the method on video images of Abies beshanzuensis, and the experimental results showed that the present algorithm has more excellent performance at 94.30% MIoU as compared with other target segmentation algorithms. The coefficient of determination (R²) is higher than 0.89 for the calculation of the branch length and inclination angle. In summary, the algorithm proposed in this paper can effectively segment the branches of tall plants and measure their length and inclination angle in a field environment, thus providing an effective method to monitor the health of valuable plants. Full article

(This article belongs to the Special Issue Deep Learning in Plant Sciences)

► Show Figures

Figure 1

17 pages, 3801 KiB

Open AccessArticle

MTDL-EPDCLD: A Multi-Task Deep-Learning-Based System for Enhanced Precision Detection and Diagnosis of Corn Leaf Diseases

by Dikang Dai, Peiwen Xia, Zeyang Zhu and Huilian Che

Plants 2023, 12(13), 2433; https://doi.org/10.3390/plants12132433 - 23 Jun 2023

Cited by 3 | Viewed by 1168

Abstract

Corn leaf diseases lead to significant losses in agricultural production, posing challenges to global food security. Accurate and timely detection and diagnosis are crucial for implementing effective control measures. In this research, a multi-task deep learning-based system for enhanced precision detection and diagnosis [...] Read more.

Corn leaf diseases lead to significant losses in agricultural production, posing challenges to global food security. Accurate and timely detection and diagnosis are crucial for implementing effective control measures. In this research, a multi-task deep learning-based system for enhanced precision detection and diagnosis of corn leaf diseases (MTDL-EPDCLD) is proposed to enhance the detection and diagnosis of corn leaf diseases, along with the development of a mobile application utilizing the Qt framework, which is a cross-platform software development framework. The system comprises Task 1 for rapid and accurate health status identification (RAHSI) and Task 2 for fine-grained disease classification with attention (FDCA). A shallow CNN-4 model with a spatial attention mechanism is developed for Task 1, achieving 98.73% accuracy in identifying healthy and diseased corn leaves. For Task 2, a customized MobileNetV3Large-Attention model is designed. It achieves a val_accuracy of 94.44%, and improvements of 4–8% in precision, recall, and F1 score from other mainstream deep learning models. Moreover, the model attains an area under the curve (AUC) of 0.9993, exhibiting an enhancement of 0.002–0.007 compared to other mainstream models. The MTDL-EPDCLD system provides an accurate and efficient tool for corn leaf disease detection and diagnosis, supporting informed decisions on disease management, increased crop yields, and improved food security. This research offers a promising solution for detecting and diagnosing corn leaf diseases, and its continued development and implementation may substantially impact agricultural practices and outcomes. Full article

(This article belongs to the Special Issue Deep Learning in Plant Sciences)

► Show Figures

Figure 1

28 pages, 10348 KiB

Open AccessArticle

Artificial Neural Network and Response Surface-Based Combined Approach to Optimize the Oil Content of Ocimum basilicum var. thyrsiflora (Thai Basil)

by Akankshya Sahu, Gayatree Nayak, Sanat Kumar Bhuyan, Abdul Akbar, Ruchi Bhuyan, Dattatreya Kar and Ananya Kuanar

Plants 2023, 12(9), 1776; https://doi.org/10.3390/plants12091776 - 26 Apr 2023

Viewed by 1052

Abstract

Ocimum basilicum var. thyrsiflora is valuable for its medicinal properties. The barriers to the commercialization of essential oil are the lack of requisite high oil-containing genotypes and variations in the quantity and quality of essential oils in different geographic areas. Thai basil’s essential [...] Read more.

Ocimum basilicum var. thyrsiflora is valuable for its medicinal properties. The barriers to the commercialization of essential oil are the lack of requisite high oil-containing genotypes and variations in the quantity and quality of essential oils in different geographic areas. Thai basil’s essential oil content is significantly influenced by soil and environmental factors. To optimize and predict the essential oil yield of Thai basil in various agroclimatic regions, the current study was conducted. The 93 datasets used to construct the model were collected from samples taken across 10 different agroclimatic regions of Odisha. Climate variables, soil parameters, and oil content were used to train the Artificial Neural Network (ANN) model. The outcome showed that a multilayer feed-forward neural network with an R squared value of 0.95 was the most suitable model. To understand how the variables interact and to determine the optimum value of each variable for the greatest response, the response surface curves were plotted. Garson’s algorithm was used to discover the influential predictors. Soil potassium content was found to have a very strong influence on responses, followed by maximum relative humidity and average rainfall, respectively. The study reveals that by adjusting the changeable parameters for high commercial significance, the ANN-based prediction model with the response surface methodology technique is a new and promising way to estimate the oil yield at a new site and maximize the essential oil yield at a particular region. To our knowledge, this is the first report on an ANN-based prediction model for Ocimum basilicum var. thyrsiflora. Full article

