A method for counting solar silicon wafers and cells based on image processing
A solar silicon wafer and image processing technology, applied in the field of image processing, can solve the problems of damaged, not widely used, error-prone silicon wafers or battery cells, etc., and achieve the effect of improving counting accuracy and efficiency
Active Publication Date: 2017-02-15
ZHENJIANG SYD TECH CO LTD
View PDF4 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The thickness of solar silicon wafers and solar cells is very thin, generally around 180 microns, with a plus or minus error of 20 microns. There are various counting methods, including manual visual inspection, laser scanning inspection, infrared inspection and machine vision inspection. Manual visual inspection is error-prone and easily causes damage to silicon wafers or cells. Laser inspection and infrared inspection are costly, have low counting accuracy, and are easily restricted by the environment. These inspection technologies are not widely used
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
[0063] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.
[0064] Such as figure 1 Shown, the method for counting solar silicon wafers and cells based on image processing comprises the following steps:
[0065] Step 101, preprocessing the side image of the stacked silicon wafer or battery sheet, such as figure 2 Shown:
[0066] Step 1011, perform median filtering on the side image of the laminated silicon wafer or cell to remove the salt and pepper noise, such as image 3 As shown, among them, image 3 The picture in part a is the side image of the silicon wafer, and the picture in part b is the side image of the solar cell; due to the uneven illumination and the inherent characteristics of the side of the silicon wafer and the cell, it often appears on the obtained side image of the stacked silicon wafer or cell. The salt-and-pepper noise superimposed on the image in the form of black and white d...
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 counting solar silicon wafers and solar cells based on image processing, which belongs to the technical field of image processing and includes the following steps: step 101, preprocessing the side images of stacked silicon wafers or solar cells; step 102 , locate the measured object, and limit the operation area by mask processing; step 103, copy the image after the mask, and perform different threshold processing respectively to obtain a denoising binary image; step 104, obtain denoising binary Post-processing the image; step 105, differential statistical counting and positioning, to obtain the number of measured stacked solar silicon wafers or battery sheets; this method collects side images of stacked solar silicon wafers or battery sheets to make the binary image stand out Filter other interference noises out of the gap, and finally obtain the precise number of slices with a differential statistical algorithm. This method solves the problem of inaccurate counting due to poor image quality and high noise, and improves the counting accuracy and efficiency.
Description
technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a method for counting solar silicon chips and battery chips based on image processing. Background technique [0002] During the production of solar wafers and cells, it is often necessary to count them. The thickness of solar silicon wafers and solar cells is very thin, generally around 180 microns, with a plus or minus error of 20 microns. There are various counting methods, including manual visual inspection, laser scanning inspection, infrared inspection and machine vision inspection. Manual visual inspection is error-prone and easily causes damage to silicon wafers or cells. Laser inspection and infrared inspection are costly, have low counting accuracy, and are easily restricted by the environment. These inspection technologies are not widely used. Due to the characteristics of non-contact, fast speed, high precision and rich lighting schemes, machine v...
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): G06T5/00
Inventor 孙智权张千童钢
Owner ZHENJIANG SYD TECH CO LTD