scholarly journals Nondestructive Detection for Egg Freshness Based on Hyperspectral Scattering Image Combined with Ensemble Learning

Sensors ◽  
2020 ◽  
Vol 20 (19) ◽  
pp. 5484
Author(s):  
Dejian Dai ◽  
Tao Jiang ◽  
Wei Lu ◽  
Xuan Shen ◽  
Rui Xiu ◽  
...  
Keyword(s):  
Light Source ◽  
Ensemble Learning ◽  
Incident Angle ◽  
Angle Of Incidence ◽  
Non Destructive Testing ◽  
Destructive Testing ◽  
Potential Applications ◽  
Nondestructive Testing Method ◽  
Non Destructive ◽  
Egg Freshness

Scattering hyperspectral technology is a nondestructive testing method with many advantages. Here, we propose a method to improve the accuracy of egg freshness, research the influence of incident angles of light source on the accuracy, and explain its mechanism. A variety of weak classifiers classify eggs based on the spectra after preprocessing and feature wavelength extraction to obtain three classifiers with the highest accuracy. The three classifiers are used as metamodels of stacking ensemble learning to improve the highest accuracy from 96.25% to 100%. Moreover, the highest accuracy of scattering, reflection, transmission, and mixed hyperspectral of eggs are 100.00%, 88.75%, 95.00%, and 96.25%, respectively, indicating that the scattering hyperspectral for egg freshness detection is better than that of the others. In addition, the accuracy is inversely proportional to the angle of incidence, i.e., the smaller the incident angle, the camera collects a larger proportion of scattering light, which contains more biochemical parameters of an egg than that of reflection and transmission. These results are very important for improving the accuracy of non-destructive testing and for selecting the incident angle of a light source, and they have potential applications for online non-destructive testing.

scholarly journals Nondestructive Detection for Egg Freshness based on Hyperspectral Scattering Image combined with Ensemble Learning

2020 ◽  
Author(s):  
Dejian DAI ◽  
Tao JIANG ◽  
Wei LU ◽  
Xuan SHEN ◽  
Rui XIU ◽  
...  
Keyword(s):  
Light Source ◽  
Ensemble Learning ◽  
Incident Angle ◽  
Angle Of Incidence ◽  
Non Destructive Testing ◽  
Destructive Testing ◽  
Potential Applications ◽  
Nondestructive Testing Method ◽  
Non Destructive ◽  
Egg Freshness

Scattering hyperspectral technology is a nondestructive testing method with many advantages. Here, we propose a method to improve the accuracy of egg freshness, research the influence of incident angles of light source on the accuracy and explain its mechanism. A variety of weak classifiers classify eggs based on the spectra after preprocessing and feature wavelength extraction to obtain three classifiers with the highest accuracy. The three classifiers are used as metamodels of stacking ensemble learning to improve the highest accuracy from 96.25% to 100%. Moreover, the highest accuracy of scattering, reflection, transmission and mixed hyperspectral of eggs are 100.00%, 88.75%, 95.00% and 96.25%, respectively, indicating that the scattering hyperspectral for egg freshness detection is better than that of the others. In addition, the accuracy is inversely proportional to the angle of incidence due that the smaller the incident angle, the camera collects a larger proportion of scattering light, which contains more biochemical parameters of an egg than that of reflection and transmission. These results are very important for improving the accuracy of non-destructive testing and selecting the incident angle of the light source, and have potential applications in online non-destructive testing.

scholarly journals The effect of the diameter of the detector collimator on saturation thickness in gamma scattering measurement

2017 ◽  
Vol 1 (T3) ◽  
pp. 68-78
Author(s):  
Chuong Dinh Huynh ◽  
Nguyen Hoang Vo ◽  
Trang Thi Ngoc Le ◽  
Linh Thi Truc Nguyen ◽  
Tuyet Kim Tran ◽  
...  
Keyword(s):  
Gamma Ray ◽  
Incident Angle ◽  
Target Thickness ◽  
Processing Technique ◽  
Scattering Method ◽  
Non Destructive Testing ◽  
Destructive Testing ◽  
Saturation Thickness ◽  
Non Destructive ◽  
Scattering Measurement

The effect of the diameter of the detector collimator on the saturation thickness in gamma-scattering measurements is studied using the spectrum of singly scattering. Geometric arrangement of gamma-scattering measurement includes: a gamma-ray collimated beam with the energy of 662 keV emitted from 137Cs source is irradiated on a rectangular aluminium target with incident angle of 90o, and detector NaI(Tl) 5.1cmx5.1cm with collimator is used to record the scatterd gamma rays at scattered angle of 120°. The experimental measurements are carried out to obtain scattered spectra with various target thickness and diameter of detector collimator. The profile of the singly scattering and multiply scattering in the scattered spectra are determined by a spectrum processing technique based on the least squares fitting. The experimental results showed that the saturation thickness of the counts of singly scattering increases with increasing the window diameter of the detector collimator. These results will support for the non-destructive testing research of application of gamma-scattering method to determine the thickness or the defect of the sample.

