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, and belongs to the technical field of image processing. The method comprises the steps of 101, preprocessing on side images of stacked silicon wafers or battery pieces; 102, positioning a measured object, and processing and limiting an operation region by a mask; 103, replicating the images covered with the mask, performing different kinds of threshold processing respectively to obtain a denoised and binarized image; 104, performing post-processing on the obtained denoised and binarized image; and 105, conducting differential statistical counting and positioning to solve the number of the stacked silicon wafers or battery pieces. According to the method, the side images of the stacked solar silicon wafers or battery pieces are collected, the binary image is enabled to highlight gaps and filter out other interference noises, and finally a differential statistical algorithm is adopted to solve the accurate number. By means of the method, a problem of inaccurate counting due to poor quality of the obtained image and high noise is solved, and the counting accuracy and efficiency are improved.

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