scholarly journals Near-Infrared Hyperspectral Imaging Combined with Deep Learning to Identify Cotton Seed Varieties

Molecules ◽  
2019 ◽  
Vol 24 (18) ◽  
pp. 3268 ◽  
Author(s):  
Zhu ◽  
Zhou ◽  
Gao ◽  
Bao ◽  
He ◽  
...  
Keyword(s):  
Deep Learning ◽  
Hyperspectral Imaging ◽  
Cotton Seed ◽  
Near Infrared ◽  
Principal Component ◽  
Critical Factor ◽  
Support Vector ◽  
Classification Models ◽  
Cotton Seeds ◽  
Better Than

Cotton seed purity is a critical factor influencing the cotton yield. In this study, near-infrared hyperspectral imaging was used to identify seven varieties of cotton seeds. Score images formed by pixel-wise principal component analysis (PCA) showed that there were differences among different varieties of cotton seeds. Effective wavelengths were selected according to PCA loadings. A self-design convolution neural network (CNN) and a Residual Network (ResNet) were used to establish classification models. Partial least squares discriminant analysis (PLS-DA), logistic regression (LR) and support vector machine (SVM) were used as direct classifiers based on full spectra and effective wavelengths for comparison. Furthermore, PLS-DA, LR and SVM models were used for cotton seeds classification based on deep features extracted by self-design CNN and ResNet models. LR and PLS-DA models using deep features as input performed slightly better than those using full spectra and effective wavelengths directly. Self-design CNN based models performed slightly better than ResNet based models. Classification models using full spectra performed better than those using effective wavelengths, with classification accuracy of calibration, validation and prediction sets all over 80% for most models. The overall results illustrated that near-infrared hyperspectral imaging with deep learning was feasible to identify cotton seed varieties.

scholarly journals Identification of Maize Kernel Vigor under Different Accelerated Aging Times Using Hyperspectral Imaging

Molecules ◽  
2018 ◽  
Vol 23 (12) ◽  
pp. 3078 ◽  
Author(s):  
Lei Feng ◽  
Susu Zhu ◽  
Chu Zhang ◽  
Yidan Bao ◽  
Xuping Feng ◽  
...  
Keyword(s):  
Aging Time ◽  
Hyperspectral Imaging ◽  
Accelerated Aging ◽  
Principal Component ◽  
Seed Vigor ◽  
Support Vector ◽  
Classification Models ◽  
Maize Kernel ◽  
Seed Aging ◽  
Maize Kernels

Seed aging during storage is irreversible, and a rapid, accurate detection method for seed vigor detection during seed aging is of great importance for seed companies and farmers. In this study, an artificial accelerated aging treatment was used to simulate the maize kernel aging process, and hyperspectral imaging at the spectral range of 874–1734 nm was applied as a rapid and accurate technique to identify seed vigor under different accelerated aging time regimes. Hyperspectral images of two varieties of maize processed with eight different aging duration times (0, 12, 24, 36, 48, 72, 96 and 120 h) were acquired. Principal component analysis (PCA) was used to conduct a qualitative analysis on maize kernels under different accelerated aging time conditions. Second-order derivatization was applied to select characteristic wavelengths. Classification models (support vector machine−SVM) based on full spectra and optimal wavelengths were built. The results showed that misclassification in unprocessed maize kernels was rare, while some misclassification occurred in maize kernels after the short aging times of 12 and 24 h. On the whole, classification accuracies of maize kernels after relatively short aging times (0, 12 and 24 h) were higher, ranging from 61% to 100%. Maize kernels with longer aging time (36, 48, 72, 96, 120 h) had lower classification accuracies. According to the results of confusion matrixes of SVM models, the eight categories of each maize variety could be divided into three groups: Group 1 (0 h), Group 2 (12 and 24 h) and Group 3 (36, 48, 72, 96, 120 h). Maize kernels from different categories within one group were more likely to be misclassified with each other, and maize kernels within different groups had fewer misclassified samples. Germination test was conducted to verify the classification models, the results showed that the significant differences of maize kernel vigor revealed by standard germination tests generally matched with the classification accuracies of the SVM models. Hyperspectral imaging analysis for two varieties of maize kernels showed similar results, indicating the possibility of using hyperspectral imaging technique combined with chemometric methods to evaluate seed vigor and seed aging degree.

