scholarly journals Hyperspectral Imaging for Minced Meat Classification Using Nonlinear Deep Features

2020 ◽  
Vol 10 (21) ◽  
pp. 7783
Author(s):  
Hamail Ayaz ◽  
Muhammad Ahmad ◽  
Manuel Mazzara ◽  
Ahmed Sohaib
Keyword(s):  
Hyperspectral Imaging ◽  
Spatial Information ◽  
Region Of Interest ◽  
Meat Industry ◽  
Food Fraud ◽  
Level Information ◽  
3D Cnn ◽  
Nonlinear Feature Extraction ◽  
Nonlinear Feature ◽  
Minced Meat

Minced meat substitution is one of the most common forms of food fraud in the meat industry. Recently, Hyperspectral Imaging (HSI) has been used for the classification and identification of minced meat types. However, conventional methods are based only on spectral information and ignore the spatial variability of the data. Moreover, these methods first tend to reduce the size of the data, which to some extent ignores the abstract level information and does not preserve the spatial information. Therefore, this work proposes a novel Isos-bestic wavelength reduction method for the different minced meat types, by retaining only Myoglobin pigments (Mb) in the meat spectra. A total of 60 HSI cubes are acquired using Fx 10 Hyperspectral sensor. For each HSI cube, a set of preprocessing schemes is applied to extract the Region of Interest (ROI) and spectral preprocessing, i.e., Golay filtering. Later, these preprocessed HSI cubes are fed into a 3D-Convolutional Neural Network (3D-CNN) model for nonlinear feature extraction and classification. The proposed pipeline outperformed several state-of-the-art methods, with an overall accuracy of 94.0%.

scholarly journals Research on Camouflage Recognition in Simulated Operational Environment Based on Hyperspectral Imaging Technology

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Donge Zhao ◽  
Shuyan Liu ◽  
Xuefeng Yang ◽  
Yayun Ma ◽  
Bin Zhang ◽  
...  
Keyword(s):  
Hyperspectral Imaging ◽  
Spatial Information ◽  
Imaging System ◽  
Recognition Rate ◽  
Region Of Interest ◽  
Practical Significance ◽  
Support Vector ◽  
Operational Environment ◽  
Imaging Technology ◽  
Training Samples

Hyperspectral imaging technology can obtain the spatial information and spectral information of the simulated operational background and its camouflage materials at the same time and identify and classify them according to their differences. In this paper, we collected the hyperspectral images (400–1000 nm) of the desert background, jungle background, desert camouflage netting, jungle camouflage netting, and jungle camouflage clothing through the hyperspectral imaging system, and the samples were preprocessed by denoising and black-and-white correction. Then, we analysed the region of interest (ROI) of the training samples by principal component analysis (PCA). After the pixels in the region of interest and their surrounding areas were averaged, 60% of the data was used as the training samples, and the remaining 40% was used as the test samples. According to their similarities and differences between them and referenced spectrum, the models of classification were established by combining the Naive Bayes (NB) algorithm, K-nearest neighbour (KNN) algorithm, random forest (RF) algorithm, and support vector machine (SVM) algorithm. The results show that among the four models, SVM model has the highest accuracy of classification and the recognition rate of jungle camouflage clothing is the highest. This study verifies the scientific and feasibility of hyperspectral imaging technology for camouflage identification and classification in a simulated operational environment, which has some practical significance.

scholarly journals Chemometric Tools for NIRS and NIR Hyperspectral Imaging

2012 ◽  
Vol 69 (1) ◽  
Author(s):  
Laura M. DALE ◽  
André THEWIS ◽  
Ioan ROTAR ◽  
Juan A. FERNANDEZ PIERNA ◽  
Christelle BOUDRY ◽  
...  
Keyword(s):  
Hyperspectral Imaging ◽  
Near Infrared ◽  
Agricultural Sector ◽  
Spatial Information ◽  
Imaging System ◽  
Agricultural Products ◽  
Chemical Information ◽  
Special Focus ◽  
Large Area ◽  
Analytical Tools

Nowadays in agriculture, new analytical tools based on spectroscopic technologies are developed. Near Infrared Spectroscopy (NIRS) is a well known technology in the agricultural sector allowing the acquisition of chemical information from the samples with a large number of advantages, such as: easy to use tool, fast and simultaneous analysis of several components, non-polluting, noninvasive and non destructive technology, and possibility of online or field implementation. Recently, NIRS system was combined with imaging technologies creating the Near Infrared Hyperspectral Imaging system (NIR-HSI). This technology provides simultaneously spectral and spatial information from an object. The main differences between NIR-HSI and NIRS is that many spectra can be recorded simultaneously from a large area of an object with the former while with NIRS only one spectrum was recorded for analysis on a small area. In this work, both technologies are presented with special focus on the main spectrum and images analysis methods. Several qualitative and quantitative applications of NIRS and NIR-HSI in agricultural products are listed. Developments of NIRS and NIR-HSI will enhance progress in the field of agriculture by providing high quality and safe agricultural products, better plant and grain selection techniques or compound feed industry’s productivity among others.

scholarly journals Comparison of spectral selection methods in the development of classification models from visible near infrared hyperspectral imaging data

2019 ◽  
Author(s):  
Aoife Gowen ◽  
Jun-Li Xu ◽  
Ana Herrero-Langreo
Keyword(s):  
Hyperspectral Imaging ◽  
Near Infrared ◽  
Spatial Information ◽  
Hyperspectral Image ◽  
Imaging Spectroscopy ◽  
Model Performance ◽  
Data Sampling ◽  
Classification Models ◽  
Imaging Data ◽  
Selection Of

Applications of hyperspectral imaging (HSI) to the quantitative and qualitative measurement of samples have grown widely in recent years, due mainly to the improved performance and lower cost of imaging spectroscopy instrumentation. Data sampling is a crucial yet often overlooked step in hyperspectral image analysis, which impacts the subsequent results and their interpretation. In the selection of pixel spectra for the calibration of classification models, the spatial information in HSI data can be exploited. In this paper, a variety of sampling strategies for selection of pixel spectra are presented, exemplified through five case studies. The strategies are compared in terms of the proportion of global variability captured, practicality and predictive model performance. The use of variographic analysis as a guide to the spatial segmentation prior to sampling leads to the selection of representative subsets while reducing the variation in model performance parameters over repeated random selection.

A New Method of Nonlinear Feature Extraction for Multi-Fault Diagnosis of Rotor Systems

2010 ◽  
Vol 41 (10) ◽  
pp. 29-37 ◽  
Author(s):  
Zhixiong Li ◽  
Xinping Yan ◽  
Chengqing Yuan ◽  
Jiangbin Zhao ◽  
Zhongxiao Peng
Keyword(s):  
Feature Extraction ◽  
Fault Diagnosis ◽  
New Method ◽  
Rotor Systems ◽  
Nonlinear Feature Extraction ◽  
Nonlinear Feature
Sign in / Sign up

Export Citation Format

Share Document