CN112330599B

CN112330599B - Dimension measurement scoring device, adjustment method and scoring method

Info

Publication number: CN112330599B
Application number: CN202011103725.5A
Authority: CN
Inventors: 余建安; 潘凌锋; 林建宇; 陈浙泊; 陈一信; 陈龙威; 颜文俊; 林斌; 郑军; 叶雪旺; 陈镇元; 吴荻苇; 洪徐健
Original assignee: Research Institute of Zhejiang University Taizhou
Current assignee: Research Institute of Zhejiang University Taizhou
Priority date: 2020-10-15
Filing date: 2020-10-15
Publication date: 2024-02-20
Anticipated expiration: 2040-10-15
Also published as: CN112330599A

Abstract

The size measurement scoring device comprises a fixed frame, an operation table, a detection table, a light source and a camera; the detection table, the light source and the camera are arranged on the fixing frame; the middle part of the detection table is provided with a through hole, the through hole is provided with a carrying plate, and the carrying plate is made of transparent materials; the light source is arranged below the detection table and corresponds to the object carrying plate; the camera is arranged on the camera fixing plate right above the object carrying plate; the operation desk is electrically connected with the light source and the camera; a standard flat crystal is arranged between the camera and the detection table; a telecentric coaxial lens is arranged at the lens of the camera, and a He-Ne laser is arranged on the side surface of the telecentric coaxial lens; the camera lens and the object carrying plate are arranged in parallel by arranging a standard flat crystal between the camera and the object carrying plate, arranging fine adjusting knobs on four corners of the object carrying plate and arranging a He-Ne laser on the camera.

Description

Dimension measurement scoring device, adjustment method and scoring method

Technical Field

The invention relates to the field of image recognition, in particular to a size measurement scoring device, an adjusting method and a scoring method.

Background

At present, a domestic higher institution sets a machining training course for some specific professions, wherein students are generally examined in the training process or at the end of the training, and a class of widely applied examination projects are to require the students to design and manufacture mechanical workpieces according to the question requirements, and the students are scored by measuring the size specification of the mechanical workpieces and comparing the mechanical workpieces with standard components or requirements according to indexes such as accurate values, tolerance and the like. At present, traditional measuring tools such as vernier calipers, micrometer and the like are still adopted in institutions to carry out manual detection, so that the dimension specification of a machined part is obtained.

The following drawbacks exist with conventional measuring tools: 1. time is required to be consumed for positioning the measurement object; 2. the more the single measuring object measuring parts are, the longer the time consumption is; 3. the long-time measurement can cause various burdens such as eye fatigue to the measurer; 4. the measurement position is judged by a measurer, so that the measurement result can be different from person to person; 5. human errors exist in measurement readings; 6. the measurement data is required to be manually input and counted by a measurer, and the method has the advantages of long time consumption, low efficiency and easy error.

On the other hand, the current assessment test method of the machining training course does not have the following functions: 1. the examination questions are intelligently acquired through the server, so that the randomness of the examination questions is ensured; 2. the test process needs to bind the size measurement result of the part manufactured by the examinee according to the identity information of the examinee, so as to ensure the accuracy of the test score; 3. the measurement result is evaluated in real time according to the examination requirement, a teacher is not required to manually input the examination result, the efficiency is improved, and errors are not easy to occur; 4. aiming at the special examination scene of the mechanical processing course of the university, only the front and side surfaces of the same part are required to be measured, and the measurement result is uploaded to the server after the measurement is completed, so that examination results are obtained, and the method is accurate and efficient.

Therefore, a device and a method for detecting and scoring machined parts of mechanical parts manufactured by students in an efficient and intelligent manner are needed.

Disclosure of Invention

The invention aims to solve the defects of the prior art, and provides a visual scoring measurement device and a visual scoring measurement system, which can be respectively endowed with rights for three users of teachers, students and tourists, can accurately read the dimension parameters of objects in pictures, and are simple in structure and convenient to use.

A dimension measurement scoring device comprises a fixing frame, an operation table, a detection table, a light source and a camera; the detection table, the light source and the camera are arranged on the fixing frame; the middle part of the detection table is provided with a through hole, the through hole is provided with a carrying plate, and the carrying plate is made of transparent materials; the light source is arranged below the detection table and corresponds to the object carrying plate; the camera is arranged on the camera fixing plate right above the object carrying plate; the operation desk is electrically connected with the light source and the camera; a standard flat crystal is arranged between the camera and the detection table; a telecentric coaxial lens is arranged at the lens of the camera, and a He-Ne laser is arranged on the side surface of the telecentric coaxial lens.

Further, the standard flat crystal is arranged on the sliding rail adjusting device; the sliding rail adjusting device comprises a vertical plate and a horizontal plate; the vertical plate passes through the detection table; two mutually parallel vertical tracks are arranged on one surface of the vertical plate, which is close to the detection table, and the horizontal plate is arranged on the vertical tracks of the vertical plate; a horizontal track is arranged on one surface of the horizontal plate, which is close to the detection table, and a standard flat crystal is arranged on the horizontal track; the top of riser is provided with the camera backup pad, and the bottom of riser is provided with the light source backup pad.

Further, a fine adjustment knob is arranged between the carrying plate and the detection table.

Further, a bracket is arranged on the detection table and is positioned on the carrying plate; the middle part of the bracket is provided with a groove.

Further, a vertical high-precision adjusting sliding rail is arranged between the detection table and the fixing frame; the vertical high-precision adjusting sliding rail is positioned at four corners of the detection table.

Further, a laser ranging device is arranged between the camera fixing plate and the detection table; the laser ranging device comprises a laser ranging sensor transmitting head and a laser ranging receiver; the laser range finding receiver is arranged on four corners of the detection table, the laser range finding sensor transmitting head is arranged on four corners of the camera fixing plate, and the laser sensor transmitting head is arranged over against the laser range finding receiver.

Further, the whole fixing frame is in a straight quadrangular shape, the inside of the fixing frame is hollow, the fixing frame is arranged above the optical vibration isolation table, and the four corners of the bottom of the optical vibration isolation table are provided with Fuma wheels; the detection table is also provided with a transparent checkerboard and an identity card reader; the operation panel sets up in the top of camera fixed plate, and the operation panel includes display module.

A method of adjusting a sizing scoring device, comprising the steps of:

step one: the camera and the light source are respectively and fixedly arranged on the camera fixing plate and the light source supporting plate; a bracket and a part to be detected are arranged on the object carrying plate; turning on a light source, and adjusting four vertical high-precision adjusting slide rails according to the definition degree of the images continuously acquired by the camera so as to enable the images to be clear;

step two: according to four groups of data obtained by four laser sensors in the laser ranging device, the four vertical high-precision adjusting slide rails are continuously adjusted, so that the four groups of data are equal, and the camera fixing plate is parallel to the detection table;

step three: removing the bracket and the part to be detected from the detection table; the horizontal and vertical adjusting slide rails on the slide rail adjusting device are adjusted, so that the standard flat crystal is opposite to the carrying plate and is spaced by a set distance, the light source is turned off, and the He-Ne laser is turned on to adjust the lower surface of the standard flat crystal to be parallel to the upper surface of the carrying plate;

step four: turning off the He-Ne laser, turning on the light source, and removing the standard flat crystal; setting a bracket at a set position above a carrying plate, setting a transparent checkerboard above the bracket, collecting images, calibrating a flat field and calculating the image magnification;

Step five: taking down the transparent checkerboard, placing the part to be detected, enabling the front face of the part to be detected to face upwards, and obtaining an image by a camera to finish the size measurement of the front face length and width and the front face internal items;

step six: and placing the side face of the part to be detected in the bracket groove upwards, acquiring an image by a camera, finishing the measurement of the height information of the side face, and ending the steps.

Furthermore, in the third step, the lower surface of the standard flat crystal is adjusted to be parallel to the upper surface of the carrier plate, first, the light rays emitted by the He-Ne laser are required to obtain interference fringes through the camera, after the interference fringes are processed, information difference values of adjacent interference fringes are obtained, and four fine adjustment knobs are continuously adjusted according to the difference values until the information difference values of the adjacent interference fringes are reduced to a set value, so that the interference fringes are approximately parallel and equidistant.

A sizing scoring method comprising the steps of:

step 1: the operation platform senses the operation of an operator, opens software according to the operation of the operator, and automatically executes the initialization operation of the opened software;

step 2: after the initialization operation of opening the software is completed, a display module on the operation desk automatically displays a user login interface; wherein the initial user login interface is provided with a tourist measurement button and a system exit button;

Step 3: user login is carried out according to the operation of an operator; the method comprises two login modes; one is to complete the login of the tourist through a button of 'tourist measurement', and enter a tourist measurement flow; the other is to complete the teacher login or student login through identification by an identity card, and enter a corresponding teacher operation flow or student examination flow;

step 4: the operation desk completes user login; if the measurement process is a tourist measurement process and a student examination process, automatically entering a dimension measurement interface, setting parameters, finishing dimension measurement, and ending the process; if the operation flow is the teacher operation flow, displaying a teacher operation panel on a user login interface; buttons for downloading test questions, uploading test questions and making test questions are arranged on the teacher operation panel;

step 5: the operation desk selects the content of teacher operation according to the operation of the operator; through the button of the test question downloading button, a test question downloading process can be entered, and the process is finished after the test question downloading is finished; the test question uploading process can be entered through the 'upload test question' button, and the process is ended after the test question uploading is completed; the test question making process can be entered through the test question making button, the dimension measuring interface is entered, and the process is ended after the test question making is completed;

The identification card in the step 3 depends on an identification card reader.

