Identification of Defective Maize Seeds Using Hyperspectral Imaging Combined with Deep Learning

Article Computer Science, Artificial Intelligence

Deep neural networks-based relevant latent representation learning for hyperspectral image classification

Akrem Sellami et al.

Summary: The study introduces a novel methodology for hyperspectral image classification using multi-view deep neural networks that combines spectral and spatial features to enhance classification performance with limited labeled samples.

PATTERN RECOGNITION (2022)

添加到收藏夹

Article Agriculture, Multidisciplinary

Moldy peanuts identification based on hyperspectral images and Point-centered convolutional neural network combined with embedded feature selection

Deshuai Yuan et al.

Summary: This study proposed a method for the nondestructive detection of moldy peanuts using near-infrared hyperspectral imaging and a lightweight point-centered convolutional neural network. By integrating embedded feature selection, the method achieved accurate classification. Compared with conventional methods, this approach performed better in terms of accuracy and the number of bands required.

COMPUTERS AND ELECTRONICS IN AGRICULTURE (2022)

添加到收藏夹

Article Chemistry, Applied

Integration of textural and spectral features of Raman hyperspectral imaging for quantitative determination of a single maize kernel mildew coupled with chemometrics

Yuan Long et al.

Summary: In this study, a line-scanning Raman hyperspectral imaging system was used to detect fungal spore quantity of a single maize kernel, establishing a quantitative model through a combination of Raman spectra and textural features. The optimal detection model was successfully established using competitive adaptive reweighted sampling (CARS) to optimize characteristic variables, providing a feasible in-situ and nondestructive alternative for detecting fungal spore quantity.

FOOD CHEMISTRY (2022)

添加到收藏夹

Article Agronomy

Hyperspectral imaging coupled with multivariate analysis and artificial intelligence to the classification of maize kernels

Fariba Alimohammadi et al.

Summary: This study aimed to explore the potential of non-destructive hyperspectral imaging in the wavelength range of 400-1000 nm to discriminate between and classify maize kernels in different cultivars. The classification was successfully performed through Linear Discriminant Analysis and Artificial Neural Network methods, and important predictor variables were identified.

INTERNATIONAL AGROPHYSICS (2022)

添加到收藏夹

Article Spectroscopy

Discrimination of unsound wheat kernels based on deep convolutional generative adversarial network and near-infrared hyperspectral imaging technology

Hao Li et al.

Summary: A novel method based on DCGAN and near-infrared hyperspectral imaging technology was proposed to identify unsound wheat kernels. By expanding samples and using classifiers like CNN, SVM, and DT, the accuracy of the classifier was significantly improved.

SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY (2022)

添加到收藏夹

Article Plant Sciences

Corn Seed Defect Detection Based on Watershed Algorithm and Two-Pathway Convolutional Neural Networks

Linbai Wang et al.

Summary: A method for corn seed defect detection based on a watershed algorithm combined with a two-pathway convolutional neural network model was developed. The experimental results showed that the proposed method was effective in identifying defective seeds and achieved high accuracy and recall rate. It outperformed the traditional method in corn seed defect detection.

FRONTIERS IN PLANT SCIENCE (2022)

添加到收藏夹

Article Plant Sciences

Hyperspectral Monitoring of Powdery Mildew Disease Severity in Wheat Based on Machine Learning

Zi-Heng Feng et al.

Summary: The study optimized the monitoring model for wheat powdery mildew by processing canopy spectral data, using different algorithms and models. It provided new ideas and methods for realizing high-precision remote sensing monitoring of crop disease status.

FRONTIERS IN PLANT SCIENCE (2022)

添加到收藏夹

Article Chemistry, Multidisciplinary

Effective band selection of hyperspectral image by an attention mechanism-based convolutional network

Zengwei Zheng et al.

Summary: This paper proposes an end-to-end trainable network framework based on 3D CNN, which combines band selection, feature extraction, and model training by learning band attention vectors for band selection. Experimental results demonstrate that the proposed attention mechanism can effectively select the most optimal band combination compared to traditional methods.

RSC ADVANCES (2022)

添加到收藏夹

Article Agricultural Engineering

Hyperspectral imaging technology combined with deep learning for hybrid okra seed identification

Zeyu Yu et al.

Summary: In this study, deep learning combined with hyperspectral imaging technology was used to identify hybrid okra seeds. The CNN model achieved the highest accuracy and strongest robustness among the four discriminant models. With an increase in the number of varieties, the classification accuracy of all models decreased, but CNN showed more stable results.

BIOSYSTEMS ENGINEERING (2021)

添加到收藏夹

Article Instruments & Instrumentation

Maturity determination of single maize seed by using near-infrared hyperspectral imaging coupled with comparative analysis of multiple classification models

Zheli Wang et al.

