• International Journal of Computer Science & Network Security
• /
• v.21 no.9
• /
• pp.51-62
• /
• 2021

Plant disease is one of the issues that can create losses in the production and economy of the agricultural sector. Early detection of this disease for finding solutions and treatments is still a challenge in the sustainable agriculture field. Currently, image processing techniques and machine learning methods have been applied to detect plant diseases successfully. However, the effectiveness of these methods still needs to be improved, especially in multiclass plant diseases classification. In this paper, a convolutional neural network with a batch normalization-based deep learning approach for classifying plant diseases is used to develop an automatic diagnostic assistance system for leaf diseases. The significance of using deep learning technology is to make the system be end-to-end, automatic, accurate, less expensive, and more convenient to detect plant diseases from their leaves. For evaluating the proposed model, an experiment is conducted on a public dataset contains 20654 images with 15 plant diseases. The experimental validation results on 20% of the dataset showed that the model is able to classify the 15 plant diseases labels with 96.4% testing accuracy and 0.168 testing loss. These results confirmed the applicability and effectiveness of the proposed model for the plant disease detection task.

• Journal of Microbiology and Biotechnology
• /
• v.19 no.10
• /
• pp.1250-1258
• /
• 2009

Bacillus spp., as a type of plant growth-promoting rhizobacteria (PGPR), were studied with regards promoting plant growth and inducing plant systemic resistance. The results of greenhouse experiments with tobacco plants demonstrated that treatment with the Bacillus spp. significantly enhanced the plant height and fresh weight, while clearly lowering the disease severity rating of the tobacco mosaic virus (TMV) at 28 days post-inoculation (dpi). The TMV accumulation in the young non-inoculated leaves was remarkably lower for all the plants treated with the Bacillus spp. An RT-PCR analysis of the signaling regulatory genes Coil and NPR1, and defense genes PR-1a and PR-1b, in the tobacco treated with the Bacillus spp. revealed an association with enhancing the systemic resistance of tobacco to TMV. A further analysis of two expansin genes that regulate plant cell growth, NtEXP2 and NtEXP6, also verified a concomitant growth promotion in the roots and leaves of the tobacco responding to the Bacillus spp.

• The Plant Pathology Journal
• /
• v.35 no.3
• /
• pp.208-218
• /
• 2019

Here, we reported a novel secreted protein elicitor PeBL2 from Brevibacillus laterosporus A60, which can induce hypersensitive response in tobacco (Nicotiana benthamiana). The ion-exchange chromatography, high-performance liquid chromatography (HPLC) and mass spectrometry were performed for identification of protein elicitor. The 471 bp PeBL2 gene produces a 17.22 kDa protein with 156 amino acids containing an 84-residue signal peptide. Consistent with endogenous protein, the recombinant protein expressed in Escherichia coli induced the typical hypersensitive response (HR) and necrosis in tobacco leaves. Additionally, PeBL2 also triggered early defensive response of generation of reactive oxygen species ($H_2O_2$ and $O_2{^-}$) and systemic resistance against of B. cinerea. Our findings shed new light on a novel strategy for biocontrol using B. laterosporus A60.

• Korean Journal Plant Pathology
• /
• v.10 no.2
• /
• pp.99-104
• /
• 1994

A computer-based diagnosing system for diseases of grasses, ornamental plant and fruit trees was developed using a 16 bit personal computer (Model Acer 900) and BASIC was used as a programing language. the developed advisory system was named as Korean Plant Disease Advisory System (KOPDAS). The diagraming system files were composed of a system operation file and several database files. The knowledge-base files are composed of text files, code files and implement program files. The knowledge-base of text files are composed of 79 files of grasses diseases, 122 files of ornamental plant diseases and 67 files of fruit tree diseases. The information of each text file include disease names, causal agents, diseased parts, symptoms, morphological characteristics of causal organisms and control methods for the diagnosing of crop diseases.

• The Plant Pathology Journal
• /
• v.39 no.4
• /
• pp.319-334
• /
• 2023

Plant disease is an important factor affecting crop yield. With various types and complex conditions, plant diseases cause serious economic losses, as well as modern agriculture constraints. Hence, rapid, accurate, and early identification of crop diseases is of great significance. Recent developments in deep learning, especially convolutional neural network (CNN), have shown impressive performance in plant disease classification. However, most of the existing datasets for plant disease classification are a single background environment rather than a real field environment. In addition, the classification can only obtain the category of a single disease and fail to obtain the location of multiple different diseases, which limits the practical application. Therefore, the object detection method based on CNN can overcome these shortcomings and has broad application prospects. In this study, an annotated apple leaf disease dataset in a real field environment was first constructed to compensate for the lack of existing datasets. Moreover, the Faster R-CNN and YOLOv3 architectures were trained to detect apple leaf diseases in our dataset. Finally, comparative experiments were conducted and a variety of evaluation indicators were analyzed. The experimental results demonstrate that deep learning algorithms represented by YOLOv3 and Faster R-CNN are feasible for plant disease detection and have their own strong points and weaknesses.