The beneficial effects of the invention are as follows:

the standard flat crystals are arranged between the camera and the object carrying plate, fine adjusting knobs are arranged on four corners of the object carrying plate, and the He-Ne laser is arranged on the camera, so that the parallel arrangement between the lens of the camera and the object carrying plate is realized;

the laser ranging device is arranged between the camera fixing plate and the detection table, and the vertical high-precision adjusting sliding rail is arranged between the detection table and the fixing frame, so that the camera fixing plate and the detection table are arranged in parallel;

the flat field of the camera is calibrated and the image magnification is calculated by arranging a transparent checkerboard on the detection table;

by arranging the bracket and the grooves on the bracket, the heights of the collected images are close when the right side of the part to be detected is arranged upwards and the side of the part to be detected is arranged upwards, the consistency of the image magnification of the camera is ensured, the dependence on the depth of the lens is reduced, the system error caused by long-distance lifting or descending of the camera is avoided, and the precision is improved;

through the arrangement of the bracket, the parts to be detected can be placed according to the set standard as far as possible, and a front image and a side image of the parts to be detected, which are easy to compare, are obtained; on the other hand, by arranging the transparent bracket which is not easy to slide, the part to be detected can be ensured to be stable in the process of acquiring the image by the camera;

According to the invention, through setting the management of the authority of students, teachers and tourists and setting the function of making test questions under the authority of the teachers, the purposes of editing and determining the test questions and collecting images of placed parts are realized, and the measurement is completed;

timely confirming the replacement of a user by setting the timing reading of the identity card information;

and (3) firstly reading the size measurement parameter zone bit of the test file by the setting system and firstly acquiring the test information zone bit by the system to confirm whether the size measurement parameter and the test information are read by the system.

Drawings

FIG. 1 is an overall construction diagram of a first embodiment of the present invention;

FIG. 2 is a front view of a first embodiment of the present invention;

FIG. 3 is a schematic view of a main portion of a first embodiment of the present invention;

FIG. 4 is a front view of a body portion of a first embodiment of the present invention;

FIG. 5 is a schematic diagram of a test bench according to a first embodiment of the invention;

FIG. 6 is a flowchart illustrating a first embodiment of an adjustment procedure;

FIG. 7 is a detailed flow chart of a first embodiment of the present invention;

FIG. 8 is a flow chart of a first embodiment of the invention;

FIG. 9 is a flowchart of extracting template source diagram feature information according to a first embodiment of the present invention;

FIG. 10 is a flowchart of a method for extracting template source circle measurement type measurement results according to a first embodiment of the present invention;

FIG. 11 is a flowchart of a method for extracting template source graph measurement type measurement results according to a first embodiment of the present invention;

FIG. 12 is a flowchart of a measurement result of the type of the source view angle measurement of the extraction template according to the first embodiment of the invention;

FIG. 13 is a flowchart of an algorithm for obtaining distortion parameters according to a first embodiment of the present invention;

FIG. 14 is a flowchart of an algorithm for obtaining a magnification according to a first embodiment of the present invention;

FIG. 15 is a flowchart of an algorithm for detecting the out-of-bounds of a part to be detected according to a first embodiment of the present invention;

FIG. 16 is a general flow chart of a measurement algorithm for the dimension of a part to be inspected according to the first embodiment of the invention;

FIG. 17 is a flowchart of an object finding and matching algorithm according to a first embodiment of the present invention;

FIG. 18 is a flowchart of a circle measurement algorithm for a part to be inspected according to a first embodiment of the present invention;

FIG. 19 is a flowchart of a measurement algorithm of a part line to be inspected according to a first embodiment of the present invention;

FIG. 20 is a flowchart of a measurement algorithm for the angle of a part to be inspected according to a first embodiment of the present invention;

FIG. 21 is an example of a mask diagram for four measurement types of circles, lines, arcs, and angles according to the first embodiment of the present invention;

fig. 22 is a diagram illustrating the image phase and the schematic diagram in step 4.7.11 according to the first embodiment of the invention.

Detailed Description

Other advantages and effects of the present invention will become apparent to those skilled in the art from the following disclosure, which describes the embodiments of the present invention with reference to specific examples. The invention may be practiced or carried out in other embodiments that depart from the specific details, and the details of the present description may be modified or varied from the spirit and scope of the present invention. It should be noted that the following embodiments and features in the embodiments may be combined with each other without conflict.

It should be noted that the illustrations provided in the following embodiments merely illustrate the basic concept of the present invention by way of illustration, and only the components related to the present invention are shown in the drawings and are not drawn according to the number, shape and size of the components in actual implementation, and the form, number and proportion of the components in actual implementation may be arbitrarily changed, and the layout of the components may be more complicated.

Embodiment one:

as shown in fig. 1, an adjustable dimension measuring instrument based on machine vision comprises an operation table 2, a detection table 3, a light source 4 and a camera 5. A through hole is formed in the middle of the detection table 3, a carrying plate 32 is arranged at the through hole, and the carrying plate 32 is made of transparent materials; the light source 4 is arranged below the carrying plate 32 and corresponds to the carrying plate 32; the camera 5 is arranged right above the carrying plate 32, and the camera 5 is arranged on the camera fixing plate 11; the console 2 is electrically connected to the light source 4 and the camera 5, and the console 2 can control the operations of the light source 4 and the camera 5.

As shown in fig. 2, the detection platform 3, the light source 4 and the camera 5 are disposed on the fixing frame 1, the fixing frame 1 is in a shape of a right quadrangular prism, the inside of the fixing frame is hollow, the fixing frame is disposed above the optical shock insulation platform 12, and the center of gravity is lowered through the optical shock insulation platform 12, so as to achieve the purpose of isolating external shock. And the four corners at the bottom of the optical shock insulation table 12 are provided with blessing Ma Lun.

A telecentric coaxial lens 51 is arranged at the lens of the camera 5, and a He-Ne laser 52 is arranged on the side surface of the telecentric coaxial lens 51, so as to facilitate the adjustment of the camera 5, the standard flat crystal 65 and the carrier plate 32 to a set state.

As shown in fig. 3 and 4, a standard flat crystal 65 is disposed between the camera 5 and the detection table 3, the standard flat crystal 65 is disposed on the slide rail adjusting device 6, a set included angle is maintained between the upper surface and the lower surface of the standard flat crystal 65, and in this embodiment, the lower surface of the standard flat crystal 65 is provided with an enhanced transmission film, so as to ensure sufficient transmission light intensity. Wherein an enhanced reflective film is provided on the upper surface of the carrier plate 32. The slide rail adjusting device 6 is located at the side of the camera 5 and the inspection table 3, and the slide rail adjusting device 6 includes a vertical plate 61 and a horizontal plate 62. The vertical plate 61 passes through the detection table 3; two mutually parallel vertical tracks are arranged on one surface of the vertical plate 61 close to the detection table 3, and a horizontal plate 62 is arranged on the vertical tracks of the vertical plate 61. The horizontal rail is arranged on one surface of the horizontal plate 62 close to the detection table 3, the standard flat crystal 65 is arranged on the horizontal rail, and the position of the standard flat crystal 65 is adjusted by adjusting the position of the standard flat crystal 65 on the horizontal rail and the position of the horizontal plate 62 on the vertical rail. The flatness of the part to be inspected can be detected by acquiring an image penetrating the standard flat crystal 65. The top of riser 61 is provided with camera backup pad 63, and the bottom of riser 61 is provided with light source backup pad 64, and wherein camera backup pad 63 and light source backup pad 64 are parallel to each other and the level sets up, and camera backup pad 63, light source backup pad 64 are made with riser 61 one-piece to be provided with bearing structure at the contained angle position between light source backup pad 64 and riser 61. The camera support plate 63 is fixedly connected with the camera 5, and the light source support plate 64 is fixedly connected with the light source 4. Wherein camera backup pad 63 still laminates with camera fixed plate 11, and camera backup pad 63 is located the lower surface of camera fixed plate 11, and camera fixed plate 11 also is used for fixed camera 5, and camera fixed plate 11 sets up in mount 1.

The detection table 3 is provided with a support 34, the support 34 is located on the carrying plate 32, and the support 34 is made of transparent materials and is used for fixing the part to be detected and avoiding the deviation of the part to be detected. The bracket 34 is in a straight quadrangular prism shape as a whole, and a groove is arranged in the middle of the bracket 34. The top of the bracket 34 can enable the part to be detected to be horizontally arranged, so that the camera 5 can acquire a front image of the part to be detected; the groove portion of the bracket 34 enables the part to be inspected to be arranged vertically, and further enables the camera 5 to acquire a side image of the part to be inspected. The depth of the groove of the bracket 34 is determined by the difference between the width and the thickness of the part to be detected, and by arranging the bracket and the groove on the bracket, the height of the acquired image is close when the right side of the part to be detected is upward and the side of the part to be detected is upward, and the image magnification of the camera is consistent.

The detection table 3 is arranged on the fixing frame 1, a vertical high-precision adjusting slide rail 35 is arranged between the detection table 3 and the fixing frame 1, and the vertical high-precision adjusting slide rail 35 is positioned at four corners of the detection table 3. The vertical high-precision adjustment slide rail 35 is adjusted to adjust the overall height and inclination angle of the detection table 3.

