scholarly journals Research on forage hyperspectral image recognition based on F-SVD and XGBoost

2021 ◽  
Vol 336 ◽  
pp. 06027
Author(s):  
Xuanhe Zhao ◽  
Xin Pan ◽  
Yubao Ma ◽  
Weihong Yan
Keyword(s):  
Processing Speed ◽  
Time Complexity ◽  
Latent Variable ◽  
Near Infrared ◽  
Hyperspectral Image ◽  
Hyperspectral Images ◽  
Singular Matrix ◽  
Latent Factors ◽  
Time Consumption ◽  
Svd Decomposition

Aiming at the high time complexity and poor accuracy of traditional SVD in hyperspectral recognition. we proposed F-SVD, which introduces the latent factors(F) into the SVD decomposition strategy and uses the correlation between the latent variable and the original variable to improve the singular matrix. Firstly, we used F-SVD to reduce the dimension of visible-near infrared hyperspectral image, and consequently designed a forage recognition model based on XGBoost. When the test set sets 40%, the OA of F-SVD-XGBoost is 91.67%, which takes 0.601s. Compared with the traditional FA-XGBoost and SVD-XGBoost, OA increases 1.98% and 1.67%, and the time consumption decreases 1.369s and 0.522s, respectively. The results show that our model not only effectively extracts the essential features of forage hyperspectral and improves the accuracy of classification, but also has a faster processing speed, so that can efficiently and quickly realize the identification of forage hyperspectral images.

scholarly journals Visualizing Near Infrared Hyperspectral Images with Generative Adversarial Networks

2020 ◽  
Vol 12 (23) ◽  
pp. 3848
Author(s):  
Rongxin Tang ◽  
Hualin Liu ◽  
Jingbo Wei
Keyword(s):  
Near Infrared ◽  
Hyperspectral Image ◽  
Geographic Location ◽  
Hyperspectral Images ◽  
Generative Adversarial Networks ◽  
Landsat 8 ◽  
Multispectral Images ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
Visualization Algorithms

The visualization of near infrared hyperspectral images is valuable for quick view and information survey, whereas methods using band selection or dimension reduction fail to produce good colors as reasonable as corresponding multispectral images. In this paper, an end-to-end neural network of hyperspectral visualization is proposed, based on the convolutional neural networks, to transform a hyperspectral image of hundreds of near infrared bands to a three-band image. Supervised learning is used to train the network where multispectral images are targeted to reconstruct naturally looking images. Each pair of the training images shares the same geographic location and similar moments. The generative adversarial framework is used with an adversarial network to improve the training of the generating network. In the experimental procedure, the proposed method is tested for the near infrared bands of EO-1 Hyperion images with LandSat-8 images as the benchmark, which is compared with five state-of-the-art visualization algorithms. The experimental results show that the proposed method performs better in producing naturally looking details and colors for near infrared hyperspectral images.

Near-infrared hyperspectral image at a glance: Some personal thoughts

NIR news ◽  
2020 ◽  
Vol 31 (5-6) ◽  
pp. 8-14
Author(s):  
José Manuel Amigo
Keyword(s):  
Machine Learning ◽  
Data Mining ◽  
Infrared Spectroscopy ◽  
Hyperspectral Imaging ◽  
Near Infrared Spectroscopy ◽  
Near Infrared ◽  
Hyperspectral Image ◽  
Hyperspectral Images ◽  
Constructive Criticism ◽  
Constructive Discussion

First of all, I want to transmit my most humble thanks to all people who believe that I deserve the “2019 Thomas Hirschfeld” award (kindly supported by FOSS) for my work on near-infrared spectroscopy and, especially, applied on hyperspectral images. I must confess that this award caught me by surprise and that I felt a bit overwhelmed when I received it. It is an honour full of respect and responsibility. I have been given the opportunity of writing this article, and I will profit it to express different personal thoughts about general but relevant aspects of near infrared applied to hyperspectral imaging. Also, since I am more a practitioner in chemometrics (or machine learning or data mining, or …) than a developer, I will also include some insights about the beautiful combination of near-infrared hyperspectral image with chemometrics. This article is just a glimpse of constructive criticism with personal thoughts that comes from my little experience in this field. Therefore, and of course, all opinions here are open for constructive discussion with the only purpose of learning (like the machines do nowadays).

Deep Learning for Dental Hyperspectral Image Analysis

2019 ◽  
Vol 2019 (1) ◽  
pp. 295-299 ◽  
Author(s):  
Oleksandr Boiko ◽  
Joni Hyttinen ◽  
Pauli Fält ◽  
Heli Jäsberg ◽  
Arash Mirhashemi ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Near Infrared ◽  
Hyperspectral Image ◽  
Image Annotation ◽  
Ground Truth ◽  
Hyperspectral Images ◽  
Hyperspectral Image Analysis ◽  
Efficient Detection

