Classification of Rubber Tree Leaf Disease Using Spectrometer

2010 ◽  
Author(s):  
H. Hashim ◽  
M.A. Haron ◽  
F.N. Osman ◽  
S A M Al Junid
Keyword(s):  
Rubber Tree ◽  
Leaf Disease ◽  
Tree Leaf

scholarly journals Using Deep Learning for Image-Based Different Degrees of Ginkgo Leaf Disease Classification

Information ◽  
2020 ◽  
Vol 11 (2) ◽  
pp. 95 ◽  
Author(s):  
Kaizhou Li ◽  
Jianhui Lin ◽  
Jinrong Liu ◽  
Yandong Zhao
Keyword(s):  
Deep Learning ◽  
Ginkgo Biloba ◽  
Plant Disease ◽  
Disease Classification ◽  
Field Conditions ◽  
Laboratory Conditions ◽  
Leaf Disease ◽  
And Training ◽  
Ginkgo Leaf

Diseases from Ginkgo biloba have brought great losses to medicine and the economy. Therefore, if the degree of disease can be automatically identified in Ginkgo biloba leaves, people will take appropriate measures to avoid losses in advance. Deep learning has made great achievements in plant disease identification and classification. For this paper, the convolution neural network model was used to classify the different degrees of ginkgo leaf disease. This study used the VGGNet-16 and Inception V3 models. After preprocessing and training 1322 original images under laboratory conditions and 2408 original images under field conditions, 98.44% accuracy was achieved under laboratory conditions and 92.19% under field conditions with the VGG model. The Inception V3 model achieved 92.3% accuracy under laboratory conditions and 93.2% under field conditions. Thus, the Inception V3 model structure was more suitable for field conditions. To our knowledge, there is very little research on the classification of different degrees of the same plant disease. The success of this study will have a significant impact on the prediction and early prevention of ginkgo leaf blight.

scholarly journals First Report of Neofusicoccum parvum causing Rubber Tree Leaf Spot in China

Plant Disease ◽  
2017 ◽  
Vol 101 (8) ◽  
pp. 1545-1545 ◽  
Author(s):  
Y. X. Liu ◽  
Y. P. Shi ◽  
Y. Y. Deng ◽  
L. L. Li ◽  
L. M. Dai ◽  
...  
Keyword(s):  
Leaf Spot ◽  
Rubber Tree ◽  
Neofusicoccum Parvum ◽  
First Report ◽  
Tree Leaf

scholarly journals First Report of Alternaria heveae Causing Black Leaf Spot of Rubber Tree in China

Plant Disease ◽  
2014 ◽  
Vol 98 (7) ◽  
pp. 1011-1011 ◽  
Author(s):  
Z. Y. Cai ◽  
Y. X. Liu ◽  
G. X. Huang ◽  
M. Zhou ◽  
G. Z. Jiang ◽  
...  
Keyword(s):  
Rubber Tree ◽  
Morphological Characteristics ◽  
Black Spot ◽  
Its Region ◽  
Post Inoculation ◽  
First Report ◽  
Leaf Spots ◽  
Plastic Bags ◽  
Manual Pressure ◽  
Tree Leaf