A laser distance measuring device 31 is arranged between the camera fixing plate 11 and the detection table 3, and the distance between the camera fixing plate 11 and the detection table 3 can be detected through the laser distance measuring device 31. The laser ranging device 31 includes a laser ranging sensor emitter and a laser ranging receiver, wherein the laser ranging receiver is disposed at four corners of the detection table 3, the laser ranging sensor emitter is disposed at four corners for the lower surface of the camera fixing plate 11, and the laser sensor emitter is disposed opposite to the laser ranging receiver.

A fine adjustment knob 33 is arranged between the carrying plate 32 and the detection table 3, and the height and the inclination angle of the carrying plate 32 can be adjusted by adjusting the fine adjustment knob 33.

As shown in fig. 5, the detection table 3 is further provided with a transparent checkerboard 36, and the transparent checkerboard 36 is disposed adjacent to the carrier plate 32. Accurate focusing for the camera 5 can be achieved by the transparent checkerboard 36. The detection table 3 is also provided with an identification card reader 37.

The console 2 is disposed above the camera fixing plate 11, and the console 2 includes a display module 21 capable of displaying the detection result and the process.

In the implementation process, the vertical high-precision adjusting slide rail 35 is adjusted through the laser ranging device 31, so that the camera fixing plate 11 is parallel to the detection table 3; the laser beam emitted by the He-Ne laser 52 passes through the telecentric coaxial lens 51, enters the upper surface of the standard flat crystal 65, is projected from the lower surface of the standard flat crystal 65, and reaches the carrier plate 32, wherein interference fringes with alternate brightness and darkness are formed between the lower surface of the standard flat crystal 65 and the upper surface of the carrier plate 32, and the micro-adjustment knob 33 is adjusted according to the fringe pattern, so that the parallelism between the lower surface of the standard flat crystal 65 and the carrier plate 32 is realized. And after the adjustment is finished, acquiring front and side images of the part to be detected, and uploading the images to the operation table 2 to finish the detection of the part to be detected.

As shown in fig. 6, a method for adjusting and measuring a dimension measurement scoring device includes the steps of:

In the third step, the lower surface of the standard flat crystal is adjusted to be parallel to the upper surface of the object carrying plate, firstly, light rays emitted by the He-Ne laser are required to obtain interference fringes through a camera, the interference fringes are processed to obtain information difference values of adjacent interference fringes, four fine adjustment knobs are continuously adjusted according to the difference values until the information difference values of the adjacent interference fringes are reduced to a set value, the interference fringes are approximately parallel to each other at equal intervals, and then the lower surface of the standard flat crystal is approximately parallel to the upper surface of the object carrying plate.

As shown in fig. 7 and 8, a machine vision-based sizing scoring method includes the following steps:

Step 3: user login is carried out according to the operation of an operator; the method comprises two login modes; one is to click through a 'tourist measurement' button to finish the login of the tourist and enter the tourist measurement flow; the other is to complete the teacher login or student login through identification by an identity card, and enter a corresponding teacher operation flow or student examination flow;

step 5: the operation desk selects the content of teacher operation according to the operation of the operator; if the 'download test question' button is clicked, the test question downloading procedure can be entered, and the procedure is ended after the test question downloading is completed; if the button for uploading the test questions is clicked, the test question uploading process can be entered, and the process is ended after the test question uploading is completed; if the 'make test question' button is clicked, the test question making process can be started, the dimension measuring interface is started, and the process is ended after the test question making is completed.

In the step 1, when the software on the console is opened, an opening software initialization operation is automatically executed, wherein the opening software initialization operation includes reading the examination folder, and initializing hardware and other initialization. It should be noted that, on the software of the operation desk, two folders related to the embodiment are provided, one is an examination folder, and the other is a production test question folder generated by a teacher producing test questions, in the embodiment, the name of the production test question folder is an examinoionfiles, and the name of the folder is kept unchanged. After the teacher makes the test questions, the test and uploading of the test questions can be performed.

The reading examination folder comprises the following steps:

step 1.1: judging whether an examination file name record file ExpinationFileName.txt exists or not. If the ExpamiationFileName.txt file exists, reading information in the file, wherein the read information is the name of the examination folder. If the ExpamiationFileName. Txt file does not exist, prompting the user to download examination questions from the server, otherwise, failing to perform the dimension measurement operation.

Step 1.2: judging whether the examination folder exists according to the name of the examination folder read by the ExpamiationFileName.txt, and if the examination folder exists, indicating that the files needed by the examination exist; if the test questions do not exist, prompting the user to download the test questions from the server, otherwise, not performing the dimension measurement operation.

Because the names of the examination folders are randomly generated, the examination folders need to be recorded through examination file name record files for searching whether the examination folders exist or not; on the other hand, the examination file name record file exists, the examination file name record file does not necessarily exist on behalf of the examination folder, and the examination file name record file is only used for searching the examination folder. All parameters and tools required by the size measurement are stored in the examination folder, and the parameters comprise a front measurement parameter, a side measurement parameter, a front calibration parameter, a side calibration parameter and a test question making tool. It should be noted that, reading the examination folder is pre-reading, in order to be able to load fast during the measurement of the subsequent size, raise the efficiency, and in actual measurement, the user's authority is combined to read the specific stored information in the examination folder.

The hardware initialization comprises the operation of opening a camera, and if the camera is successfully opened, when a dimension measurement interface is accessed, the function of drawing the camera is started to carry out real-time drawing; if the camera is opened, the user is prompted that the camera is opened unsuccessfully, meanwhile, the reason of the camera opening failure is given, the step 1 is ended, the process is ended, and the user can enter the following step 2 after the problem of the camera opening failure is solved.

The other initialization includes the initialization of the login interface and the initialization of related variables, and the initialization of the login interface includes the following aspects:

I. teacher operation panel visibility setting: invisible;

II. Guest login and exit system operation panel visibility settings: visible;

III, setting the visibility of a test question downloading and uploading progress display panel: invisible;

IV, setting the visibility of an operation process prompt box: visible;

v, enabling a timer for regularly reading identity information;

VI, enabling an operation timeout timer.

The initialization of the related variables includes the following two aspects:

1, the system first reads the initialization of the test file size measurement parameter flag bit, which is set to true in this embodiment.

2, the system initially acquires initialization of the examination information flag bit, which is set to true in this embodiment.

The system firstly reads the size measurement parameter flag bit of the examination file to confirm whether the size measurement parameter is read, if so, the flag is set to false, and the user does not need to read the parameter again after logging in at the moment, and only needs to update the size measurement parameter in each test question downloading. The system firstly acquires the examination information flag bit to confirm whether the examination information is read or not, for example, when a user logs in for the first time, if the examination information is not read before, the system firstly acquires the examination information flag bit to be true, the examination information is required to be read, the examination information is read while the test questions are downloaded, and the flag bit is set to false after the test questions and the examination information are downloaded; the examination information is a file for recording examination folder information, and the examination information comprises an examination file name recording file.

In the step 3, when the user logs in, the system is first accessed, the teacher logs in successfully, the login is overtime, the login is abnormal and the login account is wrong, the identity card information is read regularly, the reading of the identity card information is realized through an external identity card reader, and the timing time is set to be 500 milliseconds in the embodiment. The purpose of regularly reading the identity card information is to make a timely response to the new identity card information.

When the system is first accessed, if an identity card is inserted, firstly, a teacher is tried to log in according to the identity card information read by an identity card reader; if the teacher fails to log in, the student continues to try to log in, if the student fails to log in, the relevant information is prompted, and meanwhile, the identity card information is read again at regular time. If the identity card information reading failure includes that the identity card is not inserted, the identity card cannot be identified, the identity card information cannot finish teacher login, student login and the like when the system is accessed for the first time, only tourist login can be performed, and a tourist measurement flow is accessed. After the user finishes the student login or the teacher login, even if the failure includes that the identity card is not inserted, the identity card cannot be identified, the identity card information cannot finish the teacher login and the student login and the like when the identity card information is read regularly, the current login state and the login authority cannot be changed, and unless the obtained identity card information can finish other teacher logins or student logins when the identity card information is read regularly, the teacher login or the student login corresponding to the identity card information is switched.

The step of regularly reading the identity card information is as follows:

step 2.1: initializing connection of an identity card reader; if the initialization is successful, performing the next operation; if the initialization fails, prompting the user to confirm whether the identity card reader is connected normally or not, and ending the timing reading operation.

Step 2.2: card authentication operation between the identification card reader and the identification card; if the card authentication is successful, the next operation is carried out; if the card authentication fails, prompting the user that the identity card authentication fails, closing the connection of the identity card reader and ending the timing reading operation.

Step 2.3: reading identity card information; if the reading is successful, the identity card information is filled into an interface for display, the tourist measurement button is disabled, and a login thread is automatically started; if the reading fails, prompting the user that the reading of the identity card information fails, closing the connection of the identity card reader and ending the timing reading operation.