scholarly journals Rapid and Nondestructive On-Site Classification Method for Consumer-Grade Plastics Based on Portable NIR Spectrometer and Machine Learning

2020 ◽  
Vol 2020 ◽  
pp. 1-8
Author(s):  
Yinglin Yang ◽  
Xin Zhang ◽  
Jianwei Yin ◽  
Xiangyang Yu
Keyword(s):  
Near Infrared ◽  
Nearest Neighbor ◽  
Diffuse Reflectance Spectrum ◽  
Back Propagation ◽  
Principal Component ◽  
Back Propagation Neural Network ◽  
Support Vector ◽  
Site Classification ◽  
Classification Models ◽  
K Nearest Neighbor

The classification of plastic waste before recycling is of great significance to achieve effective recycling. In order to achieve rapid, nondestructive, and on-site detection, a portable near-infrared spectrometer was used in this study to obtain the diffuse reflectance spectrum for both standard and commercial plastics made by ABS, PC, PE, PET, PP, PS, and PVC. After applying a series of pretreatments, the principal component analysis (PCA) was used to analyze the cluster trend. K-nearest neighbor (KNN), support vector machine (SVM), and back propagation neural network (BPNN) classification models were developed and evaluated, respectively. The result showed that different plastics could be well separated in top three principal components space after pretreatment, and the classification models performed excellent classification results and high generalization capability. This study indicated that the portable NIR spectrometer, integrated with chemometrics, could achieve excellent performance and has great potential in the field of commercial plastic identification.

scholarly journals Identifying Freshness of Spinach Leaves Stored at Different Temperatures Using Hyperspectral Imaging

Foods ◽  
2019 ◽  
Vol 8 (9) ◽  
pp. 356 ◽  
Author(s):  
Zhu ◽  
Feng ◽  
Zhang ◽  
Bao ◽  
He
Keyword(s):  
Hyperspectral Imaging ◽  
Near Infrared ◽  
Principal Component ◽  
Imaging Systems ◽  
Support Vector ◽  
Infrared Reflectance ◽  
Near Infrared Reflectance ◽  
Different Temperatures ◽  
Learning Machine ◽  
Spinach Leaves

Spinach is prone to spoilage in the course of preservation. Spinach leaves stored at different temperatures for different durations will have varying degrees of freshness. In order to monitor the freshness of spinach leaves during storage, a rapid and non-destructive method—hyperspectral imaging technology—was applied in this study. Visible near-infrared reflectance (Vis-NIR) (380–1030 nm) and near-infrared reflectance (NIR) (874–1734 nm) hyperspectral imaging systems were used. Spinach leaves preserved at different temperatures with different durations (0, 3, 6, 9 days at 4 °C and 0, 1, 2 days at 20 °C) were studied. Principal component analysis (PCA) was adopted as a qualitative analysis method. The second-order derivative spectra were utilized to select effective wavelengths. Partial least squares discriminant analysis (PLS-DA), support vector machine (SVM), and extreme learning machine (ELM) were used to build models based on full spectra and effective wavelengths. All three models achieved good results, with accuracies above 92% for both Vis-NIR spectra and NIR spectra. ELM obtained the best results, with all accuracies reaching 100%. The overall results indicate the possibility of the freshness identification of spinach preserved at different temperatures for different durations using two kinds of hyperspectral imaging systems.

scholarly journals Detection of Sulfite Dioxide Residue on the Surface of Fresh-Cut Potato Slices Using Near-Infrared Hyperspectral Imaging System and Portable Near-Infrared Spectrometer

Molecules ◽  
2020 ◽  
Vol 25 (7) ◽  
pp. 1651 ◽  
Author(s):  
Xiulin Bai ◽  
Qinlin Xiao ◽  
Lei Zhou ◽  
Yu Tang ◽  
Yong He
Keyword(s):  
Sulfur Dioxide ◽  
Hyperspectral Imaging ◽  
Classification Accuracy ◽  
Near Infrared ◽  
Imaging System ◽  
Principal Component ◽  
Support Vector ◽  
Svm Model ◽  
Fresh Cut ◽  
Potato Slices