Rubber tree (Hevea brasiliensis Muell. Arg.) is an important industrial crop of tropical areas for natural rubber production. In October 2013, foliar spots (0.1 to 0.4 mm in diameter), black surrounded by a yellow halo, and with lesions slightly sunken were observed on the rubber tree leaf in a growing area in Heikou County of Yunnan Province. Lesion tissues removed from the border between symptomatic and healthy tissue were surface sterilized in 75% ethanol and air-dried, plated on PDA plates, and incubated at 28°C with alternating day/night cycles of light. The pathogen was observed growing out of many of the leaf pieces, and produced abundant conidia. Colonies 6.1 cm in diameter developed on potato carrot agar (PCA) after 7 days, with well-defined concentric rings of growth. Colonies on PCA were composed of fine, dark, radiating, surface and subsurface hyphae. Conidia produced in PCA culture were mostly solitary or in short chains of 2 to 5 spores, long ovoid to clavate, and light brown, 40 to 81.25 × 8 to 20 μm (200 colonies were measured), with 3 to 6 transverse septa and 0 to 2 longitudinal or oblique septa. Morphological characteristics were similar to those described for Alternaria heveae (3,4). A disease of rubber tree caused by Alternaria sp. had been reported in Mexico in 1947 (2). DNA of Ah01HK13 isolate was extracted for PCR and sequencing of the ITS region with ITS1 and ITS4 primers was completed. From the BLAST analysis, the sequence of Ah01HK13 (GenBank Accession No. KF953884), had 97% similarity to A. dauci, 96% identical to A. macrospora (AY154701.1 and DQ156342.1, respectively), indicating the pathogen belonged to Alternaria genus. According to morphological characteristics, this pathogen was identified as A. heveae. Pathogenicity of representative isolate, Ah01HK13 was confirmed using a field rubber tree inoculation method. Three rubber plants (the clone of rubber tree Yunyan77-4) were grown to the copper-colored leaf stage and inoculated by spraying spore suspension (concentration = 104 conidia/ml) to the copper-colored leaves until drops were equally distributed on it using manual pressure sprayer. Three rubber plants sprayed with sterile distilled water were used as controls. After inoculation, the plants were covered with plastic bags. The plastic bags were removed after 2 days post-inoculation (dpi) and monitored daily for symptom development (1). The experiment was repeated three times. The typical 0.1 to 0.4 mm black leaf spots were observed 7 dpi. No symptoms were observed on control plants. A fungus with the same colony and conidial morphology as A. heveae were re-isolated from leaf lesions on inoculated rubber plants, but not from asymptomatic leaves of control plants, fulfilling Koch's postulates. Based on these results, the disease was identified as black spot of rubber tree caused by A. heveae. To our knowledge, this is the first report of A. heveae on rubber tree in China. References: (1) Z. Y. Cai et al. Microbiol Res. 168:340, 2013. (2) W. J. Martin. Plant Dis. Rep. 31:155, 1947. (3) E. G. Simmons. Mycotaxon 50:262, 1994. (4) T. Y. Zhang. Page 111 in: Flora Fungorum Sinicorum: Alternaria, Science Press, Beijing, 2003.

scholarly journals Survey on Detection and Classification of Plant Leaf Disease in Agriculture Environment

IARJSET ◽  
2017 ◽  
Vol 4 (4) ◽  
pp. 137-139
Author(s):  
Prof. Patil Ashish ◽  
Patil Tanuja
Keyword(s):  
Plant Leaf ◽  
Leaf Disease

scholarly journals Apple Leaf Disease Identification with a Small and Imbalanced Dataset Based on Lightweight Convolutional Networks

Sensors ◽  
2021 ◽  
Vol 22 (1) ◽  
pp. 173
Author(s):  
Lili Li ◽  
Shujuan Zhang ◽  
Bin Wang
Keyword(s):  
Plant Diseases ◽  
Panonychus Ulmi ◽  
Accurate Identification ◽  
Convolutional Networks ◽  
Leaf Disease ◽  
Ring Rot ◽  
Field Environment ◽  
Average Accuracy ◽  
Validation Set

The intelligent identification and classification of plant diseases is an important research objective in agriculture. In this study, in order to realize the rapid and accurate identification of apple leaf disease, a new lightweight convolutional neural network RegNet was proposed. A series of comparative experiments had been conducted based on 2141 images of 5 apple leaf diseases (rust, scab, ring rot, panonychus ulmi, and healthy leaves) in the field environment. To assess the effectiveness of the RegNet model, a series of comparison experiments were conducted with state-of-the-art convolutional neural networks (CNN) such as ShuffleNet, EfficientNet-B0, MobileNetV3, and Vision Transformer. The results show that RegNet-Adam with a learning rate of 0.0001 obtained an average accuracy of 99.8% on the validation set and an overall accuracy of 99.23% on the test set, outperforming all other pre-trained models. In other words, the proposed method based on transfer learning established in this research can realize the rapid and accurate identification of apple leaf disease.

scholarly journals Lemon Leaf Disease Detection and Classification using SVM and CNN

2019 ◽  
Vol 8 (4) ◽  
pp. 11485-11488
Keyword(s):  
Image Processing ◽  
Plant Disease ◽  
Color Space ◽  
Input Image ◽  
Plant Diseases ◽  
Image Processing Technique ◽  
Support Vector ◽  
Training Time ◽  
Leaf Disease

India is a developing country and agriculture has always played a major role in bolstering the country’s economic growth. Due to various factors like industrialization, mechanization and globalization, the green fields are facing complications. So, identifying the plant disease incorrectly will lead to a huge loss of both quantity and quality of the product and it will also incur loss in time and money. Hence, identifying the condition of the plant plays a major role for successful cultivation. Now a day’s image processing technique is being employed as a focal technique for diagnosing the various features of the crop. The image processing techniques can be used for identification of the plant disease and hence classify the plant disease. Generally, the symptoms of the disease are observed on leaves, stems, flowers etc. Here, the leaves of the affected plant are used for the identification and classification of the disease. Leaf image is captured using a smart phone as the first step and then they are processed to determine the condition of the plant. Identification of plant disease follows the steps like loading the image of the plant leaf, histogram equalization for enhancing contrast of the image, segmentation process by using Lab color space model, extracting features of the segmented image using GLCM (Grey Level Cooccurrence Matrix) and finally classification of leaf disease by using MCSVM (Multi Class Support Vector Machine).This procedure obtained an accuracy percentage of 83.6%.Also, it takes long training time for large datasets. To improve the accuracy of the detection and the classification of the plants, Convolutional Neural Network (CNN) is used. The main advantage of CNN is that it automatically detects the main features of the input without any supervision of human. In CNN identification of disease follow the steps like loading the image as the input image, convolution of the feature map and finally max pooling the layers to calculate the features of the image in detail. The plant diseases are classified with an accuracy of 93.8 %.

