A target area extraction method based on hyperspectral imaging to detect the quality of shrimp

A hyperspectral imaging and target area technology, which is applied in the field of target area extraction based on hyperspectral imaging to detect shrimp quality, can solve problems such as few reports on hyperspectral image extraction, and achieve the goal of ensuring shrimp quality and safety, maintaining consumer health, Improve the detection level and the effect of technology

Active Publication Date: 2016-04-13
SOUTH CHINA UNIV OF TECH
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The above inventions and research involve data processing of hyperspectral images, but there are few reports on the extraction of target areas in complex backgrounds for hyperspectral images

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A target area extraction method based on hyperspectral imaging to detect the quality of shrimp
  • A target area extraction method based on hyperspectral imaging to detect the quality of shrimp
  • A target area extraction method based on hyperspectral imaging to detect the quality of shrimp

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0040] As shown in the visible hyperspectral imager adopted in the target area extraction method based on hyperspectral imaging detection of shrimp quality in this embodiment, it includes a computer, an image acquisition card, a camera (using a linear array detector as a sensitive element), an image spectrometer, a lens, Two symmetrically placed halogen lamps, a movable stage and a dark box, in which the camera and image spectrometer are directly connected, they are fixed inside the dark box with the halogen lamp, the image acquisition card is fixed inside the computer, and there is a movable load inside the dark box The computer controls the transmission speed of the movable stage.

[0041] Among them, the hyperspectral camera (DL-604M, Andor, Ireland) of the visible-near-infrared hyperspectral imager has a resolution of 1004×1002 pixels, a spectral range of 328-1115nm, and a spectral resolution of 1.57nm. The hyperspectral image acquisition is to take pictures of the shrimp ...

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

No PUM Login to view more

Abstract

The invention discloses a hyperspectral imaging-based target area extraction method for detecting the shrimp quality. The target area extraction method comprises the steps: firstly, preparing hyperspectral information of a shrimp training sample which is scanned by utilizing a hyperspectral imaging system, pretreating a hyperspectral image, selecting an optimal wavelength range by virtue of analysis of statistical data, establishing a soft support vector machine classification model based on a radial basic core function, detecting a to-be-detected sample of a shrimp, and calculating a target area of the to-be-detected sample of the shrimp. According to the target area extraction method, by adopting a hyperspectral imaging technique, time required in a traditional manual method is obviously reduced, the detection efficiency is improved, and the purpose of automatic, quick, nondestructive and on-line detection can be effectively realized.

Description

technical field [0001] The invention relates to the field of target area extraction in the process of hyperspectral detection and scanning of aquatic products, in particular to a target area extraction method for detecting the quality of shrimp based on hyperspectral imaging. Background technique [0002] Shrimp is an important aquatic product in China and even in the world. It is delicious and nutritious, and is deeply loved by consumers. In recent years, due to the characteristics of accuracy, speed and non-destructiveness of hyperspectral detection, it has developed rapidly in the field of aquatic products. The first problem faced by the hyperspectral detection method is to obtain the target area required for analysis and testing, that is, the position of the target area of ​​interest on the hyperspectral image. Shrimp has the characteristics of small size and irregular shape. When the number of shrimp is large, it is difficult to select the target area and it is easy to...

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
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G01N21/359
Inventor 孙大文代琼曾新安刘丹成军虎
Owner SOUTH CHINA UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap