- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Detection of adulteration with duck meat in minced lamb meat by using visible near-infrared hyperspectral imaging
摘要： This paper described a rapid and non-destructive method based on visible near-infrared (Vis-NIR) hyperspectral imaging system (400–1000 nm) for detection adulteration with duck meat in minced lamb. The multiple average of the reference spectral and a predicted relative spatial distribution coe?cient were applied in this study to reduce the noise of the spectra. The PLSR model with selected wavelengths achieved better results than others with determination of coe?cients (R2 P) of 0.98, and standard error of prediction (RMSEP) of 2.51%. And the prediction map of the duck minced in lamb meat was generated by applying the prediction model. The results of this study indicate the great potential of the hyperspectral technology applying to rapidly and accurately detect the meat adulteration in minced lamb meat.
关键词： Hyperspectral imaging,Minced lamb meat,PLSR,Duck meat,Adulteration
更新于2025-09-10 09:29:36
-
Fast Parallel Implementation of Dual-Camera Compressive Hyperspectral Imaging System
摘要： Coded aperture snapshot spectral imager (CASSI) provides a potential solution to recover the 3D hyperspectral image (HSI) from a single 2D measurement. The latest proposed design of dual-camera compressive hyperspectral imager (DC-CHI) can collect more information simultaneously with CASSI to improve the reconstruction quality. The main bottleneck now lies in the high computation complexity of the reconstruction methods, which hinders the practical application. In this paper, we propose a fast parallel implementation based on DCCHI to reach a stable and efficient HSI reconstruction. Specifically, we develop a new optimization method for the reconstruction problem, which integrates the alternative direction multiplier method (ADMM) with the total variation (TV) based regularization to boost the convergence rate. Then, to improve the time efficiency, a novel parallel implementation based on GPU is proposed. The performance of the proposed method is validated on both synthetic and real data. The experiment results demonstrate our method has a significant advantage in time efficiency while maintaining a comparable reconstruction fidelity.
关键词： GPU,fast reconstruction,Compressive sensing (CS),hyperspectral imaging
更新于2025-09-10 09:29:36
-
Excitation-Tunable Tip-Enhanced Raman Spectroscopy
摘要： Tip-enhanced Raman spectroscopy is a powerful tool to investigate chemical composition, for obtaining molecular information, and for recording images with a spatial resolution on the nanometer scale. However, it typically has been limited to a fixed excitation wavelength. We demonstrate excitation-dependent hyperspectral imaging by implementing a wavelength tunable laser to our TERS setup. Varying the excitation wavelength during TERS experiments is a key to perform spatially resolved resonant Raman scattering (RRS) with nanometer resolution, which enables mapping of transition centers and to study for example the quantum properties of electrons and phonons. To present the application potential and to verify the setup, we recorded excitation-dependent hyperspectral nanoimages of a densely packed film of carbon nanotubes (CNTs) on an Au surface and use the spectral position and intensity of the radial breathing modes for a unique assignment of the CNTs. We succeeded in identifying and imaging at least nine different tube species. The nanoimages revealed the exact position and the distribution of certain CNTs inside the film. e-TERS will have manifold application in nanoimaging, for chemical analysis and electronic studies on the nanometer scale, making it highly interesting in fields ranging from biomedicine and chemistry to material science.
关键词： nanoimaging,Tip-enhanced Raman spectroscopy,resonant Raman scattering,carbon nanotubes,hyperspectral imaging
更新于2025-09-09 09:28:46
-
Simultaneous species and sex identification of silkworm pupae using hyperspectral imaging technology
摘要： To obtain high-quality raw silk and improve the economic values of sericulture industry, sex needs to be discriminated first before cross-breeding. Much work has been reported about sex identification. However, to realize automatic separation of silkworm pupae, the species also needs to be classified, which no research has ever explored. Hence, this paper studied the feasibility of visible and near-infrared hyperspectral imaging technology to identify the species and sex of silkworm pupae. 288 hyperspectral images of silkworm pupae were collected and the average spectra were extracted from the region of interest, around the tail region of silkworm pupae. Successive projection algorithm was served as a variable selection method to choose the optimal wavelengths from the full spectra. At the same time, principal component analysis was used to choose the characteristic images. Then, the gray-level co-occurrence matrix was implemented on the first three principal component images (accounted for 99.05% of the total variances) to extract 48 textural features. Partial least squares discriminant analysis and support vector machine models were built, respectively, based on the spectral data, textural data and fusion data that included spectral and textural data, in which the support vector machine model based on the fusion data, gave the best species and sex identification result with an accuracy of 95.83%. It demonstrated that the hyperspectral imaging technology could be a new and nondestructive method to replace the manual work.
关键词： silkworm pupa,species,identification sex,Hyperspectral imaging
更新于2025-09-09 09:28:46
-
Hyperspectral Imaging Classification based on a Convolutional Neural Network with Adaptive Windows and Filters Sizes
摘要： Image classification by the Convolutional Neural Networks (CNN) has shown its great performances in recent years, in several areas, such as image processing and pattern recognition; However, there is still some improvement to do. The main problem in CNN is the initialization of the number and size of the filters, which can obviously change the results. In this article, we assign three major contributions, based on the CNN model; (1) adaptive selection of the number of filters. (2) using an adaptive size of the windows. (3) using an adaptive size of the filters. The tests results, applied to different hyperspectral datasets (SalinasA, Pavia University, and Indian Pines), have proven that this framework is able to improve the accuracy of the HSI classification.
