Image recognition alignment fast multi-piece measurement method

Abstract

The application provides a kind of image recognition alignment fast multi-piece measurement method, it is related to product measurement technical field;The method comprises the following steps: S10, the image of the shape or shape of product is displayed in display area;S20, the image of a product to be measured is collected in display area;S30, according to the image, simulate the center point of the image, and establish the XY axis coordinate system with the center point;S40, on the basis of XY axis coordinate system, the size required to be detected of product is measured;S50, after the complete measurement of all sizes of product in image, compare the standard tolerance with the actual measurement value, and make a judgment, and the judgment result is displayed in the form of OK or NG on XY axis coordinate system;S60, the image of the judgment result OK is set as standard image, and the similar product image is found with the standard image in the measurement display area automatically searched;The beneficial effects of the application are: multiple products can be measured at one time, without using corner clamp, and the measurement is more convenient.

Description

TECHNICAL FIELD

[0001] The present application relates to the product measurement technical field, more particularly, the present application relates to a kind of image recognition alignment fast multi-piece measurement method. BACKGROUND

[0002] With watch, mobile phone backside vice screen, camera and other products more and more popular, the product demand brought by it is more and more, and the appearance cutting or silk printing pattern, there will be appearance size and printing pattern size bad, and small product, printing and appearance size need to be aligned with right angle, it is troublesome, slow detection, labor cost is expensive, the appearance size of measurement rule can be operated, for irregular product, it cannot be detected by right angle.

[0003] For such small products, there are currently measuring machines, which can measure multiple products at a time, but all products must be placed at a fixed distance, and each product must be placed according to the programmed measurement quantity to be measured. For regular circles or squares, measurement can be performed, but for irregular products, measurement cannot be performed. Moreover, this method requires employees to spend a lot of effort to place the products neatly, and any slight disorder will result in measurement failure.

[0004] In the prior art, only right-angle alignment and neat product placement can be measured. Only regular products such as squares, rectangles, and regular circles can be measured, and batch measurement of irregular products cannot be performed. Only fixed programming measurement can be performed at a fixed position on the same measurement interface, and the overall data table output is not easy to determine the product result. SUMMARY

[0005] In order to overcome the shortcomings of the prior art, the present application provides an image recognition alignment fast multi-piece measurement method, which can measure multiple products at a time without using right-angle clamps, making measurement more convenient.

[0006] The technical solution adopted by the present application to solve its technical problems is: an image recognition alignment fast multi-piece measurement method, which is improved in that the method comprises the following steps:

[0007] S10, after covering the double sides of the product to be measured with a protective film, place it in the measurement display area. The light can penetrate the protective film, and the image of the shape or appearance of the product is displayed on the display area.

[0008] S20, collect an image of a product to be measured in the display area, and set the image as the standard image of the product to be measured.

[0009] S30, simulate the center point of the image according to the image, and establish an XY axis coordinate system with the center point as the origin of the coordinate system for all image measurements.

[0010] S40, measuring the size of the product to be detected on the basis of the XY axis coordinate system;

[0011] S50, after measuring all the sizes of the product in the image, comparing the standard tolerance with the actual measured value, making a judgment, and displaying the judgment result in the form of OK or NG on the XY axis coordinate system;

[0012] S60, setting the image with the OK judgment result as a standard image, automatically searching for similar product images in the measurement display area based on the standard image, and executing steps S30 to S50 on the similar product images until all the products in the measurement display area are measured.

[0013] Further, in step S10, a large field of view telecentric lens is used to collect the image of the product contour and irradiate it into the CCD camera. The large field of view telecentric lens can take pictures and measure a range of 200*300mm with a picture accuracy of ±0.005mm.

[0014] Further, in step S10, the measurement display area is a transparent glass arranged below the telecentric lens, and a parallel light source is arranged below the transparent glass.

[0015] Further, the thickness of the transparent glass is 3-5mm.

[0016] Further, in step S30, the X axis and Y axis of the XY axis coordinate system are set in a fixed direction according to the structure of the product.

[0017] Further, according to different products, a plurality of standard auxiliary lines are arranged on the XY axis coordinate system to facilitate subsequent size measurement.

[0018] In step S30, the auxiliary lines are set according to the measurement difficulty of the product, and the auxiliary lines include a center line, an edge line or a contour line that penetrates the product.

[0019] Further, in step S40, the method for measuring the size includes the steps of automatically collecting the start point coordinates, automatically collecting the end point coordinates, determining the vector direction, and calculating the size to be detected.

[0020] The beneficial effects of the present application are that the present application can measure multiple products at a time, the products do not need to be placed by the right angle and edge, the products can be placed randomly, and a certain gap between the products can be ensured; the products placed in the measurement interface can be measured as long as they are within the display range, and the products can be measured when they are fully placed or in small quantities; irregular shaped or printed pattern products can be measured. BRIEF DESCRIPTION OF DRAWINGS

[0021] Figure 1 A structural schematic diagram of a machine table used in an image recognition alignment fast multi-piece measurement method of the present application.

