Real-time hyperspectral imaging for the in-field estimation of strawberry ripeness with deep learning

Gao, Zongmei; Shao, Yuanyuan; Xuan, Guantao; Wang, Yongxian; Liu, Yi; Han, Xiang

doi:10.1016/j.aiia.2020.04.003

Cited by 101 publications

(72 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Then, the softmax function is used to provide activation information in the last layer, resulting in a category assignment. A typical CNN architecture is shown in Figure 3 for identifying the ripeness of strawberry based on hyperspectral imagery [34].…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning Application in Plant Stress Imaging: A Review

et al. 2020

Self Cite

View full text Add to dashboard Cite

Plant stress is one of major issues that cause significant economic loss for growers. The labor-intensive conventional methods for identifying the stressed plants constrain their applications. To address this issue, rapid methods are in urgent needs. Developments of advanced sensing and machine learning techniques trigger revolutions for precision agriculture based on deep learning and big data. In this paper, we reviewed the latest deep learning approaches pertinent to the image analysis of crop stress diagnosis. We compiled the current sensor tools and deep learning principles involved in plant stress phenotyping. In addition, we reviewed a variety of deep learning applications/functions with plant stress imaging, including classification, object detection, and segmentation, of which are closely intertwined. Furthermore, we summarized and discussed the current challenges and future development avenues in plant phenotyping.

show abstract

Section: Convolutional Neural Networkmentioning

confidence: 99%

“…One typical CNN architecture for estimating the ripeness of strawberry based on hyperspectral imagery[34]. Note: Conv represents convolutional layer; FC: fully connected layer.…”

mentioning

confidence: 99%

Deep Learning Application in Plant Stress Imaging: A Review

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Least squares support vector machines (LS-SVM) methodology, an optimized version of the standard SVM, is one of the supervised learning methods (classes or composition of the samples in the data matrix is involved) [21][22][23] . It has a wide application for pattern recognition and function estimation.…”

Section: Least Squares Support Vector Machinesmentioning

confidence: 99%

Determination of damaged wheat kernels with hyperspectral imaging analysis

Shao

Gao

Xuan

et al. 2020

International Journal of Agricultural and Biological Engineering

Self Cite

View full text Add to dashboard Cite

Hyperspectral imaging was applied to classify the damaged wheat kernels and healthy kernels. The spectral information was extracted from damaged wheat kernels and healthy kernels samples. The effective wavelengths were obtained from spectral of 865-1711 nm by X-loadings of principal component analysis (PCA) and successive projection algorithm (SPA) method, respectively. Partial least square method (PLS) and least square-support vector machine (LS-SVM) were then used to build classification models on full spectral data and effective wavelengths dataset, respectively. The results showed that the classification accuracy of every LS-SVM model was the best, being 100%. While the accuracy of the PLS model was slightly lower, still over 97%. The confusion matrix showed that several damaged wheat kernels samples were misclassified as healthy samples, while all healthy samples were correctly classified. The overall results indicated that hyperspectral imaging could be used for discriminating the damaged wheat kernels and could provide a reference for detecting other grain kernels grading degrees. Further, this study can provide a research basis for the development of online or portable detectors on grain damaged kernels recognition, which will be beneficial for grain grading or post-harvest quality processing of other grains.

show abstract

“…Yuan et al [ 18 ] conducted autocorrelation analysis on spectral features, disease-sensitive bands, and new disease indices to generate an optimized spectral feature set, and based on which, tea anthracnose detection is realized by developing a framework combining unsupervised classification and adaptive two-dimensional thresholding. Gao et al [ 19 ] used the sequential feature selection algorithm to select the spectral feature wavelengths and utilized neural networks to classify the early ripeness of strawberry based on the selected spatial feature images. Tian et al [ 20 ] extracted the chromaticity moments-based texture features of the filtered diseased leaf images in several characteristic wavelengths and used SVM to classify cucumber downy mildew and powdery mildew.…”

Section: Introductionmentioning

confidence: 99%

Hyperspectral Leaf Image-Based Cucumber Disease Recognition Using the Extended Collaborative Representation Model

Luo

Wang

et al. 2020

Sensors

View full text Add to dashboard Cite

Collaborative representation (CR)-based classification has been successfully applied to plant disease recognition in cases with sufficient training samples of each disease. However, collecting enough training samples is usually time consuming and labor-intensive. Moreover, influenced by the non-ideal measurement environment, samples may be corrupted by variables introduced by bad illumination and occlusions of adjacent leaves. Consequently, an extended collaborative representation (ECR)-based classification model is presented in this paper. Then, it is applied to cucumber leaf disease recognition, which constructs a pure spectral library consisting of several representative samples for each disease and designs a universal variation spectral library that deals with linear variables superimposed on samples. Thus, each query sample is encoded as a linear combination of atoms from these two spectral libraries and disease identity is determined by the disease of minimal reconstruction residuals. Experiments are conducted on spectral curves extracted from normal leaves and the disease lesions of leaves infected with cucumber anthracnose and brown spot. The diagnostic accuracy is higher than 94.7% and the average online diagnosis time is short, about 1 to 1.3 ms. The results indicate that the ECR-based classification model is feasible in the fast and accurate diagnosis of cucumber leaf diseases.

show abstract

Real-time hyperspectral imaging for the in-field estimation of strawberry ripeness with deep learning

Cited by 101 publications

References 38 publications

Deep Learning Application in Plant Stress Imaging: A Review

Deep Learning Application in Plant Stress Imaging: A Review

Determination of damaged wheat kernels with hyperspectral imaging analysis

Hyperspectral Leaf Image-Based Cucumber Disease Recognition Using the Extended Collaborative Representation Model

Contact Info

Product

Resources

About