Summary: This study utilized NIR-HSI technology and various modeling methods to classify the maturity of maize seeds, with the PLS-DA model based on feature wavelengths selected from T2 spectra achieving the optimal results. The results demonstrate the potential of hyperspectral imaging technology for rapid and accurate classification of maize seed maturity.

INFRARED PHYSICS & TECHNOLOGY (2021)

添加到收藏夹

Article Agriculture, Multidisciplinary

Chlorophyll content estimation based on cascade spectral optimizations of interval and wavelength characteristics

Di Song et al.

Summary: This study proposed a cascade method of interval-wavelength screening to improve the estimation accuracy and robustness of chlorophyll content in maize crops, leading to the establishment of a chlorophyll distribution map. By optimizing the spectral interval and secondary wavelength screening, the method successfully reduced data dimensions and enhanced model performances. The results demonstrated the potential of this approach in eliminating redundant variables and improving model accuracy.

COMPUTERS AND ELECTRONICS IN AGRICULTURE (2021)

添加到收藏夹

Article Agriculture, Multidisciplinary

Discriminant analysis and comparison of corn seed vigor based on multiband spectrum

Yali Wang et al.

Summary: This study explores seed vigor using spectral ranges and establishes models to differentiate seed vigor. In terms of selecting effective variables, the competitive adaptive reweighted sampling method shows superior performance.

COMPUTERS AND ELECTRONICS IN AGRICULTURE (2021)

添加到收藏夹

Article Agriculture, Multidisciplinary

Feasibility study on identifying seed viability of Sophora japonica with optimized deep neural network and hyperspectral imaging

Lei Pang et al.

Summary: This study focused on rapid identification of Sophora japonica seed viability through analyzing different aging grades and imbibition states. It was found that fat was the most sensitive indicator to spectral and viability changes. The deep learning model combining image performed the best with recognition accuracy above 90%. Particle swarm optimization algorithm was proposed to increase recognition rate and convergence speed.

COMPUTERS AND ELECTRONICS IN AGRICULTURE (2021)

添加到收藏夹

Article Spectroscopy

Hyperspectral imaging coupled with multivariate methods for seed vitality estimation and forecast for Quercus variabilis

Lei Pang et al.

Summary: This study investigated the feasibility of estimating and forecasting the vitality of different Quercus variabilis seeds using hyperspectral imaging. Accelerated aging facilitated the differentiation of four vitality levels. The research showed that accurate prediction of seed vitality can be achieved non-destructively, providing new methods and insights for seed studies.

SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY (2021)

添加到收藏夹

Article Agriculture, Multidisciplinary

Hyperspectral imaging techniques for rapid detection of nutrient content of hydroponically grown lettuce cultivars

Sulaymon Eshkabilov et al.

Summary: This study analyzed the online quality measurements of four lettuce cultivars using hyperspectral image processing techniques, developed algorithms to measure nutrient levels in leaf tissues, and identified optimal wave bands within specific ranges. By utilizing partial least squares regression and principal component analysis techniques, successful estimation of nutrient levels in lettuce leaf samples was achieved.

COMPUTERS AND ELECTRONICS IN AGRICULTURE (2021)

添加到收藏夹

Article Chemistry, Analytical

Hierarchical classification pathway for white maize, defect and foreign material classification using spectral imaging

Kate Sendin et al.

Summary: This study aimed to develop an accurate and affordable automated analytical technique for white maize grading using NIR spectral imaging in the South African maize industry. Through 25 PLS-DA models, the 17 categories and sub-categories were classified in a hierarchical decision pathway, achieving an overall accuracy of 93.3% for the main categories. Three waveband selection techniques were employed, with the VIP set based on only 7.3% of the original spectral variables recommended as the best trade-off between performance and cost.

MICROCHEMICAL JOURNAL (2021)

添加到收藏夹

Article Chemistry, Analytical

HyperSeed: An End-to-End Method to Process Hyperspectral Images of Seeds

Tian Gao et al.

Summary: A novel seed hyperspectral measurement platform named HyperSeed was developed to provide high-throughput, nondestructive, and precise measurement of seeds for seed quality evaluation and agricultural production improvement. Experimental results demonstrated that the proposed 3D convolutional neural network model achieved high accuracy in both seed-based and pixel-based classification, outperforming the support vector machine model. Additionally, the pipeline allows systematic analysis of spectral curves and identification of biological interest wavelengths.

SENSORS (2021)

添加到收藏夹

Article Spectroscopy

Application of long-wave near infrared hyperspectral imaging for determination of moisture content of single maize seed

Zheli Wang et al.

