Image-based film mark detection method of scribing machine

Abstract

The invention discloses an image-based film mark detection method of a scribing machine. The image-based film mark detection method comprises the following steps: S1, setting the maximum width and contrast of a tool mark needing to be extracted; s2, after the cutting action of the machine is completed, a lens moves to a cutter feeding position and a cutter discharging position to collect images; s3, obtaining a first-order partial derivative and a second-order partial derivative of the image by using a Gaussian filter; s4, calculating a sub-pixel coordinate, a response and a direction of each pixel point according to the Hesse matrix; s5, performing lagging threshold and link operation on the result to form a plurality of contour lines; and S6, linear regression is performed on the contour line, then a curve conforming to the tool mark is screened out, and the width of the curve is calculated. By the adoption of the film mark detection method, whether the tool mark exists or not is judged, the width of the tool mark is recognized, finally, information of the depth that the blade cuts into the bottom film is obtained, the cutting depth of the next cutting is adjusted, and therefore the purpose that the cutting depth is accurate and free of manual control is achieved.

Description

technical field [0001] The invention relates to the technical field of dicing machines, in particular to an image-based film mark detection method for dicing machines. Background technique [0002] When the dicing machine cuts LED chips or wafer products, it usually has higher requirements for cutting depth. Generally, the blade just cuts into the bottom film, or cuts into the bottom film by 5-10 microns, so that it can just cut through the product. It can effectively control back collapse while maintaining the excellent characteristics of the product. However, the horizontal accuracy of the working disk of the dicing machine is difficult to meet the above-mentioned standards, generally above 3 microns. The larger the size of the working disk, the greater the error, and the more difficult it is to guarantee the accuracy. It is reflected in the use of the machine that when cutting the product, the knife marks formed by the blade on the bottom film of the knife entering and e...

AI Technical Summary

Problems solved by technology

[0003] The invention proposes a film mark detection method to solve the problem that the cutting depth must be controlled by manual experience

Images