A machine vision image test card and implementation method thereof
By designing a multifunctional machine vision image test card, the problem of time-consuming and labor-intensive sample production was solved, and convenient multi-sample display and efficient training were achieved.
Patent Information
- Application Number
- CN202310219247.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-03-08
- Publication Date
- 2025-09-30
- Estimated Expiration
- 2043-03-08
AI Technical Summary
The production of existing machine vision samples consumes manpower and time, and large samples are inconvenient to carry and display, which affects training efficiency.
A machine vision image test card is designed, which contains multiple test samples set on different test surfaces, including presence detection, color extraction, positioning, color matching, result analysis, code reading and character recognition functions. Diversity is achieved by setting preset colors, parameters and different QR codes and character strings.
It provides a portable sample solution with multiple uses on one card, shortens sample preparation time, improves training efficiency, and enables convenient display of various application scenarios.
Smart Images
Figure CN116360006B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of machine vision, and in particular to a machine vision image test card and an implementation method thereof. Background Art
[0002] As a key component of artificial intelligence, machine vision has been widely applied in industries such as industry, transportation, and healthcare, becoming a key driver of intelligent production. Machine vision systems are a comprehensive technology platform integrating computer vision, image processing, optoelectronics, signal processing, and mechanics. Therefore, to promote the comprehensive development of machine vision technology, professional machine vision training is essential. This training covers common applications in the vision industry, such as presence detection, object counting, character recognition, code reading, and color recognition.
[0003] Currently, when creating machine vision samples, meticulous preparation of corresponding sample cases for different application scenarios is required, which consumes considerable manpower and time. Some samples may even be too bulky and heavy to demonstrate the final visual effect. Summary of the Invention
[0004] In order to achieve the above-mentioned purpose and other advantages according to the present invention, a first object of the present invention is to provide a method for implementing a machine vision image test card, comprising the following steps:
[0005] A first test sample and / or a second test sample and / or a third test sample and / or a fourth test sample are placed on the first test surface of the test card; wherein the first test sample is used for presence detection and color extraction, the second test sample is used for positioning, color matching, and result analysis, the third test sample is used for code reading, and the fourth test sample is used for character recognition;
[0006] A second test sample and / or a third test sample and / or a fourth test sample are set on the second test surface of the test card; the second test sample, the third test sample, and the fourth test sample on the second test surface are different from the corresponding second test sample, the third test sample, and the fourth test sample on the first test surface.
[0007] Furthermore, setting the first test sample on the first test surface of the test card includes setting the first sample material according to a preset color.
[0008] Furthermore, setting the second test sample on the test surface of the test card includes setting multiple second sample materials on the test surface of the test card according to corresponding preset parameter pairs; the preset parameter pairs include label color and position; the number of second sample materials on the two test surfaces is different.
[0009] Furthermore, setting a third test sample on the test surface of the test card includes the following steps:
[0010] Setting a preset first QR code on the first test surface of the test card;
[0011] A preset second two-dimensional code is set on the second test surface of the test card; the first two-dimensional code is different from the second two-dimensional code.
[0012] Furthermore, setting a fourth test sample on the test surface of the test card includes the following steps:
[0013] Setting a preset first character string on the first test surface of the test card;
[0014] A preset second character string is set on the second test surface of the test card; the first character string and the second character string are different types of characters.
[0015] A second object of the present invention is to provide a machine vision image test card, comprising a test card body, wherein the test card body comprises a first test surface and a second test surface, wherein a first test sample and / or a second test sample and / or a third test sample and / or a fourth test sample are provided on the first test surface, and a second test sample and / or a third test sample and / or a fourth test sample are provided on the second test surface; the second test sample, the third test sample and the fourth test sample on the second test surface are different from the corresponding second test sample, the third test sample and the fourth test sample on the first test surface; wherein the first test sample is used for presence detection and color extraction, the second test sample is used for positioning, color matching, and result analysis, the third test sample is used for code reading, and the fourth test sample is used for character recognition.
[0016] Furthermore, the first test sample is prepared by placing a first sample material on the first test surface in a preset color.
[0017] Furthermore, the second test sample is obtained by arranging a plurality of second sample materials on the first test surface and the second test surface according to corresponding preset parameter pairs; the preset parameter pairs include label color and position; and the number of second sample materials on the two test surfaces is different.
