Classification for Tomato Disease with Imbalanced Samples Based on TD-MobileNetV2

Abstract Background Tomato plant growth is frequently hampered by a high susceptibility to pests and diseases. Traditional chemical control causes a serious impact on both the environment and human health. Therefore, seeking environment-friendly and cost-effective green methods in agricultural production becomes crucial nowadays. Plant Growth Promoting Rhizobacteria (PGPR) can promote plant growth through biological activity. Their use is considered to be a promising sustainable approach for crop growth. Moreover, a vast number of biosynthetic gene clusters (BGCs) for secondary metabolite production are being revealed in PGPR, which helps to find potential anti-microbial activities for tomato disease control. Results We isolated 181 Bacillus-like strains from healthy tomato, rhizosphere soil, and tomato tissues. In vitro antagonistic assays revealed that 34 Bacillus strains have antimicrobial activity against Erwinia carotovora, Pseudomonas syringae; Rhizoctonia solani; Botrytis cinerea; Verticillium dahliae and Phytophthora infestans. The genomes of 10 Bacillus and Paenibacillus strains with good antagonistic activity were sequenced. Via genome mining approaches, we identified 120 BGCs encoding NRPs, PKs-NRPs, PKs, terpenes and bacteriocins, including known compounds such as fengycin, surfactin, bacillibactin, subtilin, etc. In addition, several novel BGCs were identified. We discovered that the NRPs and PKs-NRPs BGCs in Bacillus species are encoding highly conserved known compounds as well as various novel variants. Conclusions This study highlights the great number of varieties of BGCs in Bacillus strains. These findings pave the road for future usage of Bacillus strains as biocontrol agents for tomato disease control and are a resource arsenal for novel antimicrobial discovery.

Download Full-text

Influence of tomato genotype to phenolic compounds content and antioxidant activity as reaction to early blight

Genetika ◽

10.2298/gensr1503099m ◽

2015 ◽

Vol 47 (3) ◽

pp. 1099-1110 ◽

Cited By ~ 1

Author(s):

Sladjana Medic-Pap ◽

Dejan Prvulovic ◽

Ana Takac ◽

Slobodan Vlajic ◽

Dario Danojevic ◽

...

Keyword(s):

Antioxidant Activity ◽

Early Blight ◽

Natural Infection ◽

Alternaria Solani ◽

Vegetable Crops ◽

Disease Occurrence ◽

Two Factors ◽

Biochemical Level ◽

Tomato Genotype ◽

Tomato Disease

Early blight is one of the most common and destructive tomato disease and it is caused by the fungus Alternaria solani. The aim of this paper was to screen the reaction of ten tomato genotypes (collection of the Institute of Field and Vegetable Crops) against natural infection of early blight. Tested genotypes showed significant differences in the disease occurrence on leaves but not on fruits. However, at the biochemical level, total phenolics (TP), tannins (TT), flavonoids (TF) and antioxidant activity in tomato fruits was significantly affected by genotype, disease occurrence and interaction of these two factors. According to obtained results, content of these secondary metabolites could be used as a one of the parameters in the evaluation of tomato resistance to EB.

Download Full-text

Generation and Transformation Invariant Learning for Tomato Disease Classification

10.1109/prml52754.2021.9520693 ◽

2021 ◽

Author(s):

Getinet Yilma ◽

Kumie Gedamu ◽

Maregu Assefa ◽

Ariyo Oluwasanmi ◽

Zhiguang Qin

Keyword(s):

Disease Classification ◽

Tomato Disease

Download Full-text

ROS-based Robotic System for Tomato Disease and Ripeness Classification using Convolutional Neural Networks

10.1109/iemcon53756.2021.9623183 ◽

2021 ◽

Author(s):

Zubaidah Al-Mashhadani ◽

Balasubramaniyan Chandrasekaran

Keyword(s):

Neural Networks ◽

Convolutional Neural Networks ◽

Robotic System ◽

Tomato Disease

Download Full-text

Deep Learning-Based Object Detection Improvement for Tomato Disease

IEEE Access ◽

10.1109/access.2020.2982456 ◽

2020 ◽

Vol 8 ◽

pp. 56607-56614 ◽

Cited By ~ 3

Author(s):

Yang Zhang ◽

Chenglong Song ◽

Dongwen Zhang

Keyword(s):

Deep Learning ◽

Object Detection ◽

Tomato Disease

Download Full-text

Identification of Tomato Disease Types and Detection of Infected Areas Based on Deep Convolutional Neural Networks and Object Detection Techniques

Computational Intelligence and Neuroscience ◽

10.1155/2019/9142753 ◽

2019 ◽

Vol 2019 ◽

pp. 1-15 ◽

Cited By ~ 6

Author(s):

Qimei Wang ◽

Feng Qi ◽

Minghe Sun ◽

Jianhua Qu ◽

Jie Xue

Keyword(s):

Neural Networks ◽

Object Detection ◽

Convolutional Neural Networks ◽

Detection Methods ◽

Disease Detection ◽

Deep Convolutional Neural Networks ◽

Detection Techniques ◽

Tomato Diseases ◽

Validation Set ◽

Tomato Disease

This study develops tomato disease detection methods based on deep convolutional neural networks and object detection models. Two different models, Faster R-CNN and Mask R-CNN, are used in these methods, where Faster R-CNN is used to identify the types of tomato diseases and Mask R-CNN is used to detect and segment the locations and shapes of the infected areas. To select the model that best fits the tomato disease detection task, four different deep convolutional neural networks are combined with the two object detection models. Data are collected from the Internet and the dataset is divided into a training set, a validation set, and a test set used in the experiments. The experimental results show that the proposed models can accurately and quickly identify the eleven tomato disease types and segment the locations and shapes of the infected areas.

Download Full-text