3. Automatic detection of PET beverage bottle appearance defects by machine vision
With the increasing demand for disposable injection needles in the market and the requirements of customers for product quality, more and more medical device manufacturers use automatic injection needle detection system to comprehensively detect the appearance defects of disposable injection needles. This method replaces the traditional manual method to improve the production efficiency and product quality, solves the problem of false detection and missing detection caused by the low efficiency and slow speed of the manual method, as well as the uncertainty factors such as subjective constraints of the detection personnel, and realizes better 100% product online detection.
3.1 overview of machine vision system
Machine vision system is to capture the image through the image capturing device (including CMOS camera and CCD camera), then transfer the image to the processing unit, and judge the size, shape and color according to the pixel distribution, brightness, color and other information through digital processing. Then, according to the result of discrimination, the equipment action on site is controlled.
3.2 automatic detection scheme of appearance defects of disposable injection needle by machine vision
In this paper, the injection needle detection system is used to detect the appearance defects of the disposable injection needle. The system takes Siemens image processor [3] as the core and combines with Siemens automation equipment to form a system with both simple digital signal interface and complex industrial network interface, so that users can choose a system suitable for their working conditions, which is convenient and saves investment.
The basic detection processing flow is shown in Figure 2, and the simple system framework is shown in Figure 3: