• Journal of Information Processing Systems
• /
• v.17 no.6
• /
• pp.1115-1126
• /
• 2021

Plant disease is one of the most irritating problems for agriculture growers. Thus, timely detection of plant diseases is of high importance to practical value, and corresponding measures can be taken at the early stage of plant diseases. Therefore, numerous researchers have made unremitting efforts in plant disease identification. However, this problem was not solved effectively until the development of artificial intelligence and big data technologies, especially the wide application of deep learning models in different fields. Since the symptoms of plant diseases mainly appear visually on leaves, computer vision and machine learning technologies are effective and rapid methods for identifying various kinds of plant diseases. As one of the fruits with the highest nutritional value, apple production directly affects the quality of life, and it is important to prevent disease intrusion in advance for yield and taste. In this study, an improved deep residual network is proposed for apple leaf disease identification in a novel way, a global residual connection is added to the original residual network, and the local residual connection architecture is optimized. Including that 1,977 apple leaf disease images with three categories that are collected in this study, experimental results show that the proposed method has achieved 98.74% top-1 accuracy on the test set, outperforming the existing state-of-the-art models in apple leaf disease identification tasks, and proving the effectiveness of the proposed method.

• International Journal of Industrial Entomology and Biomaterials
• /
• v.12 no.1
• /
• pp.35-39
• /
• 2006

Fifty-six indigenous and twenty nine exotic mulberry varieties were screened against powdery mildew, Myrothecium leaf spot, Pseudocercospora leaf spot, sooty mold and bacterial leaf spot for a period of three years under field condition. The percent disease index (PDI) was recorded during peak season of the foliar diseases. Out of eighty-five varieties studied, ten varieties were highly resistant and eight were resistant to powdery mildew; six varieties were immune and seventy-eight varieties were highly resistant to Myrothecium leaf spot; sixty varieties were highly resistant and 21 were resistant to Pseudocercospora leaf spot; forty four varieties were highly resistant to sooty mold and two varieties were immune and fifty-eight were highly resistant to bacterial leaf spot. Lowest cumulatative disease index was observed in M. multicaulis (7.28) followed by Thailand lobed (7.85) and Italian mulberry (8.06).

• The Korean Journal of Pesticide Science
• /
• v.6 no.2
• /
• pp.87-95
• /
• 2002

Disease control activities of the methanol extracts from 27 plant species were investigated against six plant diseases such as rice blast, rice sheath blight, tomato gray mold, tomato late blight, wheat leaf rust and barley powdery mildew. The extracts of Humulus japonicus, Hosta longipes, Liriope platyphylla, and Astragalus membranaceus exhibited a great in vivo control activity against rice blast. Similarly, the extracts of Commelina communis and A. membranaceus were highly active on tomato gray mold and barley powdery mildew, respectively. The extracts of H. longipes, L. platyphylla, Solanum nigrum and A. membranaceus showed especially high disease control activity against wheat leaf rust, and then were selected for further tests such as protective, curative, systemic, and lasting activity against wheat leaf rust. The extracts of L. platyphylla and S. nigrum were strong protectant, and that of A. membranaceus possessed both a preventive activity and a curative activity. Systemic disease control by the selected four plant extracts was investigated by examing translaminar activity from leaf-under-surface to leaf-upper-surface and systemic activity by leaf-to-Ieaf movement. All extracts strongly controlled wheat leaf rust by translaminar movement, but hardly controlled the disease by leaf-to-leaf movement. Good lasting activity was also observed against wheat leaf rust from all of the tested extracts. Especially, disease control experiments on wheat seedlings sprayed with the extracts of S. nigrum or H. longipes 7 days prior to inoculation represented control value over 95%. These results suggest that methanol extracts of H. longipes, L. platyphylla, S. nigrum, and A. membranaceus, especially S. nigrum, would potently control wheat leaf rust caused by Puccinia recondita in the fields.

• Korean Journal Plant Pathology
• /
• v.11 no.3
• /
• pp.217-223
• /
• 1995

Nature of graft transmissibility of pear abnormal leaf spot disease was examined by various grafting methods in the greenhouse and field. When the diseased and symptomless twigs were collected in winter and grafted in the next spring to the seed-originated healthy root stock, the abnormal leaf spot was developed only in the case of the diseased twigs. Double grafting on a seed-originated healthy root stock, where the diseased and the symptomless twigs were used as 1st and 2nd scions, respectively, developed abnormal leaf spot lesions without exception on the 2nd scions. Tongue-graft with the diseased and the symptomless trees also incited abnormal leaf spots on the both trees. Abnormal leaf spots of were also developed on HN-39, an indicator pear tree, used as a 2nd scion in a double graft test, where the diseased twig and a seed-originated healthy tree were used as the 1st scion and the root stock, respectively. When the diseased twig was top-grafted to the healthy root stock, lesion development of abnormal spot was limited to the grafted twig itself in the 1st year, but expanded to the main branches in the 2nd year, and spread over the whole tree in the 3rd year. This result indicates that the causal agent of abnormal leaf spot disease is transmitted by graft.