The guest measurement process in step 4 needs to enter a dimension measurement interface, wherein the following steps are performed before entering the dimension measurement interface:

step 3.1: judging whether the examination folder exists or not; if the test questions exist, the next operation is carried out, and if the test questions do not exist, the user is prompted to request to download the test questions;

Step 3.2: judging whether the examination file information is read for the first time; in the embodiment, whether the system acquires the examination information flag bit for the first time is true or not is shown, if yes, the next operation is performed after the examination file information parameters are read, and if not, the next operation is directly performed;

step 3.3: setting an operation authority as a guest authority; the visitor authority can only measure the size of the part to be detected, and cannot carry out the operations of a data uploading server and a test question making;

step 3.4: entering a size measurement interface, and setting a camera to start to collect images.

In the step 4, the student enters the student examination flow after logging in, firstly, a logging-in process timer is automatically started for timing, and logging-in time is counted. The student examination flow needs to judge whether the first examination information reading is started or not and whether the examination information is empty or not; if one is true, reading examination information; if the two are not established, the examination information is not required to be read, and the examination question information in the examination folder can be directly read.

The reading of the examination information comprises the following steps: if the examination information is successfully read, judging whether the name of the examination file read by starting is the same as the name of the examination file in the examination information; if the names are different, updating the test file name, and storing the test file name into a test file name record file; if the names are the same, the examination information reading is completed; if the examination information is read failure, including overtime of examination information reading or abnormal reading process, prompting the user for corresponding information, clearing interface identity information and re-timing reading the identity card information.

And judging whether the examination file exists or not when the examination information exists or the reading is successful. If the examination file does not exist, prompting the user that the test question does not exist, and reading the identity card information at a fixed time; if the examination file exists, judging whether the examination file is the first examination file, and if so, judging whether the examination file is the first examination file. If the first reading is the first reading, reading the relevant parameters of the size measurement, including camera configuration parameters, camera calibration parameters, relevant parameters of a calibration result and template information, and setting the operation authority as the student authority; if the reading is not the first reading, the size measurement related parameters are not required to be read. After judging whether the examination file is read for the first time, entering a size measurement interface, and starting image acquisition. In this embodiment the examination file comprises an examination folder.

If the student login operation is not completed, including login timeout or login abnormality, prompting related information, and simultaneously, reading the identity card information at a fixed time.

When the operation authority is the authority of the students, the system has the function of submitting answers and returning to the user login interface, and when the user authority is the teacher or tourists, the system only returns to the user login interface function.

And 5, starting a login process timer to count after finishing the login operation of the teacher, and counting the login time. If the teacher logs in overtime or the network is abnormal in the login process, enabling a tourist login button to read the identity card information again.

The teacher operation comprises a test question downloading flow, a test question uploading flow and a test question making flow. In this embodiment, after the teacher logs in, the teacher will not jump to the dimension measurement interface immediately, but the teacher operation panel is displayed on the user login interface, and buttons for downloading test questions, uploading test questions and making test questions are provided on the teacher operation panel, which correspond to the test question downloading flow, the test question uploading flow and the test question making flow respectively.

If the user clicks the "download test question" button, the "download test question", "upload test question", "make test question" and "guest measurement" buttons are disabled. A prompt box is jumped out of the display module of the operation desk, and a' download test question, please wait! And starting the test question downloading thread and simultaneously carrying out test question downloading timing time statistics. It should be noted that examination information is acquired before the test questions are downloaded. If the examination information is successfully acquired, setting a test question downloading file name and an examination file name according to the examination information, and simultaneously downloading the test questions according to the compressed file name of the examination information; if the examination information is failed, overtime or abnormal, prompting corresponding information, clearing the identity card information for display, and reading the identity card information at a fixed time. And displaying the downloading progress in the downloading process, automatically decompressing the test file after the test questions are downloaded, reading the test file information, and prompting that the test questions are downloaded successfully. The read examination file information comprises the following steps:

a. Camera configuration parameters and camera calibration parameters;

b. calibrating result related parameters;

c. template information.

If the user clicks the "upload test questions" button, the test question uploading process is entered. The test question uploading process firstly needs to judge whether a test question creating folder exists or not; if yes, compressing the file folder for making the test questions, displaying the compression progress, and uploading the compressed file to the server after the compression is completed; and meanwhile, extracting the number of the dimension to be measured and the judging basis of the qualified measured dimension according to the dimension measurement information in the production test question file, and uploading the extracted number to a server. If not, the user is prompted to indicate that the test question does not exist, please make the test question-! ". The number of the dimension to be measured and the judgment basis for qualified measurement are extracted after editing in a test question making editor, and the upper tolerance limit and the lower tolerance limit of the dimension to be measured and qualified production of the dimension are set in the editor.

If the user clicks a button for making test questions, if the examination file information of the test questions made by the teacher is not read before, the examination file information is read, meanwhile, the operation authority is set as the teacher authority, and the teacher authority can make test questions and measure the sizes of parts for making the test questions; opening the size measurement interface, setting the camera to start collecting images, setting parameters and completing test question making. The method is characterized in that a dimension measurement interface which is accessed by a teacher authority is used for measuring parts by making information stored in a test question folder; other authorities, including student authorities and guest authorities, enter a dimension measurement interface that uses information stored in the examination folder to measure dimensions.

The exit system operation may be performed in both the user login interface and the dimension measurement interface. After clicking the 'exit system' button in the two interfaces, the user is prompted whether to determine to exit the system, and if the user selects yes, the system is exited.

A dimension measurement scoring system based on machine vision comprises a dimension measurement interface, wherein the dimension measurement interface is provided with a system setting button, a front measurement button and a side measurement button. The size measurement interface can complete the functions of parameter configuration, test question making, template calibration and size measurement, wherein the parameter configuration, the test question making and the template calibration are arranged under the corresponding directory of a system setting button of the size measurement interface, a password is required to be input in system setting, and the parameter configuration, the test question making and the template calibration can be performed only by inputting a correct password, wherein the test question making function can be operated only by a teacher right; clicking a front measurement button or a side measurement button, and performing a size measurement flow by the system; the size measurement interface is also provided with a 'system exit' button, after clicking the 'system exit' button, the user is prompted whether to determine to exit the system, and if the user selects to exit the system, the user exits the system. The size measurement interface for the student permission to enter is also provided with an answer submitting button, after the system exiting button is clicked, a user is prompted whether to determine the answer submitting, if the user selects the answer submitting, the answer submitting comprises uploading pictures, scores and the like, and the system exiting is performed.

The parameter configuration button is clicked to pop up a parameter setting dialog box, and the parameter setting dialog box is provided with functions of camera parameter configuration, calibration parameter configuration and data statistics. The camera parameter configuration includes settings for pixel binning, acquisition frame rate, processing frame rate, and exposure. The calibration parameter configuration includes the setting of the transverse point number, the longitudinal point number and the unit interval. The data statistics comprise the number of pictures and the setting of filter coefficients.

The test question making dialog box can be popped up after the test question making button is clicked, and front test question making and side test question making can be completed in the test question making dialog box, wherein the front test question making corresponds to the front face of the part to be detected, and the side test question making corresponds to the side face of the part to be detected. Front test question making and side test question making are respectively corresponding to a front button and a side button of the test question making dialog box. Clicking a front or side button in a test question making dialog box to enter a test question making process, wherein the test question making process comprises the following steps of:

step 4.1: acquiring a real-time diagram acquired by a current camera, opening a test question making dialog box, and transmitting the real-time diagram;

Step 4.2: making test questions, including task editing of various size measurement types, and setting the maximum tolerance upper limit and the maximum tolerance lower limit of measurement;

step 4.3: when exiting the test question making dialog box, extracting test question template information, and measuring the size of the template source diagram; the template source diagram represents an image of a standard component when the standard component is randomly placed in the view field range of the camera;

step 4.4: the relevant measurement results are saved and used in real-time dimension measurement.

It should be noted that the system will guide the placement of the part to be detected before the camera captures the real-time image. The process of guiding the placement of the parts to be detected is as follows: the size measurement interface image display window displays a guide image based on the template source image, guides a user to place the corresponding object measurement surface upwards and places the object in a proper area range. The guiding of the placement of the parts to be detected can prevent errors of the measuring surface and is also beneficial to the next measurement. The manufacturing flow of the guide map comprises the following steps:

step 4.1.1: taking the gray value of each pixel point in the template source image to 80% of the original value;

step 4.1.2: taking the gray value of each pixel point in a blank image with the same size (the gray value of each pixel is the maximum value 255) as 20% of the original value;

Step 4.1.3: superposing the two images according to gray values to obtain a guide image; wherein the pixel point with the gray value of 0 is displayed with pure black, and the pixel point with the gray value of 255 is displayed with pure white.

As shown in fig. 21, the task editing of various types of dimension measurement in step 4.2 includes editing measurement types of four basic elements including circle, line, arc and angle, so as to obtain corresponding mask characteristic information, namely a mask diagram. Wherein the line width of the circle, line, arc and angle element measurement types can be adjusted, and the line is displayed as a white area in the mask map; and outputting corresponding characteristic information after finishing the adjustment of the line width.

The circle measurement type task editing comprises the following steps:

step 4.2.1: determining a measurement type name;

step 4.2.2: determining a measurement switch value, a circle radius accurate value, an upper tolerance limit and a lower tolerance limit; the above parameters are entered by the user;

step 4.2.3: determining center coordinates, width, height and radius; and the parameters are calculated according to vector information corresponding to the graph of the minimum line width drawing measurement type during editing.