(This article belongs to the Special Issue Deep Learning in Plant Sciences)

► Show Figures

Figure 1

20 pages, 8769 KiB

Open AccessEditor’s ChoiceArticle

A Copy Paste and Semantic Segmentation-Based Approach for the Classification and Assessment of Significant Rice Diseases

by Zhiyong Li, Peng Chen, Luyu Shuai, Mantao Wang, Liang Zhang, Yuchao Wang and Jiong Mu

Plants 2022, 11(22), 3174; https://doi.org/10.3390/plants11223174 - 20 Nov 2022

Cited by 7 | Viewed by 2174

Abstract

The accurate segmentation of significant rice diseases and assessment of the degree of disease damage are the keys to their early diagnosis and intelligent monitoring and are the core of accurate pest control and information management. Deep learning applied to rice disease detection [...] Read more.

The accurate segmentation of significant rice diseases and assessment of the degree of disease damage are the keys to their early diagnosis and intelligent monitoring and are the core of accurate pest control and information management. Deep learning applied to rice disease detection and segmentation can significantly improve the accuracy of disease detection and identification but requires a large number of training samples to determine the optimal parameters of the model. This study proposed a lightweight network based on copy paste and semantic segmentation for accurate disease region segmentation and severity assessment. First, a dataset for rice significant disease segmentation was selected and collated based on 3 open-source datasets, containing 450 sample images belonging to 3 categories of rice leaf bacterial blight, blast and brown spot. Then, to increase the diversity of samples, a data augmentation method, rice leaf disease copy paste (RLDCP), was proposed that expanded the collected disease samples with the concept of copy and paste. The new RSegformer model was then trained by replacing the new backbone network with the lightweight semantic segmentation network Segformer, combining the attention mechanism and changing the upsampling operator, so that the model could better balance local and global information, speed up the training process and reduce the degree of overfitting of the network. The results show that RLDCP could effectively improve the accuracy and generalisation performance of the semantic segmentation model compared with traditional data augmentation methods and could improve the MIoU of the semantic segmentation model by about 5% with a dataset only twice the size. RSegformer can achieve an 85.38% MIoU at a model size of 14.36 M. The method proposed in this paper can quickly, easily and accurately identify disease occurrence areas, their species and the degree of disease damage, providing a reference for timely and effective rice disease control. Full article

(This article belongs to the Special Issue Deep Learning in Plant Sciences)

► Show Figures

Figure 1

22 pages, 3630 KiB

Open AccessArticle

Few-Shot Learning for Plant-Disease Recognition in the Frequency Domain

by Hong Lin, Rita Tse, Su-Kit Tang, Zhenping Qiang and Giovanni Pau

Plants 2022, 11(21), 2814; https://doi.org/10.3390/plants11212814 - 22 Oct 2022

Cited by 10 | Viewed by 1985

Abstract

Few-shot learning (FSL) is suitable for plant-disease recognition due to the shortage of data. However, the limitations of feature representation and the demanding generalization requirements are still pressing issues that need to be addressed. The recent studies reveal that the frequency representation contains [...] Read more.

Few-shot learning (FSL) is suitable for plant-disease recognition due to the shortage of data. However, the limitations of feature representation and the demanding generalization requirements are still pressing issues that need to be addressed. The recent studies reveal that the frequency representation contains rich patterns for image understanding. Given that most existing studies based on image classification have been conducted in the spatial domain, we introduce frequency representation into the FSL paradigm for plant-disease recognition. A discrete cosine transform module is designed for converting RGB color images to the frequency domain, and a learning-based frequency selection method is proposed to select informative frequencies. As a post-processing of feature vectors, a Gaussian-like calibration module is proposed to improve the generalization by aligning a skewed distribution with a Gaussian-like distribution. The two modules can be independent components ported to other networks. Extensive experiments are carried out to explore the configurations of the two modules. Our results show that the performance is much better in the frequency domain than in the spatial domain, and the Gaussian-like calibrator further improves the performance. The disease identification of the same plant and the cross-domain problem, which are critical to bring FSL to agricultural industry, are the research directions in the future. Full article

