scholarly journals Region-aggregated attention CNN for disease detection in fruit images

PLoS ONE ◽  
2021 ◽  
Vol 16 (10) ◽  
pp. e0258880
Author(s):  
Chang Hee Han ◽  
Eal Kim ◽  
Tan Nhu Nhat Doan ◽  
Dongil Han ◽  
Seong Joon Yoo ◽  
...  
Keyword(s):  
Detection System ◽  
Disease Detection ◽  
Feature Maps ◽  
Yield And Quality ◽  
Additional Level ◽  
Improved Design ◽  
Candidate Regions ◽  
Fold Cross Validation ◽  
Apple Fruits ◽  
Timely Treatment

Background Diseases and pests have a profound effect on a yearly harvest and productivity in agriculture. A precise and accurate detection of the diseases and pests could facilitate timely treatment and management of the diseases and pests and lessen the resultant loss in economy and health. Herein, we propose an improved design of the disease detection system for plant images. Methods Built upon the two-stage framework of object detection neural networks such as Mask R-CNN, the proposed network involves three types of extensions, including the addition of additional level of feature pyramids to improve the exploration and proposal of candidate regions, the aggregation of feature maps from all levels of feature pyramids per candidate region to fully exploit the information from feature pyramids, and the introduction of a squeeze-and-excitation block to the construction of feature pyramids and the aggregated feature maps to improve the representation of feature maps. Results The proposed network was evaluated using 74 images of infected apple fruits. In 3-fold cross-validation, the proposed network achieved averaged precision (AP) of 72.26, AP at 0.5 threshold of 88.51 and AP at 0.75 threshold of 82.30. In the comparative experiments, the proposed network outperformed the other competing networks. The utility of the three extensions was also demonstrated in comparison to Mask R-CNN. Conclusions The experimental results suggest that the proposed network could identify and localize the symptom of the disease with high accuracy, leading to an early diagnosis and treatment of the disease, and thus holding the potential for improving crop yield and quality.

Automated Crop Harvesting, Growth Monitoring and Disease Detection System for Vertical Farming Greenhouse

2021 ◽  
Author(s):  
Charith Jayasekara ◽  
Sajani Banneka ◽  
Gihan Pasindu ◽  
Yukthi Udawaththa ◽  
Sasini Wellalage ◽  
...  
Keyword(s):  
Detection System ◽  
Disease Detection ◽  
Growth Monitoring ◽  
Vertical Farming

scholarly journals Automated Quality Assessment of Crops Using CNN - Keras

2021 ◽  
pp. 641-645
Author(s):  
Meghashree ◽  
Alwyn Edison Mendonca ◽  
Ashika S Shetty
Keyword(s):  
Image Classification ◽  
Agricultural Production ◽  
Detection System ◽  
Cost Effective ◽  
Farming System ◽  
Modern Method ◽  
Innovative Technology ◽  
Disease Detection ◽  
Agricultural Field ◽  
Plant Leaf

Plant disease is an on-going challenge for the farmers and it has been one of the major threats to the income and the food security. This project is used to classify plant leaf into diseased and healthy leaf,to improve the quality and quantity of agricultural production in the country. The innovative technology that helps in improve the quality and quantity in the agricultural field is the smart farming system. It represented the modern method that provides cost-effective disease detection and deep learning with convolutional neural networks (CNNs) has achieved large successfulness in the categorisation of different plant leaf diseases. CNN reads a really very larger picture in a simple way. CNN nearly utilised to examine visual imagery and are frequently working behind the scenes in image classification. To extract the general features and then classify them under multiple based upon the features detected. This project will help the farmers financially in increasing the production of the crop yield as well as the overall agricultural production. The paper reviews the expected methods of plant leaf disease detection system that facilitates the advancement in agriculture. It includes various phases such as image preprocessing, image classification, feature extraction and detecting healthy or diseased.

