Fusion of machine vision technology and AlexNet-CNNs deep learning network for the detection of postharvest apple pesticide residues

Jiang, Bo; He, Jinrong; Yang, Shuqin; Fu, Hongfei; Li, Tong; Song, Huaibo; He, Dongjian

doi:10.1016/j.aiia.2019.02.001

Cited by 101 publications

(55 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Qualitative assessment of postharvest quality is similar to plant stress phenotyping, with its unique emphasis on fruit rather than plant. Most studies have investigated the use of CNNs to detect defects for fruits such as cucumbers [ 129 ], apples [ 130 , 131 ], dates [ 132 ], pears [ 133 ], blueberries [ 134 ], lemons [ 135 ], and peaches [ 136 ]. These studies reported detection accuracies from 87.85% to 98.6%, which were usually 10% to 20% higher than conventional ML methods, demonstrating the advantages of using CNNs for qualitative assessment of postharvest quality.…”

Section: Cnn-based Analytical Approaches For Image-based Plant Phementioning

confidence: 99%

Convolutional Neural Networks for Image-Based High-Throughput Plant Phenotyping: A Review

2020

Plant Phenomics

234

180

View full text Add to dashboard Cite

Plant phenotyping has been recognized as a bottleneck for improving the efficiency of breeding programs, understanding plant-environment interactions, and managing agricultural systems. In the past five years, imaging approaches have shown great potential for high-throughput plant phenotyping, resulting in more attention paid to imaging-based plant phenotyping. With this increased amount of image data, it has become urgent to develop robust analytical tools that can extract phenotypic traits accurately and rapidly. The goal of this review is to provide a comprehensive overview of the latest studies using deep convolutional neural networks (CNNs) in plant phenotyping applications. We specifically review the use of various CNN architecture for plant stress evaluation, plant development, and postharvest quality assessment. We systematically organize the studies based on technical developments resulting from imaging classification, object detection, and image segmentation, thereby identifying state-of-the-art solutions for certain phenotyping applications. Finally, we provide several directions for future research in the use of CNN architecture for plant phenotyping purposes.

show abstract

Section: Cnn-based Analytical Approaches For Image-based Plant Phementioning

confidence: 99%

Convolutional Neural Networks for Image-Based High-Throughput Plant Phenotyping: A Review

2020

Plant Phenomics

234

180

View full text Add to dashboard Cite

show abstract

“…Threshold segmentations were completed based upon gray levels in images. By concerning processing rate, Otsu algorithm, an automatically determining threshold method, was employed (Jiang et al, ). It has a natural principle that shows high relative efficiency between the classifications with maximum variance.…”

Section: Methodsmentioning

confidence: 99%

Detection of mites Tyrophagus putrescentiae and Cheyletus eruditus in flour using hyperspectral imaging system coupled with chemometrics

Wang

et al. 2020

J Food Process Engineering

View full text Add to dashboard Cite

An automatic method for detecting mites in flour has been established using hyperspectral imaging (HSI) system coupled with chemometrics. Reflectance differences among flour, Tyrophagus putrescentiae, and Cheyletus eruditus were relatively distinct. Majority of the shape features, including area, perimeter, the major, and minor axis in C. eruditus were remarkably larger than flour and T. putrescentiae. Textural features reached the level of the maximum significance except for contrast with one-way analysis of variance. Images under the ant colony optimization (ACO) wavebands in random forests (RF) classification showed at least 89% recognition rates, better than the successive projections algorithm wavebands. Artificial neural networks (ANN) with ACO wavebands gave higher recognition accuracies in training and validation sets than RF. Further analysis verified hyperspectrum with ACO-PCA-ANN (PCA, principal component analysis), which showed over 98% accuracy. This study revealed the promising potential of HSI coupled with ACO-PCA-ANN as an accurate and rapid method for detecting mites in flour.

show abstract

“…In fact, the structure of DL differs from that of hand‐crafted ML algorithms in providing an ‘end‐to‐end’ workflow. DL is derived from ANN algorithm with large number of layers and nodes [97, 98]. These complex networks rely on a cascade of multiple layers, where the input of each successive layer is the output from the previous layer.…”

Section: Ml/dl In Pd Diagnosismentioning

confidence: 99%

Machine learning and deep learning for clinical data and PET/SPECT imaging in Parkinson's disease: a review

2020

View full text Add to dashboard Cite

Machine Learning (ML) is a subfield of Artificial Intelligence (AI) that is increasingly applied to several medical diagnosis tasks, including a wide range of diseases. Importantly, various ML models were developed to address the complexity of Parkinson's Disease (PD) diagnosis. PD is a neurodegenerative disease characterized by motor and non-motor disorders where its syndromes affect the daily lives of patients. Several Computer Aided Diagnosis and Detection (CADD) systems based on hand-crafted ML algorithms achieved promising results in distinguishing PD patients from Healthy Control (HC) subjects and other Parkinsonian syndrome categories using clinical data (e.g., speech and gait impairments) and medical imaging [e.g., Position Emission Tomography (PET) and Single Photon Emission Computed Tomography (SPECT)]. Despite the good performance of hand-crafted ML algorithms, there is still a problem linked to the features' extraction and selection. In fact, Deep Learning DL has provided an ultimate solution for the features' extraction and selection related issue. An important number of studies on the diagnosis of PD using DL algorithms were developed recently. This study provides an overview of the application of hand-crafted ML algorithms and DL techniques for PD diagnosis. It also introduces key concepts for understanding the application of ML methods to diagnose PD.

show abstract

Fusion of machine vision technology and AlexNet-CNNs deep learning network for the detection of postharvest apple pesticide residues

Cited by 101 publications

References 9 publications

Convolutional Neural Networks for Image-Based High-Throughput Plant Phenotyping: A Review

Convolutional Neural Networks for Image-Based High-Throughput Plant Phenotyping: A Review

Detection of mites Tyrophagus putrescentiae and Cheyletus eruditus in flour using hyperspectral imaging system coupled with chemometrics

Machine learning and deep learning for clinical data and PET/SPECT imaging in Parkinson's disease: a review

Contact Info

Product

Resources

About