[0018] Furthermore, the third test sample is prepared by setting a preset first QR code on a first test surface of the test card and a preset second QR code on a second test surface of the test card; the first QR code is different from the second QR code.
[0019] Furthermore, the fourth test sample is formed by setting a preset first character string on a first test surface of the test card and a preset second character string on a second test surface of the test card; the first character string and the second character string are different types of characters.
[0020] Compared with the prior art, the present invention has the following beneficial effects:
[0021] The present invention provides a machine vision image test card and implementation method thereof, providing sample materials for common application areas in the vision industry involved in professional machine vision training, such as presence / absence detection, object counting, character recognition, code reading, and color recognition. The test card provided by the present invention is colorful and contains a variety of elements, enabling a single card for multiple uses. It is both compact and portable, and shortens the time required to develop machine vision sample plans, greatly facilitating the production of machine vision samples.
[0022] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention and to implement it according to the contents of the description, the following preferred embodiments of the present invention are described in detail with reference to the accompanying drawings. The specific implementation methods of the present invention are given in detail by the following embodiments and the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:
[0024] Figure 1 A flow chart of a method for implementing a machine vision image test card according to Example 1;
[0025] Figure 2 This is a schematic diagram of the first test surface of the machine vision image test card in Example 2;
[0026] Figure 3 This is a schematic diagram of the second test surface of the machine vision image test card in Example 2. DETAILED DESCRIPTION
[0027] The present invention will be further described below in conjunction with the accompanying drawings and specific implementation methods. It should be noted that, under the premise of no conflict, the various embodiments or technical features described below can be arbitrarily combined to form new embodiments.
[0028] In the subsequent description, suffixes such as "module," "component," or "unit" used to represent elements are only used to facilitate the description of the present invention and have no specific meaning. Therefore, "module," "component," or "unit" can be used interchangeably.
[0029] Example 1
[0030] A method for implementing a machine vision image test card, such as Figure 1 As shown, the following steps are included:
[0031] Set the first test sample and / or the second test sample and / or the third test sample and / or the fourth test sample on the first test surface of the test card; wherein, the first test sample is used for presence detection and color extraction, the second test sample is used for positioning, color matching, and result analysis, the third test sample is used for code reading, and the fourth test sample is used for character recognition. Specifically, the first sample material is set according to the preset color. Figure 2 As shown, Figure 2 There is a blue and red V in the upper left corner; Figure 3 As shown, Figure 3 There is no blue and red V in the upper left corner; a blue and red V is set on the first test surface of the test card, and no blue and red V is set on the second test surface of the test card. Presence detection is achieved by detecting the V on both test surfaces, and color extraction is achieved by detecting the color of the V on the first test surface.
[0032] A second test sample and / or a third test sample and / or a fourth test sample are placed on the second test surface of the test card. The second, third, and fourth test samples on the second test surface are different from the corresponding second, third, and fourth test samples on the first test surface. By providing a first and second test surface, the test card can be used as two different products, facilitating the diversity of visual samples.
[0033] Setting the second test sample on the test surface of the test card includes setting multiple second sample materials on the test surface of the test card according to corresponding preset parameter pairs; the preset parameter pairs include label color and position; the number of second sample materials on the two test surfaces is different.
[0034] like Figure 2 、 Figure 3 As shown, the positions, label colors, and numbers of industrial cameras in the middle area are different; Figure 2 The number of industrial cameras is 4. Figure 3 The number of industrial cameras in the test area is 3. By detecting the number of cameras in the first test surface and the second test surface, the number detection can be achieved. Figure 2 The camera label in the upper left corner is black, and the camera location is 818.57.756.72. The camera label in the upper right corner is blue, and the camera location is 1385.03.762.20. The camera label in the lower left corner is blue, and the camera location is 815.54.1052.87. The camera label in the lower right corner is black, and the camera location is 1387.19.1055.93. Figure 3 The camera label in the upper left corner is blue, and the camera position is 795.23.708.25. The camera label in the upper right corner is black, and the camera position is 1371.97.705.41. The camera label in the lower left corner is blue, and the camera position is 797.27.1002.70. Position detection can be achieved by detecting the camera positions in the first test surface and the second test surface, and label color detection can be achieved by detecting the camera label colors in the first test surface and the second test surface.
