Estimation of rice protein content before harvest using ground-based hyperspectral imaging and region of interest analysis

2017 ◽  
Vol 19 (4) ◽  
pp. 721-734 ◽  
Author(s):  
Hiroyuki Onoyama ◽  
Chanseok Ryu ◽  
Masahiko Suguri ◽  
Michihisa Iida
Keyword(s):  
Protein Content ◽  
Hyperspectral Imaging ◽  
Region Of Interest ◽  
Rice Protein

Protein content evaluation of processed pork meats based on a novel single shot (snapshot) hyperspectral imaging sensor

2019 ◽  
Vol 240 ◽  
pp. 207-213 ◽  
Author(s):  
Ji Ma ◽  
Da-Wen Sun ◽  
Hongbin Pu ◽  
Qingyi Wei ◽  
Xiaomei Wang
Keyword(s):  
Protein Content ◽  
Hyperspectral Imaging ◽  
Single Shot ◽  
Content Evaluation ◽  
Imaging Sensor

scholarly journals Application of Visible and Near-Infrared Hyperspectral Imaging to Determine Soluble Protein Content in Oilseed Rape Leaves

Sensors ◽  
2015 ◽  
Vol 15 (7) ◽  
pp. 16576-16588 ◽  
Author(s):  
Chu Zhang ◽  
Fei Liu ◽  
Wenwen Kong ◽  
Yong He
Keyword(s):  
Protein Content ◽  
Hyperspectral Imaging ◽  
Oilseed Rape ◽  
Soluble Protein ◽  
Near Infrared ◽  
Soluble Protein Content

Detection of the Protein Content of Ningxia Tan Sheep Using Hyperspectral Reflectance Imaging

2014 ◽  
Vol 513-517 ◽  
pp. 4235-4238
Author(s):  
Song Lei Wang ◽  
Gui Shan Liu ◽  
Xue Fu Li ◽  
Rui Ming Luo
Keyword(s):  
Protein Content ◽  
Hyperspectral Imaging ◽  
Near Infrared ◽  
Mean Squared Error ◽  
Imaging Technique ◽  
Linear Regression Analysis ◽  
Scatter Correction ◽  
Squared Error ◽  
Tan Sheep ◽  
Well Correlation

Near-infrared (NIR) hyperspectral imaging technique (900-1700nm) was evaluated to predict the protein content of Tan sheep. This research adopted NIR hyperspectral imaging to get imaging information of 72 mutton samples, multiplicative scatter correction was used to spectral data preprocessing. The optimal wavelengths were obtained through linear-regression analysis, BP neural network combined with actual measured values were established the prediction model and verified this model. The results showed that the prediction effect of model was very well. Correlation coefficient (Rp) and root mean squared error of prediction (RMSEP) of the protein were 0.87 and 1.19. The results indicated that it is feasible to predict the protein content of Tan sheep for NIR hyperspectral imaging technique.

Development of simplified models for nondestructive testing of rice (with husk) protein content using hyperspectral imaging technology

2021 ◽  
Vol 114 ◽  
pp. 103230
Author(s):  
Chengye Ma ◽  
Zhishang Ren ◽  
Zhehao Zhang ◽  
Juan Du ◽  
Chengqian Jin ◽  
...  
Keyword(s):  
Nondestructive Testing ◽  
Protein Content ◽  
Hyperspectral Imaging ◽  
Simplified Models ◽  
Imaging Technology

scholarly journals Protein content prediction in single wheat kernels using hyperspectral imaging

2018 ◽  
Vol 240 ◽  
pp. 32-42 ◽  
Author(s):  
Nicola Caporaso ◽  
Martin B. Whitworth ◽  
Ian D. Fisk
Keyword(s):  
Protein Content ◽  
Hyperspectral Imaging ◽  
Wheat Kernels

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%.

Sign in / Sign up

Export Citation Format

Share Document