Method for counting silicon wafers based on machine vision and image processing

Abstract

The invention discloses a method for counting silicon wafers based on machine vision and 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 battery sheets; step 102, positioning The object to be measured, and the operation area is limited by mask processing; step 103, the image after the mask is copied, and different threshold processing is performed respectively to obtain a denoising binary image; step 104, the obtained denoising binary image Carry out post-processing; 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, so that the binary image highlights the gap And other interference noises are filtered out, and the precise number of slices is finally obtained by 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 silicon wafer counting method based on machine vision and image processing. Background technique [0002] In the production process of solar cells, silicon chips or cells need to be counted after the incoming inspection of raw silicon chips, the factory acceptance of finished cells, and each process in the cell processing process. At present, the widely used counting method is manual visual inspection, which is completed by manual counting in a short period of time, which increases labor costs and is prone to improper operation or counting errors; and the thickness of solar silicon wafers or cells is relatively thin, generally About 180 microns and the silicon wafer or battery is fragile and afraid of pollution. Manual counting cannot meet the above requirements. [0003] With the development of machine vision technology, in the prior art, there is a metho...

AI Technical Summary

Problems solved by technology

At present, the widely used counting method is manual visual inspection, which is completed by manual counting in a short period of time, which increases labor costs and is prone to improper operation or counting errors; and the thickness of solar silicon wafers or cells is relatively thin, generally About 180 microns and the silicon wafer or battery is fragile and afraid of pollution, manual counting cannot meet the above requirements

[0003] With the development of machine vision technology, in the prior art, there is a method of obtaining images through imaging devices to complete counting. This method integrates the computer case and screen with the test case, which makes the test case bulky, and when the case fan is hot, the fan does not work. Vibration will affect the image acquisition quality of the imaging device. In addition, the imaging device does not use a light source, and the image quality of the cells captured inside the chassis is not ideal, thus affecting the counting accuracy. The above improvements cannot meet production needs in actual operation.

Images