(This article belongs to the Special Issue Deep Learning in Plant Sciences)

► Show Figures

Figure 1

17 pages, 5701 KiB

Open AccessArticle

Automated Real-Time Identification of Medicinal Plants Species in Natural Environment Using Deep Learning Models—A Case Study from Borneo Region

by Owais A. Malik, Nazrul Ismail, Burhan R. Hussein and Umar Yahya

Plants 2022, 11(15), 1952; https://doi.org/10.3390/plants11151952 - 27 Jul 2022

Cited by 20 | Viewed by 4645

Abstract

The identification of plant species is fundamental for the effective study and management of biodiversity. In a manual identification process, different characteristics of plants are measured as identification keys which are examined sequentially and adaptively to identify plant species. However, the manual process [...] Read more.

The identification of plant species is fundamental for the effective study and management of biodiversity. In a manual identification process, different characteristics of plants are measured as identification keys which are examined sequentially and adaptively to identify plant species. However, the manual process is laborious and time-consuming. Recently, technological development has called for more efficient methods to meet species’ identification requirements, such as developing digital-image-processing and pattern-recognition techniques. Despite several existing studies, there are still challenges in automating the identification of plant species accurately. This study proposed designing and developing an automated real-time plant species identification system of medicinal plants found across the Borneo region. The system is composed of a computer vision system that is used for training and testing a deep learning model, a knowledge base that acts as a dynamic database for storing plant images, together with auxiliary data, and a front-end mobile application as a user interface to the identification and feedback system. For the plant species identification task, an EfficientNet-B1-based deep learning model was adapted and trained/tested on a combined public and private plant species dataset. The proposed model achieved 87% and 84% Top-1 accuracies on a test set for the private and public datasets, respectively, which is more than a 10% accuracy improvement compared to the baseline model. During real-time system testing on the actual samples, using our mobile application, the accuracy slightly dropped to 78.5% (Top-1) and 82.6% (Top-5), which may be related to training data and testing conditions variability. A unique feature of the study is the provision of crowdsourcing feedback and geo-mapping of the species in the Borneo region, with the help of the mobile application. Nevertheless, the proposed system showed a promising direction toward real-time plant species identification system. Full article

(This article belongs to the Special Issue Deep Learning in Plant Sciences)

► Show Figures

Figure 1

17 pages, 3278 KiB

Open AccessEditor’s ChoiceArticle

Deep Learning Diagnostics of Gray Leaf Spot in Maize under Mixed Disease Field Conditions

by Hamish A. Craze, Nelishia Pillay, Fourie Joubert and Dave K. Berger

Plants 2022, 11(15), 1942; https://doi.org/10.3390/plants11151942 - 26 Jul 2022

Cited by 7 | Viewed by 2375

Abstract

Maize yields worldwide are limited by foliar diseases that could be fungal, oomycete, bacterial, or viral in origin. Correct disease identification is critical for farmers to apply the correct control measures, such as fungicide sprays. Deep learning has the potential for automated disease [...] Read more.

Maize yields worldwide are limited by foliar diseases that could be fungal, oomycete, bacterial, or viral in origin. Correct disease identification is critical for farmers to apply the correct control measures, such as fungicide sprays. Deep learning has the potential for automated disease classification from images of leaf symptoms. We aimed to develop a classifier to identify gray leaf spot (GLS) disease of maize in field images where mixed diseases were present (18,656 images after augmentation). In this study, we compare deep learning models trained on mixed disease field images with and without background subtraction. Performance was compared with models trained on PlantVillage images with single diseases and uniform backgrounds. First, we developed a modified VGG16 network referred to as “GLS_net” to perform binary classification of GLS, which achieved a 73.4% accuracy. Second, we used MaskRCNN to dynamically segment leaves from backgrounds in combination with GLS_net to identify GLS, resulting in a 72.6% accuracy. Models trained on PlantVillage images were 94.1% accurate at GLS classification with the PlantVillage testing set but performed poorly with the field image dataset (55.1% accuracy). In contrast, the GLS_net model was 78% accurate on the PlantVillage testing set. We conclude that deep learning models trained with realistic mixed disease field data obtain superior degrees of generalizability and external validity when compared to models trained using idealized datasets. Full article

(This article belongs to the Special Issue Deep Learning in Plant Sciences)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Deep Learning in Plant Sciences

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (10 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI