A method for identifying the quality of Chinese mitten crab based on hyperspectral image technology
A technology of Chinese mitten crab and hyperspectral image, which is applied in the field of fast and non-destructive quality detection of Chinese mitten crab, to achieve the effect of improving recognition speed and recognition accuracy, overcoming slow speed, and ensuring the quality and safety of aquatic products
Active Publication Date: 2021-11-23
JIANGSU UNIV
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] Aiming at the above-mentioned problems and deficiencies of manually grading Chinese mitten crabs, the present invention uses a hyperspectral imaging system to realize accurate prediction of the quality of Chinese mitten crabs, and combines chemometric algorithms to establish a mathematical model to realize fast and accurate quality evaluation of Chinese mitten crabs. ground detection
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0022] The present invention will be further described below in conjunction with accompanying drawing.
[0023] The structure of hyperspectral imaging system based on image spectrometer is as follows: figure 1 shown. The imaging device is mainly composed of a light source, a CCD camera and an image spectrometer. The CCD camera uses a line detector as a sensitive element. When working, the image spectrometer divides the light reflected or transmitted by the detection object into monochromatic light sources and then enters the CCD camera. The system adopts scanning imaging method to obtain hyperspectral images. The line detectors are arranged laterally in the vertical direction of the optical focal plane to complete the lateral scanning (x-axis direction), and can obtain the image information K of each pixel of the object in the strip space at each wavelength i (i=1, 2, 3,..., n; wherein n is a positive integer); at the same time, during the advancing process of the conveyor...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a method for identifying the quality of Chinese mitten crabs based on hyperspectral image technology. Step 1, collecting samples of Chinese mitten crabs: including several female crabs and several male crabs; Step 2, obtaining the quality of Chinese mitten crabs: according to Agricultural standard NY‑5064‑2001 Chinese mitten crab sensory indicators to identify the quality of Chinese mitten crab samples; step 3, collect hyperspectral images and correct them; step 4, obtain spectral information of the region of interest; step 5, extract abdominal spectral features Variables and back image feature variables, PCA analysis is performed on the obtained crab shell surface hyperspectral image and abdomen surface spectral information, and the first three principal components that can represent the original information of the sample are obtained. Back image texture feature information and abdomen spectral information; step 6, Construct identification model, described identification model adopts LS-SVM model; Utilize the identification model that builds to identify the quality of Chinese mitten crab. The invention overcomes the disadvantages of slow manual identification and subjective influence, and improves the intelligent detection level of the Chinese mitten crab.
Description
technical field [0001] The invention belongs to the technical field of non-destructive testing of aquatic products, and in particular relates to a rapid non-destructive testing method for the quality of Chinese mitten crabs based on hyperspectral image technology. Background technique [0002] Chinese mitten crab is an important and valuable aquatic product in my country. It is not only delicious, but also rich in protein, vitamins, calcium, phosphorus, iron and other trace elements, and has high nutritional value. With the continuous improvement of people's quality of life, the demand for Chinese mitten crab is also increasing year by year. As a leader in the aquatic industry, the annual output has reached tens of thousands of tons. In order to meet the growing demand of the market, the aquaculture output of Chinese mitten crabs is also increasing year by year; more than 90% of Chinese mitten crabs in the market are sold in the form of fresh raw materials, and the price has...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G01N21/84G01N21/31G06T7/00G06T7/136G06T7/194
CPCG01N21/31G01N21/84G01N2021/3129G06T7/0002G06T7/136G06T7/194
Inventor 石海军邹小波黄晓玮石吉勇李志华史永强赵号张芳吴胜斌
Owner JIANGSU UNIV