On the damage of apples based on hyperspectral imaging technology - Database & Sql Blog Articles

Probe domestic high frequency needle JKT-50L high frequency needle with 3 probes

Factory direct 5050 yellow light LED 5050 yellow light 5050 yellow high quality high brightness

With the improvement of people's living standards, consumers are paying more and more attention to the quality and safety of fruits and vegetables. Such as

Fruit damage will not only cause the decay of fruits and vegetables, but also seriously affect the health of consumers. Therefore, rapid and effective detection of fruit damage is very practical. Although the damage of the fruit and the normal area show great similarities in the external features, there is a certain change in the area of ​​the damaged area, and this change can be expressed by the spectrum at a specific wavelength.

Hyperspectral image technology combines the technical advantages of spectral analysis and image processing to detect and analyze the internal and external quality characteristics of the research object.

In this paper, hyperspectral image technology is used to detect the damaged area of ​​fruit to achieve the purpose of common identification of damaged areas.

two,

Test materials and methods

2.1 Experimental materials

In this study, apples were used as research objects to analyze the decayed areas of apples. The decayed area of ​​the apple is naturally formed.

2.2 Experimental equipment

Hyperspectral imaging data acquisition adopts Sichuan Shuangli Hepu Technology Co., Ltd.

GaiaSorter

Hyperspectral sorter system. The system is mainly composed of a hyperspectral imager (V10E),

CCD

Camera, light source, black box, computer, structure and real map

1

. Experimental instrument parameter settings as table

1

.

table

1 GaiaSorter

Hyperspectral sorter system parameters

Serial number

project

parameter

1

Spectral scanning range

/nm

350~1000

2

Spectral resolution

/nm

2.8

3

Collection interval

/nm

1.9

4

Number of spectral channels

520

Figure

1

GaiaSorter

Hyperspectral sorter structure diagram and real map

2.3

Image processing analysis

use

SpecView

with

ENVI/IDL

Preprocessing and analysis of hyperspectral data, mirror transformation in preprocessing, black and white frame calibration

SpecView

In progress; analysis of other data in

ENVI/IDL

In progress.

Third, the results and discussion

3.1

Spectral analysis of apple decay and normal areas

Take 200 pixels of the decayed area and the normal area of ​​the apple, obtain the spectral reflectance of the 200 pixels, and obtain the average reflectance of the 200 pixels, as shown in Figure 2, where red represents the apple. The spectral reflectance of the spectral region of the decayed region, blue represents the spectral reflectance of the normal region, and green represents the spectral reflectance of the pesticide residual region. It can be seen from the figure that in the range of 400-100 nm, the spectral reflectance of the pesticide residue region is the largest, followed by the normal region, and finally the spectral reflectance of the decay region. The study found that these three regions have a peak at 610 nm, a valley at 650 nm, and a steep slope at 650-680 nm. Since all three regions have the above characteristics, it can be considered as a characteristic location unique to apples.

Figure 2 Spectral reflectance of apple decay area, pesticide residue area and normal area

3.

2

Apple rot area extraction

According to the spectral difference between the apple and the background area, the hyperspectral image calibrated by the mirror image and the black and white frame is used to establish the pickled film by using the band calculation of the ENVI/IDL software to obtain the pure apple image, and the principal component analysis of the apple image is performed according to the obtained main component. For the component image, select the principal component image (PC2) which can distinguish the decayed area from the normal area, and obtain the apple decay area by threshold segmentation.

,

as the picture shows. The large part is the decay area and the small part is the pesticide residue area.

Figure 4 Flow chart of apple decay area and agricultural residual area extraction

3.5

discuss

The application of hyperspectral imaging technology to fruit surface damage has demonstrated its superiority of "integration of maps". Slight damage to the fruit often occurs under the epidermis, which is not much different from the color of the normal area and is difficult for the naked eye to recognize. Over time, the damaged area will gradually brown, and eventually the whole fruit will rot and even affect other fruits. The results of this study show that using hyperspectral imaging technology, using principal component analysis, pickling and other methods, can effectively extract fruit damage, so as to achieve rapid detection.