The line measurement type task editing includes the steps of:

step 4.3.1: determining a measurement type name;

step 4.3.2: determining a measurement switch value, a circle radius accurate value, an upper tolerance limit and a lower tolerance limit; the above parameters are entered by the user;

Step 4.3.3: determining the inclination angle, the length of the straight line segment and the coordinates of two end points; and the parameters are calculated according to vector information corresponding to the graph of the minimum line width drawing measurement type during editing.

The arc measurement type task editing includes the steps of:

step 4.4.1: determining a measurement type name;

step 4.4.2: determining a measurement switch value, a circle radius accurate value, an upper tolerance limit and a lower tolerance limit; the above parameters are entered by the user;

step 4.4.1: determining the radius, the angle and the coordinates of three points, wherein two points are positioned at the starting and ending points of the arc, and the other point is positioned elsewhere; and the parameters are calculated according to vector information corresponding to the graph of the minimum line width drawing measurement type during editing.

The angle measurement type task editing includes the steps of:

step 4.5.1: determining a measurement type name;

step 4.5.2: determining a measurement switch value, a circle radius accurate value, an upper tolerance limit and a lower tolerance limit; the above parameters are entered by the user;

step 4.5.3: determining the included angle and three point coordinates forming the included angle, wherein one point is positioned at the vertex of the included angle; and the parameters are calculated according to vector information corresponding to the graph of the minimum line width drawing measurement type during editing.

The combination measurement types of the two-point distance, the point-to-line distance, the two-straight line segment distance and the like can be obtained through the combination of four basic elements of circles, lines, arcs and angles. The distance between the two points comprises: the distance between the centers of circles, the distance between the centers of circles and the arc centers, the distance between the centers of circles and the vertexes of the included angles, and the like; the belonging point-to-line spacing includes: the distance from the circle center to the straight line, the distance from the arc center to the straight line, the distance from the vertex of the included angle to the straight line, and the like.

The two-point distance measuring algorithm is to calculate two-point coordinates and then calculate the distance between the two points. The point-to-straight line distance measuring algorithm is to calculate the point coordinates and the coordinates of two ends of the straight line segment respectively, and then calculate the distance from the point to the straight line segment. The distance measuring algorithm of the two straight line segments is to calculate the end point coordinates of the two straight line segments, calculate the distance from the two end points of one straight line segment to the other straight line segment, and then add the calculated two distances to obtain the average value, namely the distance between the two straight line segments.

In this embodiment, measurement data of four basic elements of a circle, a line, an arc and an angle are displayed in real time, wherein a circle measurement type displays a center coordinate and a radius value in real time, a straight line measurement type displays an inclination angle and a length value in real time, an arc measurement type displays an arc angle in real time, and an angle measurement type displays an included angle degree in real time. And finishing task editing of the circle, line, arc and angle measurement type to obtain corresponding mask characteristic information.

As shown in fig. 9, the extracting of the test question template information in the step 4.4 includes the following steps:

step 4.6.1: carrying out mean value filtering treatment on the template source diagram; the average filter window size in this embodiment is 5*5; the template source image is an image of the front face and the side face of the standard component obtained by the camera;

step 4.6.2: further thresholding; the pixel gradation value thresholding to be larger than the set threshold is set to 0, otherwise, 255; in the embodiment, the threshold value is taken as 100;

step 4.6.3: extracting outline points of a standard component in a template source diagram;

step 4.6.4: obtaining the minimum circumcircle of the outer contour to obtain the center coordinates and the radius;

step 4.6.5: extracting the ROI according to the calculated center coordinates and radius; the ROI is a rectangle, the side length of the rectangle is the diameter of the minimum circumscribing circle of the standard component in the template source diagram, the center of the rectangle is the center of the minimum circumscribing circle of the standard component, and the rotation angle of the rectangle is zero; ROI represents a region of interest

Step 4.6.6: extracting hierarchy profile information from the ROI, wherein the hierarchy profile information comprises outer profile information and inner profile information, and the outer profile and the inner profile meet the parent-child hierarchy relationship; if the outer contour and the inner contour meet the relationship of father and son levels, the outer contour is a father contour, and the inner contour is a son contour;

Step 4.6.7: obtaining the minimum circumscribed rectangle of the zero rotation angle of the outline of the rectangle, obtaining the length and width of the rectangle, and judging whether the length or width of the rectangle is larger than a set value; in this embodiment, it is expressed whether the length is greater than the number of rows of the ROI minus 2, and the width is greater than the number of columns of the ROI minus 2;

step 4.6.8: if the length or width of the rectangle is greater than the set value, the standard component is out of bounds, and the step 4.6.16 is skipped;

step 4.6.9: if the length or width of the rectangle is not larger than the set value, calculating the centroid and the minimum circumscribed rectangle of the outer contour to obtain the center coordinate, the rotation angle, the length, the width and the area of the rectangle; then judging whether an inner contour exists or not;

step 4.6.10: if the inner contour does not exist, jumping to step 4.6.16;

step 4.6.11: if the inner contour exists, judging whether the inner contour has only one effective inner contour or not;

step 4.6.12: if only one effective inner contour exists, the center coordinates, the rotation angle, the length, the width and the area of the centroid and the minimum circumscribed rectangle are obtained, and the step 4.6.16 is skipped;

step 4.6.13: if a plurality of effective inner contours exist, traversing all the effective inner contours, solving the maximum value and the minimum value of the minimum circumscribed rectangular area of the inner contours, and comparing whether the difference value between the maximum value and the minimum value is larger than a set value; in this embodiment, the set value takes the sum of squares of 10 pixels;

Step 4.6.14: if the difference value between the maximum value and the minimum value of the minimum circumscribed rectangular area is larger than the set value, the maximum inner contour and the minimum inner contour are indicated; respectively obtaining the mass centers, the center coordinates of the minimum circumscribed rectangle, the rotation angle, the length, the width and the area of the mass centers, and jumping to the step 4.6.16;

step 4.6.15: if the difference value between the maximum value and the minimum value of the minimum circumscribed rectangular area is smaller than or equal to the set value, marking that a standard component has a plurality of effective maximum inner contours, optionally taking one of the effective maximum inner contours, obtaining center coordinates, rotation angles, length and width and area of the center of mass and the minimum circumscribed rectangular area, and jumping to the step 4.6.16;

step 4.6.16: extracting circle, line, arc and angle measurement type characteristic information according to the circle, line, arc and angle measurement type task editing information;

step 4.6.17: and ending the extraction flow of the template information of the test questions.

As shown in fig. 10, in the step 4.6.16, the process of extracting the circle measurement type information in the template source diagram includes the following steps:

step 4.7.1: extracting a circle measurement type ROI in a template source diagram according to mask characteristic information of the corresponding circle measurement type obtained by task editing;

step 4.7.2: filtering the ROI gray scale image, wherein the filtering is Gaussian filtering; in the embodiment, the size of a filtering window of Gaussian filtering treatment is 5*5, and the standard deviation is 2;

Step 4.7.3: performing Hough circle finding processing on the filtered image to obtain a plurality of circles;

step 4.7.4: comparing the circles obtained in the step 4.7.3 with the circle centers of the selected mask circles respectively, and judging whether the circle center deviation is smaller than a set value or not; in this embodiment, the set value is 2mm;

step 4.7.5: if the circle center offset is greater than or equal to the set value, changing the threshold value of the Hough circle finding threshold value parameter, and jumping to the step 4.7.3; the changing of the parameter threshold value of the Hough rounding refers to reducing the parameter threshold value, and the parameter threshold value is the same in the following processes and steps, the parameter threshold value represents the accumulated threshold value of the circle center of the Hough gradient rounding detection method in the detection stage, the smaller the changing of the parameter threshold value of the Hough rounding is, the more non-existing circles can be detected, and if the threshold value is larger, the detected circles are more approximate to perfect circles; the threshold value in this embodiment ranges from 5 pixels to 1/5 of the corresponding mask circumference, which value is reduced by 5 pixels each time it is performed;

step 4.7.6: if the circle center deviation is smaller than the set value, screening out a Hough fitting circle with the smallest absolute difference value between the template source diagram and the mask circle radius, and entering a step 4.7.7;

step 4.7.7: comparing with the radius of the mask circle, judging whether the absolute difference value of the radius is smaller than a set value; in this embodiment, the set value is 2mm;

Step 4.7.8: if the absolute difference value of the radius is larger than or equal to the set value, changing the threshold value of the Huff circle finding threshold value parameter, and jumping to the step 4.7.3;

step 4.7.9: if the absolute difference value of the radius is smaller than the set value, finding out a proper Hough fitting circle;

step 4.7.10: performing edge detection on the ROI gray level map by using a Canny operator;

step 4.7.11: the ROI image and the mask ROI image after Canny treatment are phase-locked; the phase-to-phase algorithm refers to that edge points obtained by Canny edge detection processing in the ROI image are reserved in a white ring drawn in the mask ROI image, and other points are removed, as shown in FIG. 22;

step 4.7.12: extracting edge contour points to be detected of the phase and the rear image;

step 4.7.13: screening out proper contour points according to the distance from the contour points to the Hough fitting circle to form a new contour point set;

step 4.7.14: fitting a circle to the new contour point set by using a least square method to obtain a circle center and a radius;

step 4.7.15: the present flow is ended.

It should be noted that the flow of extracting the arc measurement type information in the template source diagram is identical to the flow of extracting the circle measurement type information in the template source diagram, and the difference is only different from the extracted ROI.

