Application of Hole Position Image Recognition Technology in Numerical Control Toothbrush Tufting Machine

The function of the CNC toothbrush planting machine is to implant the toothbrush bristles into the toothbrush hole. The processing process mainly completes the toothbrush blank picking, the planting head is automatically positioned in place, and the CNC worktable z, y directions A series of actions such as hole centering, color separation and hair planting. Toothbrush blanks are made by injection molding, and different specifications of toothbrush blanks have different head hole sizes and positions. The toothbrush blank hole positions and other geometric parameters need to be obtained before the tufting process, and then a numerical control processing program is written and sent to the control of the toothbrush tufting machine system. When manually measuring the toothbrush blank hole position and other parameters, there are problems such as low measurement efficiency and hole position parameter error. This paper applies image processing technology to image the hole position of the toothbrush head, writes hole position image recognition software, and realizes the automatic programming of the processing procedure of the tufting machine.

1. Toothbrush head hole position image recognition process The basic process of toothbrush head hole position image recognition software is to obtain a binary image of the toothbrush head through a scanner, and then to The value image is used to determine the outer contour of the toothbrush head, identify and extract the geometric information of the hole position, obtain the center size of each hole position, and finally generate a numerical control processing program. 1.1 Toothbrush head image reading 1.2 Toothbrush head image positioning The purpose of image positioning is to detect the edge of the toothbrush head image obtained by scanning, identify the size of the image, and determine the origin of the y coordinate. The image edge detection algorithm adopts the scanning form. It starts scanning from the first line of the image, reads the image data of the line, and then uses the four-neighbor detection method to detect the boundary of the toothbrush head image, and records the number of lines of each boundary in the image data ( Or the number of columns) old '3 J, to realize the edge positioning of the image of the toothbrush head hole. The algorithm flow for locating the upper boundary of the toothbrush head image is: (1) locating the upper boundary; (2) scanning from the left boundary of each line; (3) function of removing isolated points; (4) recording the upper line boundary of the image. 1.3 Median filtering of toothbrush head images During the input process of digital images, noises that affect the quality of digital images will be generated. For example, 'burrs' in the images are caused by noise. Median filtering of images can eliminate noises. The influence of

1.4 Contour extraction of the toothbrush head image Contour extraction of the toothbrush head image includes the extraction of the outer contour and the contour extraction of the toothbrush hole. The basic process is: judging the adjacent pixels of a pixel in the image in four directions, up, down, left, and right. If the gray value of the four adjacent points of the point is not 0, it means that the point is an internal point. The gray value is set to 0; if the gray value of one of the four adjacent points of the point is 0, the gray value remains unchanged. 1.5 Toothbrush head image cleaning The image after image contour extraction may be distorted, as shown by the arrow in Figure 5. During the scanning process, due to the defects of the toothbrush sample used for scanning and other reasons, the shape of some toothbrush holes in the toothbrush head image will be incomplete, and the image needs to be cleaned up to ensure the accuracy of the image hole position parameter calculation . This paper adopts the 'brush' in image processing, and uses the mobile 'brush' to delete the incomplete arc segments, scattered points and discontinuous points that have problems in contour extraction. 1.6 The calculation of the hole position parameter of the toothbrush head image The main steps of the calculation of the toothbrush head image hole position parameter are: (1) The recursive search mark method is used in the study of marking the toothbrush hole position in the image. First, find a black Then search for the eight neighborhoods of the black dots. If there are black dots in the neighborhood, search for the eight neighborhoods with this as the center, and so on, distinguish all the toothbrush larvae from the outline of the toothbrush head and mark them in turn. On the serial number. (2) Center detection algorithms for each toothbrush hole include the center of gravity method, the median method, the Hou curve transformation method, and the circle fitting spot center detection method. The circle fitting method has the advantages of fast calculation speed and detection of incomplete arcs. 2. Numerical control data for toothbrush tufting processing. When generating a numerical control processing program, it is necessary to set the processing coordinate origin in advance. In this study, the method of determining the origin of the toothbrush tufting processing coordinates is: if the mouse click falls within a certain toothbrush hole, the center of the hole is automatically selected as the origin of the processing coordinates; if the mouse click does not fall within a certain toothbrush hole, then The position where the mouse clicks is taken as the origin of the machining coordinates. In addition, in order to meet the requirement of implanting different colored bristles with different larvae in a toothbrush, a color processing algorithm is used to mark the image of the hole into three different colored holes '5.

2.1 Image recognition results of toothbrush head hole positions with different resolutions 2.2 Monochrome and multicolor flocking processing procedures are processed by image recognition, toothbrush hole hair color marking, hole center calculation and other processes to output multiple Color (three colors, the outermost 24 holes are the first color) The difference between single color and three color tufting program is whether there is an instruction to change different material boxes in the program. This function uses the M06 tool change instruction of the standard CNC machining program And choose yo!, ID2, yo 3 tool implementation. That is, if the M06Tol, M061D2, and M056 yo 3 instructions are removed in lines 00, 24, and 32 of the program, the above program will be converted into a monochrome flocking processing program.