关键词： Adaptive Filters,Convolutional Neural Networks,Image Classification,Hyperspectral Imaging
更新于2025-09-09 09:28:46
-
Using Hyperspectral Data to Identify Crops in a Cultivated Agricultural Landscape - A Case Study of Taita Hills, Kenya
摘要： Recent advances in hyperspectral remote sensing techniques and technologies allow us to more accurately identify larger range of crop species from airborne measurements. This study employs hyperspectral AISA Eagle VNIR imagery acquired with 9 nm spectral and 0.6 m spatial resolutions over a spectral range of 400 nm to 1000 nm. The area of study is the Taita hills in Kenya. Various crops are grown in this region basically for food and as an economic activity. The crops addressed are: maize, bananas, avocados, and sugarcane and mango trees. The main objectives of this study were to study what crop species can be distinguished from the cultivated population crops in the agricultural landscape and what feature space discriminates most effectively the spectral signatures of different species. Spectral Angle Mapper (SAM) algorithm together with some dissimilarity concepts was applied in this work. The spectral signatures for crops were collected using accurate field plot maps. Accuracy assessment was done using independent training vector data. We achieved an overall accuracy of 77% with a kappa value of 0.67. Various crops in different locations were identified and shown.
关键词： Spectral angle mapper,Hyperspectral imaging,Spectral signatures,Spectral variation,Crop identification
更新于2025-09-09 09:28:46
-
Hyperspectral Terahertz Tomography in Amplitude Contrast
摘要： Hyperspectral Terahertz Tomography in amplitude contrast is presented using a time-domain spectroscopy system in the spectral range 0.3 - 2.5 THz. The Fourier transformed signal data is used to reconstruct test objects’ cross-sections at multiple frequencies using standard filtered backprojection. The full hyperspectral set of images reconstructed at around 300 adjacent spectral points is used to trace the combined contribution of Beer-Lambert volume attenuation, Fresnel reflection losses and Rayleigh roughness scattering losses, which is in good overall agreement with the experimental results. The image quality for Styrofoam (refractive index around 1.02, attenuation coefficient < 1 mm-1) test objects is best in the range 0.8 - 2.0 THz depending on the porosity of the material.
关键词： THz,time-domain spectroscopy,hyperspectral imaging,Rayleigh roughness,hard-field tomography
更新于2025-09-09 09:28:46
-
Hyperspectral Tissue Image Segmentation using Semi-Supervised NMF and Hierarchical Clustering
摘要： Hyperspectral imaging (HSI) of tissue samples in the mid-infrared (mid-IR) range provides spectro-chemical and tissue structure information at sub-cellular spatial resolution. Disease-states can be directly assessed by analyzing the mid-IR spectra of different cell-types (e.g. epithelial cells) and sub-cellular components (e.g. nuclei), provided we can accurately classify the pixels belonging to these components. The challenge is to extract information from hundreds of noisy mid-IR bands at each pixel, where each band is not very informative in itself, making annotations of unstained tissue HSI images particularly tricky. Because the tissue structure is not necessarily identical between the two sections, only a few regions in unstained HSI image can be annotated with high confidence, even when serial (or adjacent) H&E stained section is used as a visual guide. In order to completely use both labeled and unlabeled pixels in training images, we have developed an HSI pixel classification method that uses semi-supervised learning for both spectral dimension reduction and hierarchical pixel clustering. Compared to supervised classifiers, the proposed method was able to account for the vast differences in spectra of sub-cellular components of the same cell-type and achieve an F1-score of 71.18% on two-fold cross-validation across 20 tissue images. To generate further interest in this promising modality we have released our source code and also showed that disease classification is straightforward after HSI image segmentation.
关键词： microspectroscopy,semi-supervised learning,hierarchical clustering,Hyperspectral imaging,non-negative matrix factorization
更新于2025-09-09 09:28:46
-
Compressive Hyperspectral Imaging With Spatial and Spectral Priors
摘要： This paper proposes a new compressive hyperspectral imaging method, including the design of a cost-effective distributed sampling (DS) scheme and an efficient reconstruction model. The new sampling scheme, named as distributed separate sampling (DSS), encodes different hyperspectral bands with mutually independent two-dimensional separate sensing operators. Compared with existing DS schemes, DSS reduces lots of resource overhead in the premise of generating measurements with low redundancy. Furthermore, in contrast to the existing DS schemes, DSS keeps the original structure of hyperspectral images (HSIs) during sampling procedure. The new joint reconstruction model, namely, joint nuclear/total variation/L1 norm minimization, exploits both spatial and spectral priors of HSIs. Unlike the other joint reconstruction models, the proposed model utilize an L1 -based distance function to measure the similarity between adjacent bands, which improves the recovery quality of HSIs. Besides, we develop a new compressive inversion algorithm under the split Bregman framework, which is of low computational complexity, to solve our proposed reconstruction model. Comprehensive experimental results demonstrate the efficiency of our method.
关键词： Compressive hyperspectral imaging (CHI),split Bregman,joint reconstruction,distributed sampling (DS)
更新于2025-09-09 09:28:46
-
An sparsity-based approach for spectral image target detection from compressive measurements acquired by the CASSI architecture
摘要： Hyperspectral imaging requires handling a large amount of multidimensional spectral information. Hyperspectral image acquisition, processing, and storage are computationally and economically expensive and, in most cases, slow processes. In recent years, optical architectures have been developed for acquisition of spectral information in compressed form by using a small set of measurements coded by a spatial modulator. This article formulates a processing scheme that allows the measurements acquired by such compressive sampling systems to be used to perform spectral detection of targets, by adapting traditional detection algorithms for use in the compressive sampling model, and shows that the performance is comparable with that obtained by detection processes without compression.
关键词： hyperspectral imaging,compressive sensing,target detection,sparsity model
更新于2025-09-09 09:28:46