Sodium pyrosulfite is a browning inhibitor used for the storage of fresh-cut potato slices. Excessive use of sodium pyrosulfite can lead to sulfur dioxide residue, which is harmful for the human body. The sulfur dioxide residue on the surface of fresh-cut potato slices immersed in different concentrations of sodium pyrosulfite solution was classified by near-infrared hyperspectral imaging (NIR-HSI) system and portable near-infrared (NIR) spectrometer. Principal component analysis was used to analyze the object-wise spectra, and support vector machine (SVM) model was established. The classification accuracy of calibration set and prediction set were 98.75% and 95%, respectively. Savitzky–Golay algorithm was used to recognize the important wavelengths, and SVM model was established based on the recognized important wavelengths. The final classification accuracy was slightly less than that based on the full spectra. In addition, the pixel-wise spectra extracted from NIR-HSI system could realize the visualization of different samples, and intuitively reflect the differences among the samples. The results showed that it was feasible to classify the sulfur dioxide residue on the surface of fresh-cut potato slices immersed in different concentration of sodium pyrosulfite solution by NIR spectra. It provided an alternative method for the detection of sulfur dioxide residue on the surface of fresh-cut potato slices.

scholarly journals Non-Destructive Detection Pilot Study of Vegetable Organic Residues Using VNIR Hyperspectral Imaging and Deep Learning Techniques

Sensors ◽  
2021 ◽  
Vol 21 (9) ◽  
pp. 2899
Author(s):  
Youngwook Seo ◽  
Giyoung Kim ◽  
Jongguk Lim ◽  
Ahyeong Lee ◽  
Balgeum Kim ◽  
...  
Keyword(s):  
Deep Learning ◽  
Hyperspectral Imaging ◽  
Near Infrared ◽  
Imaging System ◽  
Imaging Technique ◽  
Support Vector ◽  
Organic Residues ◽  
Efficient Detection ◽  
Non Destructive

Contamination is a critical issue that affects food consumption adversely. Therefore, efficient detection and classification of food contaminants are essential to ensure food safety. This study applied a visible and near-infrared (VNIR) hyperspectral imaging technique to detect and classify organic residues on the metallic surfaces of food processing machinery. The experimental analysis was performed by diluting both potato and spinach juices to six different concentration levels using distilled water. The 3D hypercube data were acquired in the range of 400–1000 nm using a line-scan VNIR hyperspectral imaging system. Each diluted residue in the spectral domain was detected and classified using six classification methods, including a 1D convolutional neural network (CNN-1D) and five pre-processing methods. Among them, CNN-1D exhibited the highest classification accuracy, with a 0.99 and 0.98 calibration result and a 0.94 validation result for both spinach and potato residues. Therefore, in comparison with the validation accuracy of the support vector machine classifier (0.9 and 0.92 for spinach and potato, respectively), the CNN-1D technique demonstrated improved performance. Hence, the VNIR hyperspectral imaging technique with deep learning can potentially afford rapid and non-destructive detection and classification of organic residues in food facilities.

scholarly journals Visible hyperspectral imaging for lamb quality prediction

2015 ◽  
Vol 82 (12) ◽  
Author(s):  
Tong Qiao ◽  
Jinchang Ren ◽  
Zhijing Yang ◽  
Chunmei Qing ◽  
Jaime Zabalza ◽  
...  
Keyword(s):  
Hyperspectral Imaging ◽  
Near Infrared ◽  
Singular Spectrum Analysis ◽  
Principal Component ◽  
Visible Range ◽  
Support Vector ◽  
Eating Quality ◽  
Long Time ◽  
Spectral Profiles ◽  
Evaluation Approaches

