Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method and device for identifying different variety green tea based on multiple spectrum image texture analysis

A multi-spectral image and texture analysis technology, applied in the field of optical analysis of materials, can solve heavy problems and achieve the effect of powerful, accurate identification and online identification

Inactive Publication Date: 2007-10-24
ZHEJIANG UNIV
View PDF0 Cites 55 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the identification process of famous tea, it is relatively easy to identify individual tea pieces, but it is necessary

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
  • Method and device for identifying different variety green tea based on multiple spectrum image texture analysis
  • Method and device for identifying different variety green tea based on multiple spectrum image texture analysis
  • Method and device for identifying different variety green tea based on multiple spectrum image texture analysis

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0027] As shown in Figure 1, it includes a 3CCD multi-spectral imager 1, a light source 2, a dark box 3, a conveyor belt 4, a pulley 5, a motor 6 and a computer 7. Install a dark box 3 on the conveyor belt 4 containing green tea. The dark box 3 is equipped with a light source 2 on both sides, and a 3CCD multi-spectral imager 1 is installed in the middle of the dark box 3. The light source 2 and the 3CCD multi-spectral imager 1 are all aligned on the conveyor belt 4. Green tea, the reflected light received by the 3CCD multi-spectral imager 1 is transmitted to the computer processing system through the RS-232 interface and the image capture card; the motor 6 belt drives the conveyor belt 4 through the pulley 5 to drive.

[0028] The 3CCD multi-spectral imager 1 is a Duncan MS series 3CCD multi-spectral imaging system.

[0029] The frame grabber is PCI1424 or PCI1428 from National Instrument.

[0030] First, a 3CCD multi-spectral imager is used to collect the multi-spectral image of ...

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 method for analyzing and checking different green teas based on multi-spectrum image, and a relative device. The method comprises that first, using a 3CCD camera to obtain three channel images of tea sample synchronously, analyzing the texture character of the image of different green teas in each channel, using texture statistic analysis method or frequency spectrum analysis method to extract the texture character parameters of pretreated tea image, and optimize parameters. The invention can remove the parameters which can not show the common character of different teas and show the character difference between different teas, to obtain the texture character parameters of different teas via parameter correlation analysis, main component analysis and significance analysis. And the optimized character parameter is input a classifier to build quantitative check model which can be used to recognize the kind of sample. The invention can check the kind of green tea quickly, accurately, non-damaged, and online.

Description

technical field [0001] The invention relates to a method for analyzing materials by optical means, in particular to a method and device for identifying different varieties of green tea based on texture analysis of multi-spectral images. Background technique [0002] The quality of tea generally refers to the color, aroma, taste and shape of tea. At the same time, the commodity of tea is strong, and the beautiful shape and glossy color cannot be ignored, and the sensory evaluation of the quality of tea often first examines the shape (including the shape and color of dry tea), especially famous tea, which is The appearance of a shape accounts for 30% of its quality weight. Therefore, the shape of tea leaves is one of the important items that make up the quality of tea leaves. There are many types of tea in our country, and the shapes of tea leaves are gorgeous and colorful. Most of them have a certain artistic quality, which can be tasted and appreciated. Moreover, most of t...

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
IPC IPC(8): G01N21/27G01N21/84G01N33/00
Inventor 何勇李晓丽裘正军陆江峰何超
Owner ZHEJIANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com