The aim of this work is automatic and efficient detection of medically-relevant features from oral and dental hyperspectral images by applying up-to-date deep learning convolutional neural network techniques. This will help dentists to identify and classify unhealthy areas automatically and to prevent the progression of diseases. Hyperspectral imaging approach allows one to do so without exposing the patient to ionizing X-ray radiation. Spectral imaging provides information in the visible and near-infrared wavelength ranges. The dataset used in this paper contains 116 hyperspectral images from 18 patients taken from different viewing angles. Image annotation (ground truth) includes 38 classes in six different sub-groups assessed by dental experts. Mask region-based convolutional neural network (Mask R-CNN) is used as a deep learning model, for instance segmentation of areas. Preliminary results show high potential and accuracy for classification and segmentation of different classes.

scholarly journals Cluster-Wise Weighted NMF for Hyperspectral Images Unmixing with Imbalanced Data

2021 ◽  
Vol 13 (2) ◽  
pp. 268
Author(s):  
Xiaochen Lv ◽  
Wenhong Wang ◽  
Hongfu Liu
Keyword(s):  
Spatial Information ◽  
Hyperspectral Image ◽  
Imbalanced Data ◽  
Reconstruction Error ◽  
Hyperspectral Data ◽  
Weight Matrix ◽  
Hyperspectral Images ◽  
Mixed Data ◽  
Sparsity Constraints ◽  
Additional Constraints

Hyperspectral unmixing is an important technique for analyzing remote sensing images which aims to obtain a collection of endmembers and their corresponding abundances. In recent years, non-negative matrix factorization (NMF) has received extensive attention due to its good adaptability for mixed data with different degrees. The majority of existing NMF-based unmixing methods are developed by incorporating additional constraints into the standard NMF based on the spectral and spatial information of hyperspectral images. However, they neglect to exploit the nature of imbalanced pixels included in the data, which may cause the pixels mixed with imbalanced endmembers to be ignored, and thus the imbalanced endmembers generally cannot be accurately estimated due to the statistical property of NMF. To exploit the information of imbalanced samples in hyperspectral data during the unmixing procedure, in this paper, a cluster-wise weighted NMF (CW-NMF) method for the unmixing of hyperspectral images with imbalanced data is proposed. Specifically, based on the result of clustering conducted on the hyperspectral image, we construct a weight matrix and introduce it into the model of standard NMF. The proposed weight matrix can provide an appropriate weight value to the reconstruction error between each original pixel and the reconstructed pixel in the unmixing procedure. In this way, the adverse effect of imbalanced samples on the statistical accuracy of NMF is expected to be reduced by assigning larger weight values to the pixels concerning imbalanced endmembers and giving smaller weight values to the pixels mixed by majority endmembers. Besides, we extend the proposed CW-NMF by introducing the sparsity constraints of abundance and graph-based regularization, respectively. The experimental results on both synthetic and real hyperspectral data have been reported, and the effectiveness of our proposed methods has been demonstrated by comparing them with several state-of-the-art methods.

scholarly journals Leveraging colour-based pseudo-labels to supervise saliency detection in hyperspectral image datasets

2021 ◽  
Author(s):  
Annalisa Appice ◽  
Angelo Cannarile ◽  
Antonella Falini ◽  
Donato Malerba ◽  
Francesca Mazzia ◽  
...  
Keyword(s):  
Visual Attention ◽  
Hyperspectral Image ◽  
Saliency Detection ◽  
Hyperspectral Images ◽  
Spectral Information ◽  
Imaging Analysis ◽  
Analysis Task ◽  
Visual Attention Mechanism ◽  
Land Use Monitoring ◽  
Research Resources

AbstractSaliency detection mimics the natural visual attention mechanism that identifies an imagery region to be salient when it attracts visual attention more than the background. This image analysis task covers many important applications in several fields such as military science, ocean research, resources exploration, disaster and land-use monitoring tasks. Despite hundreds of models have been proposed for saliency detection in colour images, there is still a large room for improving saliency detection performances in hyperspectral imaging analysis. In the present study, an ensemble learning methodology for saliency detection in hyperspectral imagery datasets is presented. It enhances saliency assignments yielded through a robust colour-based technique with new saliency information extracted by taking advantage of the abundance of spectral information on multiple hyperspectral images. The experiments performed with the proposed methodology provide encouraging results, also compared to several competitors.

scholarly journals Detecting Bacterial Biofilms Using Fluorescence Hyperspectral Imaging and Various Discriminant Analyses

Sensors ◽  
2021 ◽  
Vol 21 (6) ◽  
pp. 2213
Author(s):  
Ahyeong Lee ◽  
Saetbyeol Park ◽  
Jinyoung Yoo ◽  
Jungsook Kang ◽  
Jongguk Lim ◽  
...  
Keyword(s):  
Discriminant Analysis ◽  
Hyperspectral Imaging ◽  
Food Processing ◽  
Nearest Neighbor ◽  
Hyperspectral Image ◽  
Uv Light ◽  
Hyperspectral Images ◽  
K Nearest Neighbor ◽  
E Coli ◽  
Discriminant Analyses