AbstractThree factors, including tenderness, juiciness and flavour, are found to have an impact on lamb eating quality, which determines the repurchase behaviour of customers. In addition to these factors, the surface colour of lamb can also influence the purchase decision of consumers. From a long time ago, meat industries have been looking for fast and non-invasive objective quality evaluation approaches, where near-infrared spectroscopy (NIRS) and hyperspectral imaging (HSI) have shown great promises in assessing beef quality compared with conventional methods. However, rare research has been conducted for lamb samples. Therefore, in this paper the feasibility of the HSI system for evaluating lamb quality was tested. In total 80 lamb samples were imaged using a visible range HSI system and the spectral profiles were used for predicting lamb quality related traits. For some traits, noise was further removed from HSI spectra by singular spectrum analysis (SSA) for better performance. Considering support vector machine (SVM) is sensitive to high dimensional data, principal component analysis (PCA) was applied to reduce the dimensionality of HSI spectra before feeding into SVM for constructing prediction equations. The prediction results suggest that HSI is promising in predicting some lamb eating quality traits, which could be beneficial for lamb industries.

scholarly journals Near-infrared spectroscopy for the distinction of wood and charcoal from Fabaceae species: comparison of ANN, KNN AND SVM models

2020 ◽  
Vol 29 (3) ◽  
pp. e020
Author(s):  
Helena Cristina Vieira ◽  
Joielan Xipaia dos Santos ◽  
Deivison Venicio Souza ◽  
Polliana D’ Angelo Rios ◽  
Graciela Inés Bolzon de Muñiz ◽  
...  
Keyword(s):  
Near Infrared ◽  
Principal Component ◽  
Nearest Neighbors ◽  
Support Vector ◽  
Classification Models ◽  
K Nearest Neighbors ◽  
Araucaria Forest ◽  
Vector Machines ◽  
Wood Analysis ◽  
Artificial Neural Network Ann

Aim of study: The objective of this work was to evaluate the potential of NIR spectroscopy to differentiate Fabaceae species native to Araucaria forest fragments.Area of study; Trees of the evaluated species were collected from an Araucaria forest stand in the state of Santa Catarina, southern Brazil, in the region to be flooded by the São Roque hydroelectric project.Material and methods: Discs of three species (Inga vera, Machaerium paraguariense and Muellera campestris) were collected at 1.30 meters from the ground. They were sectioned to cover radial variation of the wood (regions near bark, intermediate and near pith). After wood analysis, the same samples were carbonized. Six spectra were obtained from each specimen of wood and charcoal. The original and second derivative spectra, principal component statistics and classification models (Artificial Neural Network: ANN, Support Vector Machines with kernel radial basis function: SVM and k-Nearest Neighbors: k-NN) were investigated.Main results: Visual analysis of spectra was not efficient for species differentiation, so three NIR classification models for species discrimination were tested. The best results were obtained with the use of k-NN for both wood and charcoal and ANN for wood analysis. In all situations, second derivative NIR spectra produced better results.Research highlights: Correct discrimination of wood and charcoal species for control of illegal logging was achieved. Fabaceae species in an Araucaria forest stand were correctly identified.Keywords: Araucaria forest; identification of species; classification models.Abbreviations used: Near infrared: NIR, Lages Herbarium of Santa Catarina State University: LUSC, Principal component analysis: PCA, artificial neural network: ANN, support vector machines with kernel radial basis function: SVM, k-nearest neighbors: k-NN.

scholarly journals Variety Identification of Raisins Using Near-Infrared Hyperspectral Imaging

Molecules ◽  
2018 ◽  
Vol 23 (11) ◽  
pp. 2907 ◽  
Author(s):  
Lei Feng ◽  
Susu Zhu ◽  
Chu Zhang ◽  
Yidan Bao ◽  
Pan Gao ◽  
...  
Keyword(s):  
Hyperspectral Imaging ◽  
Near Infrared ◽  
Network Models ◽  
Principal Component ◽  
Component Analysis ◽  
Variety Identification ◽  
Support Vector ◽  
Neural Network Models ◽  
K Nearest Neighbors ◽  
Standard Normal Variate

Different varieties of raisins have different nutritional properties and vary in commercial value. An identification method of raisin varieties using hyperspectral imaging was explored. Hyperspectral images of two different varieties of raisins (Wuhebai and Xiangfei) at spectral range of 874–1734 nm were acquired, and each variety contained three grades. Pixel-wise spectra were extracted and preprocessed by wavelet transform and standard normal variate, and object-wise spectra (sample average spectra) were calculated. Principal component analysis (PCA) and independent component analysis (ICA) of object-wise spectra and pixel-wise spectra were conducted to select effective wavelengths. Pixel-wise PCA scores images indicated differences between two varieties and among different grades. SVM (Support Vector Machine), k-NN (k-nearest Neighbors Algorithm), and RBFNN (Radial Basis Function Neural Network) models were built to discriminate two varieties of raisins. Results indicated that both SVM and RBFNN models based on object-wise spectra using optimal wavelengths selected by PCA could be used for raisin variety identification. The visualization maps verified the effectiveness of using hyperspectral imaging to identify raisin varieties.

