High-precision measurement method for reflective workpiece based on machine vision

Abstract

The invention discloses a high-precision measurement method for a reflective workpiece based on machine vision. The high-precision measurement method comprises the following steps that a. imaging of the surface of a workpiece having a concave part is performed by using a visual system; b. the concave part is dyed so that the concave part is enabled to form color difference relative to the non-concave part of the surface of the workpiece; and c. imaging of the surface of the workpiece is performed again, and the imaging result is uploaded to a computer to perform image processing. The concave part of the surface of the workpiece is dyed and the concave part is enabled to form color difference and contrast relative to the non-concave part so that the concave part and the non-concave part are distinguished by the visual system, and then image processing is performed by utilizing the computer so that the contour of the reflective workpiece is obtained. According to the method, high-precision measurement can be performed on the reflective workpiece, a feature recognition algorithm is optimized to a great extent and thus detection efficiency can be enhanced. The high-precision measurement method can be used for high-precision measurement of the contour of the reflective workpiece.

Description

technical field [0001] The invention relates to the field of measuring reflective workpieces, in particular to a high-precision measuring method for reflective workpieces based on machine vision. Background technique [0002] With the rise of labor costs, manpower is gradually replaced by machines. Among them, people gradually use machine vision instead of manual measurement, which can greatly improve efficiency and reduce costs. [0003] Machine vision is the use of machines instead of human eyes for measurement and judgment. The machine vision system refers to converting the ingested target into an image signal through machine vision products (that is, the image capture device, which is divided into CMOS and CCD), and sending it to a dedicated image processing system to obtain the shape information of the captured target. According to the pixel distribution And brightness, color and other information are converted into digital signals; the image system performs various op...

AI Technical Summary

Problems solved by technology

There are also certain technical bottlenecks in the use of machine vision to identify reflective workpieces. The main problem lies in: the contrast between the contour to be detected and the background area is extremely small, and the contour features in the image captured by the camera are very difficult to extract, even if they are extracted through complex algorithms. , the robustness of the system is also very poor, the application of lighting can extract part of the contour information, but it cannot fully meet the measurement requirements

The lighting method must also be compatible with the image recognition algorithm, and the general image recognition algorithm cannot be resolved even under complex reflective conditions.

[0006] For this reason, most of the workpiece measurements are now manual, but manual measurement requires the use of a projector to measure the inner contour of the workpiece. The disadvantage is that the working hours are long and the efficiency is low.

Images