Biofilms formed on the surface of agro-food processing facilities can cause food poisoning by providing an environment in which bacteria can be cultured. Therefore, hygiene management through initial detection is important. This study aimed to assess the feasibility of detecting Escherichia coli (E. coli) and Salmonella typhimurium (S. typhimurium) on the surface of food processing facilities by using fluorescence hyperspectral imaging. E. coli and S. typhimurium were cultured on high-density polyethylene and stainless steel coupons, which are the main materials used in food processing facilities. We obtained fluorescence hyperspectral images for the range of 420–730 nm by emitting UV light from a 365 nm UV light source. The images were used to perform discriminant analyses (linear discriminant analysis, k-nearest neighbor analysis, and partial-least squares discriminant analysis) to identify and classify coupons on which bacteria could be cultured. The discriminant performances of specificity and sensitivity for E. coli (1–4 log CFU·cm−2) and S. typhimurium (1–6 log CFU·cm−2) were over 90% for most machine learning models used, and the highest performances were generally obtained from the k-nearest neighbor (k-NN) model. The application of the learning model to the hyperspectral image confirmed that the biofilm detection was well performed. This result indicates the possibility of rapidly inspecting biofilms using fluorescence hyperspectral images.

scholarly journals Machine Learning-Based Prediction of Selected Parameters of Commercial Biomass Pellets Using Line Scan Near Infrared-Hyperspectral Image

Processes ◽  
2021 ◽  
Vol 9 (2) ◽  
pp. 316
Author(s):  
Lakkana Pitak ◽  
Kittipong Laloon ◽  
Seree Wongpichet ◽  
Panmanas Sirisomboon ◽  
Jetsada Posom
Keyword(s):  
Near Infrared ◽  
Hyperspectral Image ◽  
Thermal Conversion ◽  
High Energy ◽  
Volatile Matter ◽  
Successive Projections Algorithm ◽  
Color Distribution ◽  
Standard Normal Variate ◽  
Distribution Mapping ◽  
Standard Normal

Biomass pellets are required as a source of energy because of their abundant and high energy. The rapid measurement of pellets is used to control the biomass quality during the production process. The objective of this work was to use near infrared (NIR) hyperspectral images for predicting the properties, i.e., fuel ratio (FR), volatile matter (VM), fixed carbon (FC), and ash content (A), of commercial biomass pellets. Models were developed using either full spectra or different spatial wavelengths, i.e., interval successive projections algorithm (iSPA) and interval genetic algorithm (iGA), wavelengths and different spectral preprocessing techniques. Their performances were then compared. The optimal model for predicting FR could be created with second derivative (D2) spectra with iSPA-100 wavelengths, while VM, FC, and A could be predicted using standard normal variate (SNV) spectra with iSPA-100 wavelengths. The models for predicting FR, VM, FC, and A provided R2 values of 0.75, 0.81, 0.82, and 0.87, respectively. Finally, the prediction of the biomass pellets’ properties under color distribution mapping was able to track pellet quality to control and monitor quality during the operation of the thermal conversion process and can be intuitively used for applications with screening.

Determination of starch content in single kernel using near-infrared hyperspectral images from two sides of corn seeds

2020 ◽  
Vol 110 ◽  
pp. 103462
Author(s):  
Chen Liu ◽  
Wenqian Huang ◽  
Guiyan Yang ◽  
Qingyan Wang ◽  
Jiangbo Li ◽  
...  
Keyword(s):  
Near Infrared ◽  
Starch Content ◽  
Hyperspectral Images ◽  
Two Sides

scholarly journals A Distributed Parallel Algorithm Based on Low-Rank and Sparse Representation for Anomaly Detection in Hyperspectral Images

Sensors ◽  
2018 ◽  
Vol 18 (11) ◽  
pp. 3627 ◽  
Author(s):  
Yi Zhang ◽  
Zebin Wu ◽  
Jin Sun ◽  
Yan Zhang ◽  
Yaoqin Zhu ◽  
...  
Keyword(s):  
Anomaly Detection ◽  
Sparse Representation ◽  
Parallel Algorithm ◽  
Hyperspectral Image ◽  
Hyperspectral Images ◽  
Low Rank ◽  
Detection Methods ◽  
Matrix Computations ◽  
Hyperspectral Image Processing ◽  
Mapreduce Model

Anomaly detection aims to separate anomalous pixels from the background, and has become an important application of remotely sensed hyperspectral image processing. Anomaly detection methods based on low-rank and sparse representation (LRASR) can accurately detect anomalous pixels. However, with the significant volume increase of hyperspectral image repositories, such techniques consume a significant amount of time (mainly due to the massive amount of matrix computations involved). In this paper, we propose a novel distributed parallel algorithm (DPA) by redesigning key operators of LRASR in terms of MapReduce model to accelerate LRASR on cloud computing architectures. Independent computation operators are explored and executed in parallel on Spark. Specifically, we reconstitute the hyperspectral images in an appropriate format for efficient DPA processing, design the optimized storage strategy, and develop a pre-merge mechanism to reduce data transmission. Besides, a repartitioning policy is also proposed to improve DPA’s efficiency. Our experimental results demonstrate that the newly developed DPA achieves very high speedups when accelerating LRASR, in addition to maintaining similar accuracies. Moreover, our proposed DPA is shown to be scalable with the number of computing nodes and capable of processing big hyperspectral images involving massive amounts of data.

Sign in / Sign up

Export Citation Format

Share Document