[0035] Placing a third test sample on the test surface of the test card comprises the following steps:
[0036] Setting a preset first QR code on the first test surface of the test card;
[0037] The preset second QR code is set on the second test surface of the test card; the first QR code is different from the second QR code. Figure 2 As shown, the QR code on the first test surface is CZ; Figure 3 As shown, the two-dimensional code on the second test surface is CC; code reading detection can be achieved by detecting the two-dimensional codes on the first test surface and the second test surface.
[0038] Setting the fourth test sample on the test surface of the test card includes the following steps:
[0039] Setting a preset first character string on the first test surface of the test card;
[0040] The preset second character string is set on the second test surface of the test card; the first character string and the second character string are different types of characters. Figure 2 As shown, the address on the first test surface is a Chinese address, such as Figure 3 As shown, the address on the second test surface is an English address.
[0041] The visual software positioning process of the above-mentioned machine vision image test card is as follows: certain features that exist on both test surfaces of the test card, such as "CC" or a QR code, can be taken as templates for template matching. By training the common features and using the template matching algorithm to locate the entire test card as a whole, character recognition, color recognition, feature positioning and other functions can be performed in the positioned coordinate space.
[0042] The visual sample effect achieved by the method for implementing a machine vision image test card provided by the present invention is as follows: Figure 2 、 Figure 3 The test cards shown demonstrate versatility. Figure 2 、 Figure 3 The results shown in the figure are a summary of various scenarios of machine vision samples. It should be noted that according to the above four distinctions, a variety of different visual samples can be produced, not limited to Figure 2 、 Figure 3 Schematic visual sample.
[0043] Example 2
[0044] A machine vision image test card includes a test card body, the test card body including a first test surface and a second test surface, wherein a first test sample and / or a second test sample and / or a third test sample and / or a fourth test sample are provided on the first test surface, and a second test sample and / or a third test sample and / or a fourth test sample are provided on the second test surface; the second test sample, the third test sample, and the fourth test sample on the second test surface are different from the corresponding second test sample, the third test sample, and the fourth test sample on the first test surface. The first test sample is used for presence detection and color extraction, the second test sample is used for positioning, color matching, and result analysis, the third test sample is used for code reading, and the fourth test sample is used for character recognition. By providing the first test surface and the second test surface, the test card can be used as two different products, which is conducive to achieving diversity in visual samples. In this embodiment, the first test surface and the first test surface card are 90 mm long and 54 mm wide.
[0045] The first test sample is prepared by placing the first sample material on the first test surface according to the preset color. Figure 2 As shown, Figure 2 There is a blue and red V in the upper left corner; Figure 3 As shown, Figure 3 There is no blue and red V in the upper left corner; a blue and red V is set on the first test surface of the test card, and no blue and red V is set on the second test surface of the test card. Presence detection is achieved by detecting the V on both test surfaces, and color extraction is achieved by detecting the color of the V on the first test surface.
[0046] The second test sample is prepared by placing a plurality of second sample materials on the first test surface and the second test surface according to corresponding preset parameter pairs; the preset parameter pairs include label color and position; and the number of second sample materials on the two test surfaces is different.
[0047] like Figure 2 、 Figure 3 As shown, the positions, label colors, and numbers of industrial cameras in the middle area are different; Figure 2 The number of industrial cameras is 4. Figure 3 The number of industrial cameras in the test area is 3. By detecting the number of cameras in the first test surface and the second test surface, the number detection can be achieved. Figure 2The camera label in the upper left corner is black, and the camera location is 818.57.756.72. The camera label in the upper right corner is blue, and the camera location is 1385.03.762.20. The camera label in the lower left corner is blue, and the camera location is 815.54.1052.87. The camera label in the lower right corner is black, and the camera location is 1387.19.1055.93. Figure 3 The camera label in the upper left corner is blue, and the camera position is 795.23.708.25. The camera label in the upper right corner is black, and the camera position is 1371.97.705.41. The camera label in the lower left corner is blue, and the camera position is 797.27.1002.70. Position detection can be achieved by detecting the camera positions in the first test surface and the second test surface, and label color detection can be achieved by detecting the camera label colors in the first test surface and the second test surface.