[0022] Figures 2 to 6 A specific embodiment diagram of an image recognition alignment fast multi-piece measurement method of the present application. Figures 7 to 10 A specific embodiment diagram of establishing a coordinate system in an image recognition alignment fast multi-piece measurement method of the present application. DETAILED DESCRIPTION

[0023] The present application will be further described below in conjunction with the accompanying drawings and embodiments.

[0024] The concept, specific structure and generated technical effects of the present application will be clearly and completely described below in conjunction with embodiments and drawings, so as to fully understand the purposes, features and effects of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments of the present application, other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the present application. In addition, all the coupling / connection relations involved in the patent do not mean that the components are directly connected, but means that a better coupling structure can be composed by adding or reducing coupling accessories according to the specific implementation situation. The technical features in the present application can be combined with each other as long as they are not contradictory and conflicting.

[0025] The present application discloses an image recognition alignment fast multi-piece measurement method, referring to Figure 1 FIG. 1 is a structural schematic diagram of a machine table used in an image recognition alignment fast multi-piece measurement method of the present application. The machine table includes a CCD, a telecentric lens, a transparent glass and a light source. The transparent glass is located below the telecentric lens, and the light source is located below the transparent glass. The parallel light emitted by the light source is shot to the transparent glass.

[0026] Based on the machine table, the present application provides an image recognition alignment fast multi-piece measurement method, including the following steps:

[0027] S10, after covering the double sides of the product to be measured with a protective film, the product to be measured is placed into a measurement display area. The light can penetrate the protective film, and the image of the shape or appearance of the product is displayed in the display area.

[0028] In the embodiment, the measuring display area is transparent glass with a thickness of 4 mm. After the product to be measured is placed on the transparent glass, light can pass through the transparent glass and the protective film, and the non-light-transmitting area of the product blocks the light. When the image is captured by the CCD above, the shape of the product is displayed. In the embodiment, a large field of view telecentric lens is used to collect the image of the product contour and irradiate the CCD camera. The large field of view telecentric lens can take a picture in a range of 200*300 mm with a precision of ±0.005 mm.

[0029] S20, collecting an image of a product to be measured in the display area and setting the image as a standard image of the product to be measured;

[0030] In combination with Figure 2 In the embodiment, a plurality of products are arranged in an array, and the image collected in the display area is the image in the upper left corner of Figure 2 In the embodiment, the X axis and the Y axis of the XY axis coordinate system are set in a fixed direction according to the structure of the product. Referring to In the embodiment, the X axis and the Y axis of the XY axis coordinate system are set in a fixed direction according to the structure of the product. Referring to

[0031] In the embodiment, the X axis and the Y axis of the XY axis coordinate system are set in a fixed direction according to the structure of the product. Referring to In the embodiment, the X axis and the Y axis of the XY axis coordinate system are set in a fixed direction according to the structure of the product. Referring to

[0032] In the embodiment, the X axis and the Y axis of the XY axis coordinate system are set in a fixed direction according to the structure of the product. Referring to Figure 2 In the embodiment, the X axis and the Y axis of the XY axis coordinate system are set in a fixed direction according to the structure of the product. Referring to

[0033] In the embodiment, the X axis and the Y axis of the XY axis coordinate system are set in a fixed direction according to the structure of the product. Referring to

[0034] In the embodiment, the X axis and the Y axis of the XY axis coordinate system are set in a fixed direction according to the structure of the product. Referring to Figure 7 In the embodiment, the X axis and the Y axis of the XY axis coordinate system are set in a fixed direction according to the structure of the product. Referring to Figure 8 In the embodiment, the X axis and the Y axis of the XY axis coordinate system are set in a fixed direction according to the structure of the product. Referring to Figure 9 In the embodiment, the X axis and the Y axis of the XY axis coordinate system are set in a fixed direction according to the structure of the product. Referring to

[0035] When the product is an irregular product, the coordinate system is established by a dot matrix. For example,Figure 10 As shown, the profile of the standard product is grabbed to form a number of points, i.e. a dot matrix, all of which are numbered, and a virtual coordinate system is established through each point; it can be on the edge of the product or at the center, but can represent the product structure.

[0036] The product is measured, all steps are bound to the profile dot matrix of the product, i.e. the elements and positions of the product measurement are corresponded to the numbering of the dot matrix, so as to form an independent detection program. Then the profile of the product to be detected is run through the program, which is exactly or close to the position marked by the standard program, so that the size of the subsequent product is measured.