scholarly journals Identification of peat type and humification by laboratory VNIR/SWIR hyperspectral imaging of peat profiles with focus on fen-bog transition in aapa mires

2020 ◽  
Author(s):  
L. Granlund ◽  
M. Keinänen ◽  
T. Tahvanainen
Keyword(s):  
Hyperspectral Imaging ◽  
Near Infrared ◽  
Support Vector ◽  
High Resolution Imaging ◽  
Factors Affecting ◽  
Vector Machines ◽  
Resolution Imaging ◽  
Shortwave Infrared ◽  
Type Classification ◽  
Wide Potential

Abstract Aims Hyperspectral imaging (HSI) has high potential for analysing peat cores, but methodologies are deficient. We aimed for robust peat type classification and humification estimation. We also explored other factors affecting peat spectral properties. Methods We used two laboratory setups: VNIR (visible to near-infrared) and SWIR (shortwave infrared) for high resolution imaging of intact peat profiles with fen-bog transitions. Peat types were classified with support vector machines, indices were developed for von Post estimation, and K-means clustering was used to analyse stratigraphic patterns in peat quality. With separate experiments, we studied spectral effects of drying and oxidation. Results Despite major effects, oxidation and water content did not impede robust HSI classification. The accuracy between Carex peat and Sphagnum peat in validation was 80% with VNIR and 81% with SWIR data. The spectral humification indices had accuracies of 82% with VNIR and 56%. Stratigraphic HSI patterns revealed that 36% of peat layer shifts were inclined by over 20 degrees. Spectral indices were used to extrapolate visualisations of element concentrations. Conclusions HSI provided reliable information of basic peat quality and was useful in visual mapping, that can guide sampling for other analyses. HSI can manage large amounts of samples to widen the scope of detailed analysis beyond single profiles and it has wide potential in peat research beyond the exploratory scope of this paper. We were able to confirm the capacity of HSI to reveal shifts of peat quality, connected to ecosystem-scale change.

scholarly journals Deep Learning Methods for Classification of Certain Abnormalities in Echocardiography

Electronics ◽  
2021 ◽  
Vol 10 (4) ◽  
pp. 495
Author(s):  
Imayanmosha Wahlang ◽  
Arnab Kumar Maji ◽  
Goutam Saha ◽  
Prasun Chakrabarti ◽  
Michal Jasinski ◽  
...  
Keyword(s):  
Deep Learning ◽  
Short Term Memory ◽  
Support Vector ◽  
Variational Autoencoder ◽  
Different Types ◽  
Static Images ◽  
Long Short Term Memory ◽  
2D And 3D ◽  
Better Than

This article experiments with deep learning methodologies in echocardiogram (echo), a promising and vigorously researched technique in the preponderance field. This paper involves two different kinds of classification in the echo. Firstly, classification into normal (absence of abnormalities) or abnormal (presence of abnormalities) has been done, using 2D echo images, 3D Doppler images, and videographic images. Secondly, based on different types of regurgitation, namely, Mitral Regurgitation (MR), Aortic Regurgitation (AR), Tricuspid Regurgitation (TR), and a combination of the three types of regurgitation are classified using videographic echo images. Two deep-learning methodologies are used for these purposes, a Recurrent Neural Network (RNN) based methodology (Long Short Term Memory (LSTM)) and an Autoencoder based methodology (Variational AutoEncoder (VAE)). The use of videographic images distinguished this work from the existing work using SVM (Support Vector Machine) and also application of deep-learning methodologies is the first of many in this particular field. It was found that deep-learning methodologies perform better than SVM methodology in normal or abnormal classification. Overall, VAE performs better in 2D and 3D Doppler images (static images) while LSTM performs better in the case of videographic images.

Sign in / Sign up

Export Citation Format

Share Document