[0048] The third test sample is tested by setting a preset first QR code on the first test surface of the test card and a preset second QR code on the second test surface of the test card; the first QR code is different from the second QR code. Figure 2 As shown, the QR code on the first test surface is CZ; Figure 3 As shown, the two-dimensional code on the second test surface is CC; code reading detection can be achieved by detecting the two-dimensional codes on the first test surface and the second test surface.
[0049] The fourth test sample is prepared by setting a preset first character string on the first test surface of the test card and a preset second character string on the second test surface of the test card; the first character string and the second character string are different types of characters. Figure 2 As shown, the address on the first test surface is a Chinese address, such as Figure 3 As shown, the address on the second test surface is an English address.
[0050] Figure 2 、 Figure 3 The results shown in the figure are a summary of various scenarios of machine vision samples. It should be noted that according to the above four distinctions, a variety of different visual samples can be produced, not limited to Figure 2 、 Figure 3 Schematic visual sample.
[0051] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.
[0052] The foregoing is merely an example of the present invention and is not intended to limit the present invention to one or more embodiments. It will be apparent to those skilled in the art that various modifications and variations may be made to the present invention to one or more embodiments. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention to one or more embodiments shall be included within the scope of the claims of the present invention to one or more embodiments.
Claims
1. A method for implementing a machine vision image test card, characterized in that: The following steps are involved: A first test sample and / or a second test sample and / or a third test sample and / or a fourth test sample are placed on the first test surface of the test card; wherein the first test sample is used for presence detection and color extraction, the second test sample is used for positioning, color matching, and result analysis, the third test sample is used for code reading, and the fourth test sample is used for character recognition; Setting a second test sample and / or a third test sample and / or a fourth test sample on the second test surface of the test card; the second test sample, the third test sample, and the fourth test sample on the second test surface are different from the corresponding second test sample, the third test sample, and the fourth test sample on the first test surface; The setting of the first test sample on the first test surface of the test card includes setting the first sample material according to a preset color; Setting the second test sample on the test surface of the test card includes setting a plurality of second sample materials on the test surface of the test card according to corresponding preset parameter pairs; the preset parameter pairs include label color and position; and the number of second sample materials on the two test surfaces is different; Setting the fourth test sample on the test surface of the test card includes the following steps: Setting a preset first character string on the first test surface of the test card; A preset second character string is set on the second test surface of the test card; the first character string and the second character string are different types of characters.
2. The method for implementing a machine vision image test card according to claim 1, wherein: Placing a third test sample on the test surface of the test card comprises the following steps: Setting a preset first QR code on the first test surface of the test card; A preset second two-dimensional code is set on the second test surface of the test card; the first two-dimensional code is different from the second two-dimensional code.
3. The machine vision image test card implemented by the implementation method of a machine vision image test card according to claim 1, characterized in that: The test card comprises a test card body, the test card body comprising a first test surface and a second test surface, wherein a first test sample and / or a second test sample and / or a third test sample and / or a fourth test sample are provided on the first test surface, and a second test sample and / or a third test sample and / or a fourth test sample are provided on the second test surface; the second test sample, the third test sample, and the fourth test sample on the second test surface are different from the corresponding second test sample, the third test sample, and the fourth test sample on the first test surface; wherein the first test sample is used for presence detection and color extraction, the second test sample is used for positioning, color matching, and result analysis, the third test sample is used for code reading, and the fourth test sample is used for character recognition; The first test sample is prepared by placing a first sample material on the first test surface according to a preset color; The second test sample is prepared by placing a plurality of second sample materials on the first test surface and the second test surface according to corresponding preset parameter pairs; the preset parameter pairs include label color and position; and the number of second sample materials on the two test surfaces is different; The fourth test sample is prepared by setting a preset first character string on a first test surface of the test card and a preset second character string on a second test surface of the test card; the first character string and the second character string are different types of characters.
4. A machine vision image test card according to claim 3, characterized in that: The third test sample is prepared by setting a preset first two-dimensional code on a first test surface of the test card and a preset second two-dimensional code on a second test surface of the test card; the first two-dimensional code is different from the second two-dimensional code.