scholarly journals A Modified Wavenumber Algorithm of Multi-Layered Structures with Oblique Incidence Based on Full-Matrix Capture

2021 ◽  
Vol 11 (22) ◽  
pp. 10808
Author(s):  
Bei Yu ◽  
Haoran Jin ◽  
Yujian Mei ◽  
Jian Chen ◽  
Eryong Wu ◽  
...  
Keyword(s):  
Wave Field ◽  
Oblique Incidence ◽  
Incident Angle ◽  
Layered Structures ◽  
Non Destructive Testing ◽  
Destructive Testing ◽  
Extended Phase ◽  
Full Matrix ◽  
Coordinate Rotation ◽  
Non Destructive

Full-matrix capture (FMC)-based ultrasonic imaging provides good sensitivity to small defects in non-destructive testing and has gradually become a mainstream research topic. Many corresponding algorithms have been developed, e.g., the total focusing method (TFM). However, the efficiency of the TFM is limited, especially in multi-layered structures. Although the appearance of wavenumber algorithms, such as extended phase-shift migration (EPSM) methods, has improved imaging efficiency, these methods cannot be applied to cases with oblique incidence. Therefore, a modified wavenumber method for full-matrix imaging of multi-layered structures with oblique array incidence is proposed. This method performs a coordinate rotation in the frequency domain to adapt it to the oblique incidence. It then utilizes wave-field extrapolation to migrate the transmitting and receiving wave field to each imaging line, and a correlation imaging condition is used to reconstruct a total focused image. The proposed method can deal with any incident angle without precision loss. Moreover, it inherits the computational efficiency advantages of the wavenumber algorithms. The simulation and experimental results show that the proposed method performs better in terms of accuracy and efficiency than the TFM. Specifically, it is nearly 60 times faster than the TFM when processing an FMC dataset with a size of 4096 × 64 × 64.

Non destructive testing of works of art by terahertz analysis

2013 ◽  
Vol 64 (2) ◽  
pp. 21001 ◽  
Author(s):  
Jean-Luc Bodnar ◽  
Jean-Jacques Metayer ◽  
Kamel Mouhoubi ◽  
Vincent Detalle
Keyword(s):  
Non Destructive Testing ◽  
Destructive Testing ◽  
Works Of Art ◽  
Non Destructive

Modeling of a sensitive element on a planar mushroom-shaped metamaterial for non-destructive testing and searching for inhomogeneities in technological media

2020 ◽  
pp. 54-59
Author(s):  
A. A. Yelizarov ◽  
A. A. Skuridin ◽  
E. A. Zakirova
Keyword(s):  
Sensitive Element ◽  
Non Destructive Testing ◽  
Destructive Testing ◽  
Resonant Frequency Shift ◽  
Maltese Cross ◽  
Informative Parameters ◽  
Non Destructive ◽  
Cross Type ◽  
Electrodynamic Structure ◽  
Electrophysical Parameters

A computer model and the results of a numerical experiment for a sensitive element on a planar mushroom-shaped metamaterial with cells of the “Maltese cross” type are presented. The proposed electrodynamic structure is shown to be applicable for nondestructive testing of geometric and electrophysical parameters of technological media, as well as searching for inhomogeneities in them. Resonant frequency shift and change of the attenuation coefficient value of the structure serve as informative parameters.

STUDY OF HOMOGENEITY, POROSITY AND INTERNAL DEFECTS IN AERATED AND EPS AGGREGATE POLY BRICKS USING NEUTRON RADIOGRAPHY TECHNIQUE

2015 ◽  
Vol 7 (2) ◽  
pp. 1428-1439
Author(s):  
Khurshed Alam ◽  
Md. Sayeedur Rahman ◽  
Md. Mostafizur Rahman ◽  
S. M. Azaharul Islam
Keyword(s):  
Optical Density ◽  
Neutron Radiography ◽  
Density Variation ◽  
Expanded Polystyrene ◽  
Elemental Distribution ◽  
Non Destructive Testing ◽  
Internal Defects ◽  
Destructive Testing ◽  
Radiographic Images ◽  
Non Destructive

A powerful non-destructive testing (NDT) technique is adopted to study the internal defects and elemental distribution/homogeneity and porosity of aerated brick and EPS aggregate poly brick samples. In the present study the internal defects like homogeneity, porosity, elemental distribution, EPS aggregate and aerator distributor in the test samples have been observed by the measurement of gray value/optical density of the neutron radiographic images of these samples. From this measurement it is found that the neutron intensity/optical density variation with the pixel distance of the AOI of the NR images in both expanded polystyrene (EPS) aggregate poly brick and aerated brick samples comply almost same in nature with respect to the whole AOI but individually each AOI shows different nature from one AOI to another and it confirms that the elemental distribution within a AOI is almost homogeneous. Finally it was concluded that homogeneity, elemental distribution in the EPS aggregate poly brick sample is better than that of the aerated brick sample. 

Sign in / Sign up

Export Citation Format

Share Document