It should be noted that there may be a plurality of mask feature information of the circle measurement type, and the above measurement flow is performed separately for each mask feature information of the circle measurement type; mask feature information for arc, line, and angle measurement types is also a separate measurement procedure.

As shown in fig. 11, in the step 4.6.16, the process of extracting the line measurement type information in the template source diagram includes the following steps:

step 4.8.1: extracting a linear measurement type ROI in a template source diagram according to the mask characteristic information of the corresponding line measurement type obtained by task editing;

step 4.8.2: performing edge detection on the ROI gray level map by using a Canny operator;

step 4.8.3: carrying out Hough straight line finding processing on the image processed by Canny to obtain a plurality of straight line segments;

step 4.8.4: comparing the straight line segment obtained in the step 4.8.3 with the inclination angle of the mask straight line segment, and judging whether the inclination angle deviation is smaller than a set value or not; in this embodiment, the set value is 7.5 degrees;

step 4.8.5: if the inclination angle deviation is greater than or equal to a set value, changing a threshold value of a Hough finding straight line parameter, and jumping to the step 4.8.3 for execution, wherein the Hough finding straight line parameter comprises a threshold value parameter of an accumulated plane, the length of the lowest line segment and the maximum line forming distance; the threshold parameter of the accumulation plane represents the value that a portion must reach in the accumulation plane when it is identified as a straight line in the graph; the maximum line formation represents the maximum distance that allows the same line of points to be connected together; in the embodiment, the threshold parameter threshold value expression of the accumulation plane is 160-2*M, the threshold value expression of the length of the lowest line segment is 80-M, the threshold value expression of the maximum line spacing is 36-2*q, wherein M is more than or equal to 0 and less than or equal to 71,0 and less than or equal to Q is more than 16, the initial value of M is 0, the initial value of Q is 0, and each time step c is executed, M is added by 5, and Q is added by 1;

Step 4.8.6: if the inclination angle deviation is smaller than the set value, screening out the straight line segment with the longest length from the straight line segments meeting the inclination angle deviation;

step 4.8.7: the ROI image and the mask ROI image after Canny treatment are phase-locked;

step 4.8.8: extracting edge contour points to be detected of the phase and the rear image;

step 4.8.9: screening out proper contour points according to the distance from the contour points to the Hough fitting straight line segment to form a new contour point set;

step 4.8.10: fitting a straight line to the new contour point set by using a least square method to obtain an inclination angle and coordinates of two end points of a straight line segment;

step 4.8.11: the present flow is ended.

As shown in fig. 12, in the step 4.6.16, the process of extracting the angle measurement type information in the template source diagram includes the following steps:

step 4.9.1: extracting an angle measurement type ROI in a template source diagram according to mask characteristic information of the corresponding angle measurement type obtained by task editing;

step 4.9.2: performing edge detection on the ROI gray level map in the template source map by using a Canny operator;

step 4.9.3: carrying out Hough straight line finding processing on the image processed by Canny, and obtaining a plurality of straight line segments in a template source diagram;

step 4.9.4: according to the oblique angles of the two straight line segments forming the included angle in the mask angle, including the oblique angle of the first straight line segment and the oblique angle of the second straight line segment, two groups of straight line segments are screened out from the plurality of straight line segments obtained in the step 4.9.3, namely the first group of straight line segments and the second group of straight line segments, wherein the absolute value of the difference between the oblique angle of the straight line segment in the first group of straight line segments and the oblique angle of the first straight line segment in the mask angle is smaller than a set value, 7.5 degrees in the embodiment, and the absolute value of the difference between the oblique angle of the straight line segment in the second group of straight line segments and the oblique angle of the second straight line segment in the mask characteristic information is smaller than the set value, and 7.5 degrees in the embodiment; if each group of straight line segments selected by the screening method at least comprises one straight line segment, the screening is successful, otherwise, the screening is failed;

Step 4.9.5: if the screening in the step 4.9.4 is not successful, changing the straight line parameter of the Hough finding, and jumping to the step 4.9.3 for execution;

step 4.9.6: if the screening in the step 4.9.4 is successful, respectively calculating the distance from the end point of any one straight line segment in the mask angle to the other straight line segment, wherein the end point is one end far away from the included angle, obtaining two distance values, and taking a smaller distance value D in the two distance values; traversing the first group of straight line segments obtained in the step 4.9.4, screening out the straight line segments with the distance from the straight line segments to the set point smaller than the set point to form a new first group of straight line segments, wherein the set point is the end point of the first straight line segment far away from one end of the included angle in mask characteristic information, in the embodiment, if D/5 is more than 70 pixels, the set point is 70 pixels, otherwise, the set point is D/5; similarly, traversing the second group of straight line segments obtained in the step 4.9.4, screening out the straight line segments with the set point to straight line segment distance smaller than the set point, and forming a new second group of straight line segments, wherein the set point is the end point of the second straight line segment far away from one end of the included angle in mask characteristic information, and the set point has the same value as the first group of straight line segments; if the new first group of straight line segments and the new second group of straight line segments meet the requirement of at least one straight line segment, the screening is successful, otherwise, the screening fails;

Step 4.9.7: if the screening in the step 4.9.6 is not successful, changing the Hough straight line finding parameter, and jumping to the step 4.9.3 for execution;

step 4.9.8: if the screening in the step 4.9.6 is successful, traversing a random group of straight line segments in the new first group of straight line segments and the new second group of straight line segments, and screening out the straight line segment with the longest length;

step 4.9.9: obtaining the included angle between the longest straight line segment obtained in the step 4.9.8 and each straight line segment in the other group of straight line segments;

step 4.9.10: comparing the included angle obtained in the step 4.9.9 with the included angle of the mask, screening out straight line segments meeting the conditions from the other group of straight line segments according to the fact that the difference value between the included angle and the angle of the mask is smaller than a set value, and judging whether the screening is successful or not; if at least one straight line segment is screened out from the other group of straight line segments, the screening is successful;

step 4.9.11: if the screening in the step 4.9.10 is not successful, changing the Hough straight line finding parameter, and jumping to the step 4.9.3 for execution;

step 4.9.12: if the screening in the step 4.9.10 is successful, screening out the straight line segment with the longest length from the other group of straight line segments after the screening in the step 4.9.10 is completed;

step 4.9.13: obtaining two straight line segments through the steps 4.9.8 and 4.9.12, calculating an included angle between the two straight line segments, comparing the included angle with a mask included angle, and judging whether the deviation is smaller than a set value; in this embodiment, the set value is 10 degrees;

Step 4.9.14: if the deviation is greater than or equal to the set value, the characteristic information of the lift angle measurement type fails, and the step 4.9.19 is skipped to execute;

step 4.9.15: if the deviation is smaller than the set value, finding the outer contour of the image after Canny processing;

step 4.9.16: screening two contour point sets according to the distance from the contour point to the two straight line segments;

step 4.9.17: fitting straight lines to the two contour point sets by using a least square method to obtain two end point coordinates and an oblique angle;

step 4.9.18: further obtaining an included angle and vertex coordinates of the two straight line segments;

step 4.9.19: the present flow is ended.

The template calibration button can enter a template calibration interface after being clicked, distortion correction and amplification rate calculation can be carried out on the current measured part at the template calibration interface, distortion parameters and amplification rate are obtained through calibration, and the parameters are used for size measurement in real-time measurement. Clicking a front or side button arranged in a template calibration interface to enter a template calibration process, wherein the template calibration process comprises the following steps:

step 5.1: the calibration plate is placed at different positions in the view field, and the images of the calibration plate are respectively acquired;

step 5.2: after the image acquisition of the calibration plate is completed, closing the camera acquisition, and calling a calibration algorithm to perform image calibration processing;

Step 5.3: after the calibration process is completed, updating the calibration parameters to the latest calibration parameters;

step 5.4: and exiting the template calibration interface.

As shown in fig. 13 and 14, the image calibration process in step 5.2 includes obtaining distortion parameters and obtaining magnification. The distortion parameters are obtained through a Zhengyou distortion correction algorithm, which comprises the following steps:

step 5.1.1: reading calibration image data and calibration parameters of the acquired image, wherein the transverse points in the calibration parameters are the number of rows of the checkerboard of the index calibration plate, the longitudinal points are the number of columns of the checkerboard, and the unit interval is the real physical size of each cell of the checkerboard;

step 5.1.2: extracting corner information from each frame of calibration image;

step 5.1.3: further extracting sub-pixel corner information by using the extracted corner information;

step 5.1.4: initializing a space three-dimensional coordinate system of the corner points on the calibration plate;

step 5.1.5: carrying out camera calibration by using the extracted sub-pixel angular point information and the spatial three-dimensional coordinate system information of the angular points on the calibration plate to obtain distortion parameters participating in each frame of image in the camera, and rotation vectors and translation vectors of each frame of image;

step 5.1.6: evaluating the calibration result; firstly, obtaining distortion parameters through camera calibration, carrying out reprojection calculation on a space three-dimensional coordinate point of each frame of image to obtain a new projection point, calculating the error between the new projection point and an old projection point, if the error is smaller than a set value of 0.15 pixels, conforming to the requirements, storing a calibration result and the distortion parameters, and ending the process; if the error is greater than or equal to 0.15 pixel of the set value, the process is ended and the acquisition of the calibration image is prompted.