[0037] S40, measuring the size to be detected of the product on the basis of the XY axis coordinate system;

[0038] In the step S40, the method for measuring the size includes the steps of automatically collecting the start point coordinate, automatically collecting the end point coordinate, determining the vector direction, and calculating the size to be detected, in sequence.

[0039] Referring to Figure 3 As shown, the size to be measured in the embodiment includes L1-L8, and the specific size in the embodiment is as shown in Figure 3 For example, the size of L1 is 38.85±0.05mm.

[0040] S50, after the size measurement of the product in the image is completed, the standard tolerance is compared with the actual measurement value, a judgment is made, and the judgment result is displayed in the form of OK or NG on the XY axis coordinate system;

[0041] Referring to Figure 4 As shown, after all the sizes of the image in the upper left corner are measured, they are compared with the standard tolerance, and the judgment is OK. At this time, the judgment result is directly displayed on the XY axis coordinate system of the product image;

[0042] S60, setting the image with the OK judgment result as a standard image, automatically searching for similar product images with the standard image in the measurement display area, and executing the steps S30-S50 on the similar product images until the measurement of all the products in the measurement display area is completed.

[0043] Referring to Figure 5 As shown, it is a result diagram automatically searched in the display area according to the standard image.

[0044] Referring to Figure 6 As shown, it is a result diagram after the measurement of all the products in the measurement display area is completed by repeating the steps S30-S50.

[0045] Based on the above embodiment, the application provides a kind of image recognition alignment fast multi-piece measurement method, by setting standard image, and all images are automatically searched to find similar products, and each independent individual is analyzed separately, and the corresponding result is output, and the product is identified on the measurement interface, therefore, the application optimizes the single-piece measurement mode in the prior art into multi-piece simultaneous measurement, and 20-30 pieces can be measured at a time, with short time, and measurement can be completed within 3S.

[0046] For the defects of the measurement mode in the prior art, the application can measure multiple products at a time, the products do not need to be placed by right-angle edge, etc., the products can be placed randomly, and a certain gap between the products can be ensured; the products placed on the measurement interface can be measured as long as they are within the display range, and the full or less quantity can be measured; irregular shape or printed pattern products can be measured; when measuring and determining, the product is directly displayed above the measurement interface, and the product OK\NG state can be easily determined.

[0047] The above is a specific description of the preferred embodiment of the application, but the application is not limited to the described embodiment, and those skilled in the art can make various equivalent modifications or replacements without departing from the spirit of the application, and these equivalent modifications or replacements are all included in the scope defined by the claims of the present application.

Claims

1. A method for image recognition alignment fast multi-piece measurement, characterized in that, The method comprises the following steps: S10, after the double-side protective film of the product to be measured is covered, the product to be measured is placed in the measurement display area, the light can penetrate the protective film, and the image of the shape or contour of the product is displayed on the display area; S20, an image of the product to be measured is collected on the display area, and the image is set as the standard image of the product to be measured; S30, according to the image, the center point of the image is simulated, and the XY axis coordinate system is established based on the center point, and the XY axis coordinate system is set as the coordinate origin of all image measurements; In the step S30, the X axis and the Y axis of the XY axis coordinate system are set in fixed directions according to the structure of the product; In the step S30, according to the different products, a plurality of standard auxiliary lines are set on the XY axis coordinate system to facilitate the subsequent measurement of the size; the auxiliary lines are set according to the measurement difficulty of the product, and the auxiliary lines include the center line, the edge line or the contour line penetrating the product; S40, the size to be detected of the product is measured based on the XY axis coordinate system; S50, after the measurement of all the sizes of the product in the image is completed, the standard tolerance is compared with the actual measurement value, a judgment is made, and the judgment result is displayed on the XY axis coordinate system in the form of OK or NG; S60, the image with the OK judgment result is set as the standard image, the similar product images are found by searching the standard image in the measurement display area, and the steps S30 to S50 are executed on the similar product images until the measurement of all the products in the measurement display area is completed.

2. The image recognition alignment rapid multi-piece measurement method according to claim 1, characterized in that, In the step S10, a large field of view telephoto lens is used to collect the image of the product contour, and the image is irradiated into the CCD camera; the large field of view telephoto lens can measure the range of 200*300mm with the photographing accuracy of ±0.005mm.

3. The image recognition alignment rapid multi-piece measurement method of claim 2, wherein, In the step S10, the measurement display area is a transparent glass arranged below the telephoto lens, and a parallel light source is arranged below the transparent glass.

4. The image recognition alignment rapid multi-piece measurement method of claim 3, wherein, The thickness of the transparent glass is 3-5mm.

5. The method of claim 1, wherein, In the step S40, the measurement method comprises the following steps in sequence: automatically collecting the start point coordinates, automatically collecting the end point coordinates, determining the vector direction, and calculating the size to be detected.

Images