scholarly journals ỨNG DỤNG GIS VÀ VIỄN THÁM ĐÁNH GIÁ BIẾN ĐỘNG DIỆN TÍCH CÂY CAO SU DO ẢNH HƯỞNG CỦA BÃO SỐ 10 NĂM 2013 TẠI HUYỆN BỐ TRẠCH, TỈNH QUẢNG BÌNH GIAI ĐOẠN 2013-2019

2021 ◽  
Vol 5 (3) ◽  
pp. 2614-2623
Author(s):  
Phạm Hữu Tỵ ◽  
Nguyễn Ngọc Thanh ◽  
Lê Hải Minh ◽  
Nguyễn Văn Bình
Keyword(s):  
Maximum Likelihood ◽  
Rubber Tree ◽  
Rubber Plantation ◽  
Statistical Interpretation ◽  
Field Surveys ◽  
Local Staff ◽  
Report Data ◽  
The Impact ◽  
Tree Development

Nghiên cứu này sử dụng ảnh vệ tỉnh Landsat LC8 của các năm 2013, 2014, và 2019 để giải đoán phân loại lớp phủ cây cao su ở huyện Bố Trạch, tỉnh Quảng Bình và đánh giá biến động diện tích cao su sau ảnh hưởng của bão số 10 (tên là Wutip) năm 2013. Kết quả giải đoán còn sử dụng để đánh giá thiệt hại diện tích trồng cây cao su do ảnh hưởng của bão số 10 năm 2013 và biến động diện tích trồng cây cao su giai đoạn 2013-2019. Các số liệu điều tra thực địa, phỏng vấn cán bộ, số liệu báo cáo thứ cấp, tài liệu phục vụ các hội thảo về phát triển cây cao su ở Quảng Bình đã được thu thập để hỗ trợ cho công việc phân tích, giải đoán ảnh vệ tinh. Nghiên cứu này kết hợp phương pháp giải đoán ảnh theo định hướng đối tượng kết hợp với thuật toán Maximum Likelihood. Kết quả giải đoán đã được đánh giá, độ chính xác giải đoán tổng thể biến động từ 82-88% và hệ số Kappa biến động từ 0,8-0,87 trong các năm nghiên cứu. Qua thống kê kết quả giải đoán ảnh viễn thám Landsat LC8, diện tích trồng cây cao su tại huyện Bố Trạch, tỉnh Quảng Bình bị thiệt hại đáng kể do ảnh hưởng của bão số 10 năm 2013, hơn 1.500 ha bị thiệt hại. Tuy nhiên, mỗi năm diện tích cây sao su được khôi phục lại và trồng mới tại huyện Bố Trạch, do đó sau bão số 10 năm 2013, diện tích cây cao su tăng lên đáng kể từ năm 2014-2019, hơn 2.500 ha. ABSTRACT This study used Landsat LC8 satellite images of 2013, 2014, and 2019 to interpret the classification of rubber tree landcover in Bo Trach district, Quang Binh province and evaluate changes in rubber area after the impact of storms number 10 (named Wutip) in 2013. The results of interpretation were also used to assess the damage of rubber plantations due to the impact of typhoon number 10 in 2013 and changes in rubber plantation area in the period of 2013- 2019. Data from field surveys, interviews with local staff, secondary report data, and documents of conference on rubber tree development in Quang Binh was collected to support analysis and interpretation. This study combined the object-oriented image analysis method combined with the Maximum Likelihood algorithm. The interpretation results were evaluated, the overall interpretation overall accuracy varied from 82-88% and the Kappa coefficient varied from 0.8-0.87 in the studied years. Through the statistical interpretation results of the Landsat LC8 detective, the rubber plantation area in Bo Trach district, Quang Binh province was significantly damaged due to the impact of typhoon number 10 in 2013, over 1500 hectares were damaged. However, each year, the area of ​​​​the rubber tree is restored and newly replanted in Bo Trach district, so after the typhoon number 10 in 2013, the area of ​​rubber trees increased significantly from 2014-2019, over 2,500 ha.

Sign in / Sign up

Export Citation Format

Share Document