The video images of the printed products are continuously captured by the camera installed on the production line, and the speed of the camera is below 30 frames / s and is adjustable. The image collected by the camera is first quantified, and the analog signal is converted into a digital signal, from which a key frame that effectively represents the content of the lens is extracted and displayed on the display. For a frame of image, the analysis method of still image can be used to deal with, through the size measurement and multi-spectral analysis can identify each color mark on the video image, the color space and color parameters of the color mark and some other related.
Due to various factors, various noises will appear, such as Gaussian noise, salt and pepper noise, and random noise. Noise brings many difficulties to image processing. It has a direct impact on image segmentation, feature extraction, and image recognition. Therefore, the image collected in real time needs to be filtered. Image filtering requires the removal of noise outside the image, while maintaining the details of the image. When the noise is Gaussian noise, the most commonly used is a linear filter, which is easy to analyze and implement; but the linear filter has a poor filtering effect on salt and pepper noise. The traditional median filter can reduce the salt and pepper noise in the image, but the effect Not ideal, that is, the fully dispersed noise is removed, and the noise close to each other will be retained, so when the pepper and salt noise is more serious, its filtering effect is obviously deteriorated. The improved median filtering method of this system. This method first finds the median of the noise image window after removing the maximum and minimum gray value pixels, then calculates the difference between the median and the corresponding pixel gray value, and then compares it with the threshold to determine whether to use the obtained value Instead of the gray value of the pixel.
Image segmentation detects each color mark at this stage and separates it from the background. The edge of the object is reflected by the gray discontinuity. The type of L edge can be divided into two types. One is the step edge, and the pixels on both sides The gray value is significantly different; the second is the roof-like edge, which is located at the turning point of the change of the gray value from increasing to decreasing. For step edges, the second-order direction derivative is zero crossing at the edge, so differential calculation can be used To do edge detection operator. The differential operator-like edge detection method is similar to high-pass filtering in the high spatial domain. It has the effect of increasing high-frequency components. This type of operator is quite sensitive to noise. For step edges, the commonly available operators are the gradient operator Sobel. And Kirsh operator. For roof-like edges, Laplace transform and Kirsh operator can be used. Since the color scale is rectangular and the gray levels of adjacent edges differ greatly, edge detection is used to segment the image. Sobert edge sub is used here for edge detection. It uses local difference operators to find edges, which can better separate color scales. In the actual detection process, the color image edge detection method is used to select the appropriate color base (such as intensity, chroma, saturation, etc.) for detection. According to the characteristics of the type of the printing machine, that is, the colors of the colors of the printing machine and the characteristics of the layout, multi-threshold processing is performed to obtain a binary map of each color.
The segmented image is measured, and the object is identified by the measured value. Since the color scale is a rectangular shape with regular shapes, the following features can be extracted: (1) Calculate the rectangular area from pixels, (2) Rectangularity, (3 ) Chromaticity (H) and saturation (S), and then get the spacing between the color scales according to the number of pixels between the color scales, and compare with the set value to get the difference between the two, a total of m measurements, take the average The difference provides the corresponding adjustment signal to the digital AC servo adjustment section. To adjust the relative position of the color roller, thereby eliminating or reducing printing misalignment. During feature extraction, multi-spectral image analysis is performed on the image to quantitatively represent color scales, such as the color of pixels in a color image. The HIS format is used to obtain two parameters of color information for each color scale: chroma and saturation. To check the quality of the ink. Perform statistical calculations on the two-color binary maps or template matching with standard graphics to measure ink debris and other parameters during the printing process.
The printing machine is unrolled by the unwinder and passes through each printing unit in turn to perform printing and drying of various colors. The winding machine performs the rewinding L. Each color printing will be printed on the edge of the printing material for color registration. The color marking lines are 10 mm long and 1 mm wide. The marking lines of each adjacent color should be parallel to each other when the overprint is accurate, and the vertical (longitudinal) distance is 20 mm. The video image of the printed product is continuously captured by the camera installed on the production line. Through the size measurement and multi-spectral analysis, the color patches on the video image can be identified, and the color patch spacing and color parameter L of the color patch can be obtained. If the interval between two adjacent color patches is greater than or less than 20 mm, it indicates that there is a deviation in the overprint. The deviation signal is sent to the servo frequency conversion drive unit, which drives the AC servo motor to move the corresponding register correction roller ML up and down to extend or shorten the stroke of the printing material from the previous unit printing plate roller to the unit printing plate roller for dynamic correction.
QCROBOT can provide this machine vision module and engineering solution.
"Puzzle 3D Eraser Bulk,Puzzle 3D Eraser,Building Blocks Eraser,Toppers Cute Erasers "
Yiwu Shengshang Stationery Co., Ltd. , https://www.ss-stationery.com