• Mycobiology
• /
• v.46 no.3
• /
• pp.278-282
• /
• 2018

Chrysanthemum coronarium is an economically important plant in Asia, and used medicinally, ornamentally and as a vegetable. In April 2017, leaf spot disease on C. coronarium was observed in Shiyan, Hubei, China. A single-spore isolate was obtained and identified based on morphology and sequence analysis using four regions (rDNA ITS, GAPDH, $EF-1{\alpha}$, and RPB2). The results indicated that the fungus is Alternaria argyranthemi. The pathogenicity tests revealed that the species could cause severe leaf spot and blight disease on the host. This is the first report of leaf spot disease on C. coronarium caused by A. argyranthemi in the world, which is also a new record of Alternaria species in China.

• Plant Disease and Agriculture
• /
• v.5 no.1
• /
• pp.50-54
• /
• 1999

Leaf blight outbreak was investigated in sweet persimmon tree orchards in Korea during a three-year period from 1995 to 1997. The man percentage of sweet perismmon leaves blighted by Pestalotiopsis theae was 15.9%. The highest disease incidence was surveyed to 20% in Milryang. The disease began from early June to late October, and peaked in September and October. The lesion size on leaf ranged mainly 1-3 cm. The typical symptoms were large grayish concentric lesions of oval patterns of either mesophyll or margin of the leaf, and olde trees were more susceptible than younger ones.

• Research in Plant Disease
• /
• v.27 no.3
• /
• pp.107-114
• /
• 2021

During a disease survey on weeds and minor cultivated crops in Korea, a brown leaf spot disease was observed on Sonchus asper. Leaf lesions were round or irregular in shape, and grayish brown to brown with a purple margin. In severe infection, lesions enlarged and coalesced, resulting in blighting of the leaves. The isolates from these leaf lesions were identified as Alternaira sonchi based on morphological characteristics and phylogenetic analyses of Internal transcribed spacer region, Alternaria allergen a1, glyceraldehyde 3-phosphate dehydrogenase, RNA polymerase II, and translation elongation factor genes. This study provides a comprehensive description of the morphological characteristics and phylogenetical traits of A. sonchi causing brown leaf spot on S. asper in Korea.

• Journal of the Korean Society of Tobacco Science
• /
• v.14 no.2
• /
• pp.126-132
• /
• 1992

This experiment was conducted to examine estimates of heterosis, degree of dominance, heritability and phenotypic and genotypic correlation for several mutant characters in flue-cured tobacco variety. Significant heterosis was noted, recording 2.73 and 6.16% for leaf width, -6.86 and -4.72 for leaf shape index, 19.8 and 23.4% for bacterial wilt disease index in Fl an4 F2 generation, respectively, and -1.44 for days to flower in F2 generation. And also leaf width was appeared partial dominance in Fl, and leaf shape index in Fl and F2, Leaf width in F2 was appeared overdominance. Estimated heritabilities in the broad sense ranged from 0.77 to 0.87 for plant and stalk height and days to flower, while those of leaf number, leaf length and width, leaf shape index and bacterial wilt disease index ranged from 0.50 to 0.65. And the heritabilities in the narrow sense were appeared 0.64 and 0.72 for stalk and plant height, respectively, and the others were ranged from 0.32 to 0.47 Positive genotpic correlations appeared among plant height, stalk height, leaf length and leaf width, and between leaf shape index ands day to flower. And negative genotypic correlations appeared between leaf shape index and plant height and stalk height and leaf width, and between bacterial wilt disease index and leaf length.

• Korean Journal Plant Pathology
• /
• v.14 no.1
• /
• pp.52-61
• /
• 1998

This paper is the fifth report about the fungal diseases of economic resource plants observed newly in Korea. It contains short descriptions on symptoms, occurrence conditions, pathogens, and some phytopathological notes for each of 10 fungal plant diseases. They are identified as leaf spot of Adenophora triphylla var. japonica by Septoria lengyelii, leaf spot of Calystegia soldanella by S. convolvuli, leaf spot of Campanula punctata by S. campanulae, leaf spot of Codonopsis lanceolata by S. codonopsidis, leaf spot of Geum japonicum by s. gei, black spot of Oenanthe javanica by s. oenanthes, leaf spot of Oenothera odorata by S. oenotherae, angular leaf spot of Rehmannia glutinosa by S. digitalis, brown spot of Rubus crataegifolius by s. rubi, and leaf spot of Viola verecunda by S. violae-palustris, respectively.

• Research in Plant Disease
• /
• v.19 no.3
• /
• pp.196-200
• /
• 2013

This study was carried out to investigate yield loss due to soybean leaf spot disease caused by Cercospora sojina Hara and to determine the economic threshold level. The investigations revealed highly significant correlations between disease severity (diseased leaf area) and yield components (pod number per plant, total grain number per plant, total grain weight per plant, percent of ripened grain, weight of hundred seed, and yield). The correlation coefficients between leaf spot severity and each component were -0.90, -0.90, -0.92, -0.99, -0.90 and -0.94, respectively. The yield was inversely proportional to the diseased leaf area increased. The regression equation, yield prediction model, between disease severity (x) and yield (y) was obtained as y = -3.7213x + 354.99 ($R^2$ = 0.9047). Based on the yield prediction model, economic injury level and economic threshold level could be set as 3.3% and 2.6% of diseased leaf area of soybean.