The process of obtaining the magnification comprises the following steps:

step 5.2.1: correcting the acquired calibration image of a certain frame by using the calibration result;

step 5.2.2: extracting corner information from the corrected image;

step 5.2.3: extracting sub-pixel corner information;

step 5.2.4: traversing the corrected image column number, and calculating and storing the distance from the first row to the first row of each column;

step 5.2.5: sorting the saved intervals of each column;

step 5.2.6: selecting a plurality of columns with the middle column as a center, and accumulating the saved intervals of the selected columns;

step 5.2.7: according to the accumulated value, calculating an average value;

step 5.2.8: according to the average value, the column number and the physical size, the amplification rate is calculated, and the calculation formula of the amplification rate is the average value/(column number-2)/the physical size;

step 5.2.9: the present flow is ended.

The dimension measurement flow comprises the following steps:

step 6.1: detecting part out-of-limit according to the current real-time diagram, and judging whether the detected part is out-of-limit or not; if the part is out of limit, a prompt box is popped up to prompt the user that the part to be tested is out of limit, and the user closes the prompt box and then performs the next operation; if the operation is not out of the limit, the next operation is directly carried out;

step 6.2: judging whether the front template or the side template exists, if so, carrying out the next operation, otherwise, prompting to manufacture the template, then measuring, and ending the flow;

Step 6.3: judging whether an image is acquired or not; if the image is acquired, starting a front/side dimension measurement processing thread, and running a dimension measurement algorithm; if no image is acquired, prompting the user that no image is acquired, and ending the flow;

step 6.4: judging whether the number of the processed pictures reaches a processing threshold value or not; if the processing threshold is not reached, prompting that the camera is started, continuously collecting n images, wherein n represents the number of the images which are missing, and ending the flow; if the processing threshold is reached, front/side data processing is performed; the data processing is to calculate standard deviation of the processing result data of each picture, and calculate the average value of the rest data after the data is kicked off according to the standard deviation;

step 6.5: after the data processing is completed, the measurement results of the respective sizes are displayed on the interface.

As shown in fig. 15, the part out-of-limit detection in the step 6.1 includes the following steps:

step 6.1.1: reading a to-be-detected image and a template source image of a part to be detected;

step 6.1.2: carrying out differential processing on a to-be-detected image of the part to be detected and a template source image, and judging whether the two frames of images are consistent; if the shapes and the displacements of the parts to be detected are consistent, the Flag bit Flag is set to 0, if the shapes and the displacements of the parts to be detected are inconsistent, the shapes or the displacements of the parts to be detected are changed, and the Flag bit Flag is set to 1;

Step 6.1.3: filtering the diagram to be tested; removing high-frequency noise points through median filtering processing, and reserving contour edge information, wherein a median filtering window is 9 pixels by 9 pixels in the embodiment;

step 6.1.4: performing gray threshold binarization processing on the filtered image; wherein the pixel gray value greater than the set threshold is set to 255, and conversely, to 0; the present embodiment sets a threshold value of 180;

step 6.1.5: searching all closed loop contours in the image; the closed-loop profile means that the distance between any two adjacent profile points in the profile is smaller than a set value, and the set value of the embodiment takes 2 pixels;

step 6.1.6: solving the perimeter of the maximum closed-loop outline, and judging whether the perimeter meets the setting condition or not; setting the condition that the maximum closed-loop contour perimeter is not less than 0.99 times and not more than 1.01 times of the image perimeter; if the circumference does not meet the condition, checking the Flag bit Flag, and ending the flow; if the circumference satisfies the condition, go to step 6.1.7; if Flag is equal to 0, the detection result indicates that the part to be detected is out of bounds, but the shape and displacement of the part to be detected are unchanged; if Flag is equal to 1, the detection result indicates that the part to be detected is out of bounds and the shape or displacement of the part to be detected changes;

Step 6.1.7: solving the maximum closed-loop contour centroid, and judging whether the centroid meets the set condition or not;

the setting condition is that the distance between the transverse coordinate of the mass center (X-axis coordinate) and the transverse coordinate of the center point of the image is not more than a set value, 5 pixels are taken in the embodiment, and the distance between the longitudinal coordinate of the mass center (Y-axis coordinate) and the longitudinal coordinate of the center point of the image is also not more than the set value, and 5 pixels are taken in the embodiment; if the mass center does not meet the set condition, checking a Flag bit Flag, wherein if the Flag is equal to 0, the detection result indicates that the part to be detected is out of bounds, but the shape and displacement of the part to be detected are unchanged; if Flag is equal to 1, the detection result indicates that the part to be detected is out of bounds and the shape or displacement of the part to be detected changes; if the mass center meets the set condition, judging whether the total closed-loop contour number in the image is 1 or not;

if the total closed-loop contour number in the image is 1, checking a Flag bit Flag; if the Flag is equal to 0, the detection result is that the part to be detected is out of bounds but the shape and the displacement of the part to be detected are unchanged, and if the Flag is equal to 1, the detection result is that the part to be detected is out of bounds and the shape or the displacement of the part to be detected is changed; if the total number of closed loop contours in the image is greater than 1, checking a Flag bit Flag, if the Flag is equal to 0, the detection result is that the part to be detected is unbounded and the shape and displacement of the part to be detected are unchanged, and if the Flag is equal to 1, the detection result is that the part to be detected is unbounded and the shape or displacement of the part to be detected is changed;

Step 6.1.8: the present flow is ended.

The differential processing in the step 6.1.2 is specifically implemented as follows: firstly, differentiating a to-be-detected image and a template source image, comparing gray values of all pixel points in two frames of images, and adding 1 to a gray value statistical value when the gray value statistical value is larger than a set value, wherein the gray value initial value is 0, and the set value is 80 in the embodiment; after all the pixel points are traversed, the gray value statistical value is larger than a set threshold value, which indicates that the shape or displacement of the part to be detected changes, otherwise, the shape or displacement of the part to be detected is unchanged, and the set threshold value is 99% of the number of all the pixel points in the embodiment.

As shown in fig. 16, the size measurement algorithm in step 6.3 includes the following steps:

step 6.2.1: correcting the read real-time map to be tested by using calibration parameters;

step 6.2.2: judging whether the shape and displacement of the part to be detected are unchanged;

step 6.2.3: if the shape and displacement of the part to be detected are unchanged, measuring each measuring type according to the extracted characteristic information of the template source diagram;

step 6.2.4: if the shape and/or displacement of the part to be detected changes, searching and matching the object, and judging whether the part to be detected is matched with the template source diagram;

Step 6.2.5: if the part to be detected is matched with the template source diagram, measuring the circle, the line, the arc and the angle measurement type according to the extracted characteristic information of the template source diagram, and ending the flow;

step 6.2.6: if the part to be detected is not matched with the template source diagram, the fact that the part to be detected is not found is indicated, and the process is ended.

As shown in fig. 17, in the step 6.2.4, the object searching and matching process includes the following steps:

step 6.3.1: carrying out mean value filtering treatment on the graph to be measured; the mean filter window in this embodiment is 3 pixels by 3 pixels;

step 6.3.2: performing thresholding processing, setting the gray value of the pixel larger than the set threshold to 0, otherwise setting the gray value to 255, and setting the set threshold to 100 in the embodiment;

step 6.3.3: extracting outline information of the hierarchical part to be detected; the outline information of the to-be-detected hierarchical part comprises outline information and inner outline information of the to-be-detected part, wherein the outline and the inner outline meet the parent-child hierarchical relationship, the outer outline is a parent outline, and the inner outline is a child outline;

step 6.3.4: judging whether the absolute value of the difference between the minimum circumscribed rectangular area of the outer contour of the part to be detected and the minimum circumscribed rectangular area of the outer contour of the template source diagram is smaller than a set value; in the embodiment, the value range of the set value is 15% of the minimum circumscribed rectangular area of the outline of the template source diagram;

Step 6.3.5: if the absolute value of the difference between the minimum circumscribed rectangular area of the outer contour of the part to be detected and the minimum circumscribed rectangular area of the outer contour of the template source diagram is larger than or equal to a set value, ending the flow;

step 6.3.6: if the absolute value of the difference between the minimum circumscribed rectangular area of the outer contour of the part to be detected and the minimum circumscribed rectangular area of the outer contour of the template source diagram is smaller than a set value, judging whether the absolute value of the difference between the minimum circumscribed rectangular length-width ratio of the outer contour of the part to be detected and the minimum circumscribed rectangular length-width ratio of the outer contour of the template source diagram is smaller than the set value or not; the value range of the set value in the embodiment is 10% of the minimum circumscribed rectangular length-width ratio of the outline of the template source diagram;

step 6.3.7: if the absolute value of the minimum external rectangular length-width ratio of the outer outline of the part to be detected and the minimum external rectangular length-width ratio difference of the outer outline of the template source diagram is larger than or equal to a set value, ending the flow;

step 6.3.8: if the absolute value of the difference between the minimum external rectangular length-width ratio of the outer outline of the part to be detected and the minimum external rectangular length-width ratio of the outer outline of the template source diagram is smaller than a set value, solving a minimum external circle of the outer outline, and taking the circle center as a rotation center;

step 6.3.9: judging whether the distance between the outline centroid of the template source diagram and the minimum circumscribed rectangle center of the outline of the template source diagram is larger than a set value or not; the set value in this embodiment is 20 pixels;