Summary: In this study, a long-wave near infrared hyperspectral imaging system was developed to accurately predict moisture content in single maize seeds. A model based on CARS-SPA-LS-SVM method coupled with mixed spectral proved to be the most optimal for moisture content prediction.

SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY (2021)

添加到收藏夹

Article Agriculture, Multidisciplinary

A new attention-based CNN approach for crop mapping using time series Sentinel-2 images

Yumiao Wang et al.

Summary: The study proposed a novel attention-based convolutional neural network approach (Geo-CBAM-CNN) for crop classification using time series Sentinel-2 images. By integrating geographic information of crops and enhancing the model's attention spectrally and spatially, the Geo-CBAM-CNN model achieved the best performance in large scale applications.

COMPUTERS AND ELECTRONICS IN AGRICULTURE (2021)

添加到收藏夹

Article Chemistry, Applied

Aflatoxin rapid detection based on hyperspectral with 1D-convolution neural network in the pixel level

Jiyue Gao et al.

Summary: In this study, 1D-CNN was successfully applied to detect aflatoxin, achieving high accuracy through parameter optimization, and demonstrating the effectiveness of neural networks compared to feature selection. Ultimately, providing a core algorithm for the intelligent sorter and positively impacting grain processing and prenatal detoxification in foreign trade enterprises.

FOOD CHEMISTRY (2021)

添加到收藏夹

Article Food Science & Technology

Detection of foreign materials in cocoa beans by hyperspectral imaging technology

Ali Saeidan et al.

Summary: The study investigates the use of hyperspectral imaging technology for detecting foreign materials in cocoa beans, with results showing SVM performing well in classifying these materials.

FOOD CONTROL (2021)

添加到收藏夹

Article Spectroscopy

Hyperspectral prediction of sugarbeet seed germination based on gauss kernel SVM

Jun Yang et al.

Summary: This study successfully predicted the germination rate of sugarbeet seeds using hyperspectral image processing technology, and found that the SVM-RBF model provided the highest prediction accuracy.

SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY (2021)

添加到收藏夹

Article Biochemical Research Methods

DeepFeature: feature selection in nonimage data using convolutional neural network

Alok Sharma et al.

Summary: Artificial intelligence methods, particularly deep neural networks such as convolutional neural networks, offer capabilities for discovering complex biological mechanisms from raw data. However, interpreting the results of these methods in a biomedical context remains a challenge. This study introduces an approach using CNN for nonimage data feature selection, showing promising results for predicting cancer types and identifying key pathways.

BRIEFINGS IN BIOINFORMATICS (2021)

添加到收藏夹

Article Food Science & Technology

Identification of rice-weevil (Sitophilus oryzae L.) damaged wheat kernels using multi-angle NIR hyperspectral data

Liu Zhang et al.

Summary: This study proposed a novel method to identify sound wheat kernels and RW-damaged wheat kernels using multi-angle near-infrared hyperspectral data calibration model. The best hybrid model SNV-SPA-LDA was found through multivariate data analysis, with an accuracy of 97%, sensitivity of 98%, and specificity of 96%. The results indicated the reliability of the calibrated model based on hyperspectral data from four sides of wheat kernel.

JOURNAL OF CEREAL SCIENCE (2021)

添加到收藏夹

Article Chemistry, Analytical

Rice Seed Purity Identification Technology Using Hyperspectral Image with LASSO Logistic Regression Model

Weihua Liu et al.

Summary: This study proposes a hyperspectral rice seed purity identification method based on the LASSO logistic regression model (LLRM), showing that LLRM can consistently select feature wavelength bands and improve recognition accuracy for rice seeds.

SENSORS (2021)

添加到收藏夹

Article Instruments & Instrumentation

A temporal group attention approach for multitemporal multisensor crop classification

Zhengtao Li et al.

INFRARED PHYSICS & TECHNOLOGY (2020)

添加到收藏夹

Article Spectroscopy

Hyperspectral imaging technology combined with deep forest model to identify frost-damaged rice seeds

Liu Zhang et al.

SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY (2020)

添加到收藏夹

Article Chemistry, Analytical

Diagnosis of the Severity of Fusarium Head Blight of Wheat Ears on the Basis of Image and Spectral Feature Fusion

Linsheng Huang et al.

SENSORS (2020)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Squeeze-and-Excitation Networks

Jie Hu et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2020)

添加到收藏夹

Article Plant Sciences

Identification of Bacterial Blight Resistant Rice Seeds Using Terahertz Imaging and Hyperspectral Imaging Combined With Convolutional Neural Network

Jinnuo Zhang et al.

FRONTIERS IN PLANT SCIENCE (2020)

添加到收藏夹

Article Agriculture, Multidisciplinary

Rapid and non-destructive seed viability prediction using near-infrared hyperspectral imaging coupled with a deep learning approach

Te Ma et al.