Plant Disease Detection Using Machine Learning Approaches

2021 ◽  
pp. 122-130
Author(s):  
Sukanta Ghosh ◽  
Shubhanshu Arya ◽  
Amar Singh
Keyword(s):  
Plant Disease ◽  
Crop Yields ◽  
Detection System ◽  
Visual Observation ◽  
Plant Diseases ◽  
Disease Detection ◽  
Learning Approaches ◽  
Factors Affecting ◽  
Plant Leaf ◽  
Market Situation

Agricultural production is one of the main factors affecting a country's domestic market situation. Many problems are the reasons for estimating crop yields, which vary in different parts of the world. Overuse of chemical fertilizers, uneven distribution of rainfall, and uneven soil fertility lead to plant diseases. This forces us to focus on effective methods for detecting plant diseases. It is important to find an effective plant disease detection technique. Plants need to be monitored from the beginning of their life cycle to avoid such diseases. Observation is a kind of visual observation, which is time-consuming, costly, and requires a lot of experience. For speeding up this process, it is necessary to automate the disease detection system. A lot of researchers have developed plant leaf detection systems based on various technologies. In this chapter, the authors discuss the potential of methods for detecting plant leaf diseases. It includes various steps such as image acquisition, image segmentation, feature extraction, and classification.

scholarly journals Automatic deep learning-based colorectal adenoma detection system and its similarities with pathologists

BMJ Open ◽  
2020 ◽  
Vol 10 (9) ◽  
pp. e036423
Author(s):  
Zhigang Song ◽  
Chunkai Yu ◽  
Shuangmei Zou ◽  
Wenmiao Wang ◽  
Yong Huang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Colorectal Adenoma ◽  
Detection System ◽  
Model Performance ◽  
Area Under The Curve ◽  
Learning Model ◽  
Feature Maps ◽  
Adenoma Detection ◽  
Microscopic Evaluation ◽  
Deep Learning Model

ObjectivesThe microscopic evaluation of slides has been gradually moving towards all digital in recent years, leading to the possibility for computer-aided diagnosis. It is worthwhile to know the similarities between deep learning models and pathologists before we put them into practical scenarios. The simple criteria of colorectal adenoma diagnosis make it to be a perfect testbed for this study.DesignThe deep learning model was trained by 177 accurately labelled training slides (156 with adenoma). The detailed labelling was performed on a self-developed annotation system based on iPad. We built the model based on DeepLab v2 with ResNet-34. The model performance was tested on 194 test slides and compared with five pathologists. Furthermore, the generalisation ability of the learning model was tested by extra 168 slides (111 with adenoma) collected from two other hospitals.ResultsThe deep learning model achieved an area under the curve of 0.92 and obtained a slide-level accuracy of over 90% on slides from two other hospitals. The performance was on par with the performance of experienced pathologists, exceeding the average pathologist. By investigating the feature maps and cases misdiagnosed by the model, we found the concordance of thinking process in diagnosis between the deep learning model and pathologists.ConclusionsThe deep learning model for colorectal adenoma diagnosis is quite similar to pathologists. It is on-par with pathologists’ performance, makes similar mistakes and learns rational reasoning logics. Meanwhile, it obtains high accuracy on slides collected from different hospitals with significant staining configuration variations.

Establishment of Residue Analysis of Propanil (Dichloropropionanilide), Linuron and Diphenamide in Agricultural Commodities

1985 ◽  
Vol 48 (4) ◽  
pp. 320-324 ◽  
Author(s):  
YOSHIO ITO ◽  
HIDEYO SUZUKI ◽  
SHUNJIRO OGAWA ◽  
MASAHIRO IWAIDA
Keyword(s):  
Detection System ◽  
Residue Analysis ◽  
Brown Rice ◽  
Sodium Hydride ◽  
Gas Chromatograph ◽  
Florisil Column ◽  
Florisil Column Chromatography ◽  
Additional Level ◽  
Ppm Level

A method for simultaneous determination of residues of three herbicides containing nitrogen, propanil (3′,4′-dichloropropionanilide), linuron and diphenamide, in agricultural commodites was established. The herbicides were extracted by acetone from samples, transferred into dichloromethane, then the dichloromethane extract was dried. The residue was dissolved in n-hexane, and purified from oily contaminants by partition with acetonitrile. The acetonitrile extract was further purified by Florisil column chromatography with dichloromethane. Diphenamide was determined directly by use of gas chromatograph equipped with a flame-thermoionic detection system (FTDGC). DCPA and linuron were derivatized into their N-monomethyl derivatives by a strong methylation method by use of sodium hydride and methyl iodide in a mixture of dimethyl sulfoxide and benzene, and then subjected to determination by FTD-GC. Recoveries of the three herbicides from brown rice, barley, corn, potato, carrot and onion were not less than 80% at the additional level of 1.0 ppm, while not less than 70% at 0.1 ppm level, respectively.

Sign in / Sign up

Export Citation Format

Share Document