• Journal of Microbiology and Biotechnology
• /
• v.19 no.2
• /
• pp.194-203
• /
• 2009

$HpaG_{Xooc}$, from rice pathogenic bacterium Xanthomonas oryzae pv. oryzicola, is a member of the harpin group of proteins, eliciting hypersensitive cell death in non-host plants, inducing disease and insect resistance in plants, and enhancing plant growth. To express and secret the $HpaG_{Xooc}$ protein in Bacillus subtilis, we constructed a recombinant expression vector pM43HF with stronger promoter P43 and signal peptide element nprB. The SDS-PAGE and Western blot analysis demonstrated the expression of the protein $HpaG_{Xooc}$ in B. subtilis. The ELISA analysis determined the optimum condition for $HpaG_{Xooc}$ expression in B. subtilis WBHF. The biological function analysis indicated that the protein $HpaG_{Xooc}$ from B. subtilis WBHF elicits hypersensitive response(HR) and enhances the growth of tobacco. The results of RT-PCR analysis revealed that $HpaG_{Xooc}$ induces expression of the pathogenesis-related genes PR-1a and PR-1b in plant defense response.

• Proceedings of the Korean Society of Plant Pathology Conference
• /
• 2003.10a
• /
• pp.25-27
• /
• 2003

Since 1993, a total of 50 problematic plant diseases unrecorded in Korea were surveyed in Gyeongnam province. Totally 34 new host plants to corresponding pathogens investigated in this study were 5 fruit trees, 9 vegetables, 12 ornamental plants, 3 industrial crops, and 5 medicinal plants. Among the newly recorded fruit tree diseases, fruit rot of pomegranate caused by Coniella granati and Rhizopus soft rot of peach caused by Rhizopus nigricans damaged severely showing 65.5% and 82.4% infection rate. Among the vegetable diseases, corynespora leaf spot of pepper caused by Corynespora cassiicola and the crown gall of pepper caused by Agrobacterium tumefaciens, powdery mildew of tomato caused by Oidiopsis taurica were the most severe revealing 47.6%, 84.7%, and 54.5% infection rate in heavily infected fields, respectively. In ornamental plants, collar rot of lily caused by Sclerotium rolfsii, gray mold of primula caused by Botrytis cinerea, soot leaf blight of dendrobium caused by Pseudocercospora dendrobium, sclerotinia rot of obedient plant caused by Sclerotinia sclerotiorum showed 32.7 to 64.8% disease incidence. On three industrial plants such as sword bean, broad bean, and cowpea, eight diseases were firstly found in this study. Among the diseases occurring on broad bean, rust caused by Uromyces viciae-fabae and red spot caused by Botrytis fabae were the major limiting factor for the cultivation of the plant showing over 64% infection rate in fields. In medicinal plants, anthracnose of safflower caused by Collectotrichum acutatum was considered the most severe disease on the plant and followed by collar rot caused by Sclerotium rolfsii.(중략)

• The Plant Pathology Journal
• /
• v.35 no.1
• /
• pp.11-18
• /
• 2019

Gaeumannomyces graminis var. tritici is a soil borne pathogenic fungus associated with wheat roots. The accurate quantification of gene expression during the process of infection might be helpful to understand the pathogenic molecular mechanism. However, this method requires suitable reference genes for transcript normalization. In this study, nine candidate reference genes were chosen, and the specificity of the primers were investigated by melting curves of PCR products. The expression stability of these nine candidates was determined with three programs-geNorm, Norm Finder, and Best Keeper. $TUB{\beta}$ was identified as the most stable reference gene. Furthermore, the exopolygalacturonase gene (ExoPG) was selected to verify the reliability of $TUB{\beta}$ expression. The expression profile of ExoPG assessed using $TUB{\beta}$ agreed with the results of digital gene expression analysis by RNA-Seq. This study is the first systematic exploration of the optimal reference genes in the infection process of Gaeumannomyces graminis var. tritici.

• Proceedings of the Korean Society of Plant Pathology Conference
• /
• 1994.06a
• /
• pp.1-10
• /
• 1994

Biological control of plant disease has been considered a potential control strategy in integrated pest management in recent years. This paper reviewed the progress of research on the biological control of plant diseases in Korea during the last two decades and adopts some future prospects. The crop diseases included, red pepper, Phytophthora blight, ginseng root rots cucumber wilt, sesame damping-off, strawberry wilt and tobacco bacterial wilt and mosaic. Biological control of plant diseases requires a multi-disciplinary approach involving input from plant pathologists, ecologists, mycologists and molecular biologists. The author proposed to organize a group“Committee for Biological Control”including researchers, industries, growers and administrators.

• Korean Journal of Veterinary Service
• /
• v.41 no.2
• /
• pp.119-123
• /
• 2018

There has recently been a growing demand for pathodiagnosis to determine the cause of death in cats. We retrospectively analyzed the diseases diagnosed in cats that were submitted to Animal and Plant Quarantine Agency (APQA) in 2015~2017. Overall diagnostic rate in feline samples was 85.2% (n=104/122). Among diagnosed cases, infectious diseases (n=63) were responsible for most of the feline diseases and feline panleukopenia (n=29) were most prevalent. Highly pathogenic avian influenza (HPAI) H5N6 was first diagnosed in cats at the end of December 2016 in the HPAI outbreaks. One case in 2015, 4 cases in 2016, and 14 cases in 2017 were associated with animal abuse, such as trauma and poisoning. These results suggest that suitable vaccination of feline infectious diseases, monitoring of the susceptible domestic animals during HPAI outbreaks, and interest on veterinary forensics to prevent and determine animal abuse are needed.