COMPUTERS AND ELECTRONICS IN AGRICULTURE (2020)

添加到收藏夹

Article Chemistry, Analytical

Prediction of Sweet Corn Seed Germination Based on Hyperspectral Image Technology and Multivariate Data Regression

Huawei Cui et al.

SENSORS (2020)

添加到收藏夹

Article Agricultural Engineering

Non-destructive identification of slightly sprouted wheat kernels using hyperspectral data on both sides of wheat kernels

Liu Zhang et al.

BIOSYSTEMS ENGINEERING (2020)

添加到收藏夹

Article Instruments & Instrumentation

Application of near-infrared hyperspectral imaging for variety identification of coated maize kernels with deep learning

Chu Zhang et al.

INFRARED PHYSICS & TECHNOLOGY (2020)

添加到收藏夹

Article Plant Sciences

Wheat Kernel Variety Identification Based on a Large Near-Infrared Spectral Dataset and a Novel Deep Learning-Based Feature Selection Method

Lei Zhou et al.

FRONTIERS IN PLANT SCIENCE (2020)

添加到收藏夹

Review Chemistry, Analytical

Recent Applications of Multispectral Imaging in Seed Phenotyping and Quality MonitoringAn Overview

Gamal ElMasry et al.

SENSORS (2019)

添加到收藏夹

Article Agriculture, Multidisciplinary

Automated spectral feature extraction from hyperspectral images to differentiate weedy rice and barnyard grass from a rice crop

Yanchao Zhang et al.

COMPUTERS AND ELECTRONICS IN AGRICULTURE (2019)

添加到收藏夹

Article Agriculture, Multidisciplinary

Visualizing distribution of moisture content in tea leaves using optimization algorithms and NIR hyperspectral imaging

Jun Sun et al.

COMPUTERS AND ELECTRONICS IN AGRICULTURE (2019)

添加到收藏夹

Review Biochemical Research Methods

Hyperspectral imaging for seed quality and safety inspection: a review

Lei Feng et al.

PLANT METHODS (2019)

添加到收藏夹

Article Chemistry, Analytical

Noninvasive and Nondestructive Detection of Cowpea Bruchid within Cowpea Seeds with a Hand-Held Raman Spectrometer

Lee Sanchez et al.

ANALYTICAL CHEMISTRY (2019)

添加到收藏夹

Article Agricultural Engineering

Non-destructive identification of maize haploid seeds using nonlinear analysis method based on their near-infrared spectra

Lina Yu et al.

BIOSYSTEMS ENGINEERING (2018)

添加到收藏夹

Article Chemistry, Applied

Classification of white maize defects with multispectral imaging

Kate Sendin et al.

FOOD CHEMISTRY (2018)

添加到收藏夹

Article Spectroscopy

Rapid and visual detection of the main chemical compositions in maize seeds based on Raman hyperspectral imaging

Guiyan Yang et al.

SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY (2018)

添加到收藏夹

Article Biochemical Research Methods

Hyperspectral band selection using genetic algorithm and support vector machines for early identification of charcoal rot disease in soybean stems

Koushik Nagasubramanian et al.

PLANT METHODS (2018)

添加到收藏夹

Article Chemistry, Analytical

THz Spectroscopic Investigation of Wheat-Quality by Using Multi-Source Data Fusion

Hongyi Ge et al.

SENSORS (2018)

添加到收藏夹

Article Chemistry, Analytical

Application of Hyperspectral Imaging and Chemometric Calibrations for Variety Discrimination of Maize Seeds

Xiaolei Zhang et al.

SENSORS (2012)

添加到收藏夹

Article Biochemical Research Methods

Permutation importance: a corrected feature importance measure

Andre Altmann et al.

BIOINFORMATICS (2010)

添加到收藏夹

Article Chemistry, Analytical

Key wavelengths screening using competitive adaptive reweighted sampling method for multivariate calibration

Hongdong Li et al.

ANALYTICA CHIMICA ACTA (2009)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Least squares twin support vector machines for pattern classification

M. Arun Kumar et al.

EXPERT SYSTEMS WITH APPLICATIONS (2009)

添加到收藏夹

Article Chemistry, Multidisciplinary

Random forest: A classification and regression tool for compound classification and QSAR modeling

V Svetnik et al.

JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES (2003)

添加到收藏夹

Article Automation & Control Systems

The successive projections algorithm for variable selection in spectroscopic multicomponent analysis

MCU Araújo et al.

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS (2001)

添加到收藏夹

Identification of Defective Maize Seeds Using Hyperspectral Imaging Combined with Deep Learning

相关参考文献

导出引文

分享论文