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

Automatic color identification and classification method for polycrystalline cell images

An automatic recognition and classification method technology, applied in the field of image processing, can solve problems such as inability to meet accurate color recognition and classification, color difference does not fully conform to visual effects, uneven color space model, etc., and is suitable for large-scale promotion and application. Fast sorting and fast recognition effects

Inactive Publication Date: 2017-11-14
SHANGHAI DIANJI UNIV
View PDF7 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The RGB color space model is a device-related and uneven color space model. The color difference obtained according to the spatial distance does not fully conform to the human visual effect, and cannot meet the technical requirements for accurate color recognition and classification.

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
  • Automatic color identification and classification method for polycrystalline cell images
  • Automatic color identification and classification method for polycrystalline cell images
  • Automatic color identification and classification method for polycrystalline cell images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] The present invention will be further elaborated below in conjunction with the accompanying drawings and specific embodiments.

[0051] like Figure 1 ~ Figure 3 As shown, the color automatic recognition and classification method of the polycrystalline cell image of the present invention,

[0052] The steps are as follows:

[0053] (1) Obtain an image of the real color of the surface of the polycrystalline cell;

[0054] (2) performing preprocessing such as rotating, extracting, filtering and correcting the image obtained in step (1);

[0055] (3) Image segmentation is performed on the image obtained in step (2), and several adjacent pixels with similar characteristics such as color and brightness are segmented into a sub-region. The entire image contains at least one sub-region, and the weight W of each sub-region is calculated. ;

[0056] (4) Calculate the average value of the RGB of each sub-region in step (3) And convert it to CIELAB uniform color space, get t...

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

An automatic color identification and classification method for polycrystalline cell images includes the following steps: rotating, extracting, filtering and correcting an obtained image in advance; segmenting the image, classifying a plurality of adjacent pixels with similar color and brightness features to the same sub-region, and calculating the weight W of each sub-region, wherein the image contains at least one sub-region; calculating the average value of RGB (R<->, G<->, B<->) of each sub-region and transforming the average value to a CIELAB uniform color space, and determining the dominant visual color of the image and (L*, a*, b*) thereof in a CIELAB approximate uniform color space according to the weights W of the sub-regions and the color difference values of the sub-regions; and calculating the three attributes of color corresponding to (L*, a*, b*), namely, hue Hab*, lightness L* and chroma Cab*, in the CIELAB approximate uniform color space.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method for automatic color recognition and classification of polycrystalline cell images. Background technique [0002] The manufacturing process of polycrystalline silicon solar cells determines the complexity of the color inside the cell, and the color of each polycrystalline silicon solar cell is different from each other. The surface color of polysilicon solar cells generally shows a gradual change, although the main tone of its color is blue, but it is also ever-changing. If photovoltaic modules contain cells of different colors, it will inevitably affect the consistency of the appearance of the modules. With the rapid promotion and application of distributed photovoltaic power plants, the application market has also put forward higher requirements for the overall appearance and color of photovoltaic building integration. Currently, solar cell manufacturers rout...

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): G06K9/34G06K9/46G06T7/11G06T7/90
CPCG06T7/11G06T7/90G06V10/267G06V10/56
Inventor 祁永庆
Owner SHANGHAI DIANJI 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