Step 6.3.10: if the distance between the outline centroid of the template source diagram and the minimum circumscribed rectangle center of the outline of the template source diagram is smaller than or equal to the set value, jumping to a step 6.3.18;

step 6.3.11: if the distance between the outline centroid of the template source diagram and the minimum circumscribed rectangle center of the outline of the template source diagram is larger than a set value, judging whether the absolute value of the difference between the outline centroid of the part to be detected and the minimum circumscribed rectangle center of the outline centroid of the template source diagram and the aspect ratio of the outline centroid of the template source diagram to the minimum circumscribed rectangle is smaller than the set value; the value range of the set value in the embodiment is 10% of the length-width ratio from the outline centroid of the template source diagram to the minimum circumscribed rectangle of the outline;

step 6.3.12: if the absolute value of the difference between the center distance between the outline centroid of the part to be detected and the minimum circumscribed rectangle and the aspect ratio between the outline centroid of the template source diagram and the minimum circumscribed rectangle of the outline thereof is greater than or equal to a set value, jumping to a step 6.3.18;

step 6.3.13: if the absolute value of the difference between the center distance between the outline centroid of the part to be detected and the minimum circumscribed rectangle and the length-width ratio between the outline centroid of the template source diagram and the minimum circumscribed rectangle of the outline centroid of the part to be detected is smaller than a set value, the rotation angle of the part to be detected relative to the template source diagram is calculated;

Step 6.3.14: combining the center coordinates and angle information of the template source diagram, translating and rotating the diagram to be detected, namely extracting a region of interest (ROI) of the part to be detected from the diagram to be detected; then creating a blank diagram with the same size as the diagram to be detected, translating the part to be detected to the center of the blank diagram, and rotating the part to be detected to the same angle as the template source diagram; in the embodiment, the ROI is a rectangle, the side length of the rectangle is the diameter of the smallest circumscribed circle of the template source diagram, and the center of the rectangle is the center of the smallest circumscribed circle of the part to be detected;

step 6.3.15: judging whether the vector angle from the centroid of the outer contour of the part to be detected to the minimum circumscribed rectangle center of the part to be detected is smaller than a set value or not compared with the vector angle from the centroid of the outer contour of the template source diagram to the minimum circumscribed rectangle center of the template source diagram, wherein the set value in the embodiment takes 7.5 degrees.

Step 6.3.16: if the vector angle difference in the step 6.3.15 is smaller than the set value, the object matching is successful, and the process is ended;

step 6.3.17: if the vector angle difference in the step 6.3.15 is greater than or equal to the set value, the step 6.3.18 is entered;

step 6.3.18: judging whether an inner contour exists according to the minimum circumscribed rectangular area of the maximum inner contour of the template source diagram; if not, the object matching is successful, the rotation angle of the part to be detected relative to the template source diagram is calculated, the center coordinate and the angle information of the template source diagram are combined, the object is translated and rotated, and the process is ended; if yes, judging whether the template source diagram has only one effective maximum inner contour;

Step 6.3.19: if the template source diagram has only one effective maximum inner contour, effective inner contour matching is carried out; the effective inner contour matching comprises the steps of judging whether the minimum circumscribed rectangular area of the maximum inner contour of the part to be detected is matched with the minimum circumscribed rectangular area of the maximum inner contour of the template source diagram, further judging whether the aspect ratio of the minimum circumscribed rectangular area of the maximum inner contour is matched in sequence, judging whether the center distances of the minimum circumscribed rectangular areas of the outer contour and the maximum inner contour are matched, solving the rotation angle of the part to be detected relative to the template source diagram, combining the center coordinates and angle information of the template source diagram, rotating and translating an object, and judging whether the vector angles of the centers of the minimum circumscribed rectangular areas of the outer contour and the maximum inner contour are matched or not to detect whether the matching is successful;

step 6.3.20: if the template source diagram does not meet the condition that only one effective maximum inner contour exists, judging whether the template source diagram has a plurality of maximum inner contours or has both a maximum inner contour and a minimum outer contour;

step 6.3.21: if the template source diagram has a plurality of maximum inner contours, traversing all inner contours in the part to be detected, carrying out effective inner contour matching on each inner contour, judging whether at least one inner contour matching is successful, if so, successfully matching the object, and ending the flow; if not, the object is not successfully matched, and the process is ended;

Step 6.3.22: if the template source diagram has a maximum inner contour and a minimum outer contour; firstly, carrying out effective inner contour matching on the maximum inner contour; if the maximum inner outline is matched, the object is successfully matched, and the process is ended;

if the maximum inner contour is not matched, then carrying out effective inner contour matching on the minimum inner contour detection object; if the minimum inner outline is matched, the object is successfully matched, and the process is ended; if the minimum inner contour is not matched, the object is not successfully matched, and the process is ended.

As shown in fig. 18, the measurement procedure of the circle measurement type of the graph to be measured in the step 6.2.5 includes the following steps:

step 6.4.2: extracting the ROI of the circle measurement type in the graph to be measured according to the characteristic information of the circle measurement type manufactured by the template source graph;

step 6.4.3: carrying out Gaussian filtering treatment on the ROI gray level diagram in the diagram to be detected;

step 6.4.4: carrying out Hough circle finding processing on the filtered image to obtain a plurality of circles in the image to be detected;

step 6.4.5: comparing the circle center of the circle obtained in the to-be-detected diagram with the template source diagram, and judging whether at least one circle exists on the to-be-detected diagram and the circle center deviation of the selected circle on the template source diagram is within 2 mm;

step 6.4.6: if the circle satisfying the step 6.4.5 does not exist on the graph to be tested, changing the Huff circle finding parameter threshold value, and jumping to the step 6.4.4;

Step 6.4.7: if the circles meeting the requirement of the step 6.4.5 exist on the to-be-detected diagram, screening out the circles on the template source diagram and the circles on the to-be-detected diagram, and enabling the absolute difference of the radii of the two Hough fitting circles to be the smallest;

step 6.4.8: comparing the radii of the circles screened in the step 6.4.7, and judging whether the absolute difference value of the radii is within 2mm or not;

step 6.4.9: if the absolute difference value of the radius is not within 2mm, changing the threshold value of the Hough circle finding parameter, and jumping to the step 6.4.4;

step 6.4.9: if the absolute difference value of the radius is within 2mm, the fact that a proper Hough fitting circle is found is indicated;

step 6.4.20: gradient is calculated on the Gaussian filtered image;

step 6.4.21: calculating sub-pixel edge points; the edge points are defined as the maximum value of the difference values of adjacent gradient modulus values, in the embodiment, quadratic equation fitting is performed by calculating quadratic function interpolation of gradient modulus values at three adjacent points in the gradient direction, namely, three coordinate points (A point, B point and C point), and the compensation value eta is obtained:

the edge sub-pixel points are the middle points in the adjacent three points and added with compensation values, wherein the I (G) (A) I represents the gradient modulus value of the A point, the I (G) (B) I represents the gradient modulus value of the B point, and the I (G) (C) I represents the gradient modulus value of the C point;

Step 6.4.22: connecting the sub-pixel edge points into a contour;

step 6.4.23: screening contour points by double threshold values;

step 6.4.24: screening out proper contour points according to the distance from the contour points to the found proper Hough fitting circle to form a new contour point set;

step 6.4.25: fitting a circle to the new contour point set by using a least square method to obtain a circle center and a radius;

step 6.4.26: the present flow is ended.

In the step 6.4.3, the gaussian filtering process represents sliding convolution with a discretized window. The gaussian filtering process first requires the calculation of a gaussian weight matrix, assuming in the example that the coordinates of the center point are (0, 0), then the coordinates of the 8 points nearest to it are as follows: assuming standard deviation σ=1.5, the weight matrix for a filter radius of 1 is as follows: the sum of the weights of these 9 points is equal to 0.4787147. If only the weighted average of these 9 points is calculated, it is also necessary to let the sum of their weights equal to 1, so the upper 9 values are divided by 0.4787147, respectively, to obtain the final weight matrix: with the weight matrix, a center point and n points around can be calculated, each point being multiplied by its own weight value and added, which is the gaussian filtered value of the center point. This process is repeated for all points, resulting in a Gaussian filtered image.

In the step 6.4.20, the gradient of the image after the gaussian filtering is calculated and the gradient modulus are calculated and approximated by using the center difference, specifically, the gradient of any pixel (X, Y) in the image is divided into an X component and a Y component, and the X component is the gray value of the pixel (x+1, Y) minus the gray value of the pixel (X-1, Y); the Y component is the gray value of the pixel point (x, y+1) minus the gray value of the pixel point (x, Y-1); the gradient modulus is the root number after the sum of the squares of the X component and the sum of the squares of the Y component are added.

In the step 6.4.22, the sub-pixel edge points are connected into a contour representation, and contour point sets belonging to the same edge are grouped together to form a link; wherein each contour point corresponds to a pixel point, firstly, the pixels classified into the same link should have an approximate gradient direction, the approximate gradient direction indicates that the included angle between adjacent pixels on the same link should be smaller than 90 degrees, taking pixels a and B as examples, and the mathematical expression is as follows: g (A) & gt 0, wherein g (A) represents the gradient of the point A and g (B) represents the gradient of the point B; in addition, the image profile can separate the bright and dark regions, so a continuous link would need to divide the dark region to the same side of the curve, a simple way is to verify if the vector from edge point A to point B is approximately orthogonal to one of the two possible gradient directions (X-axis direction or Y-axis direction) of point A.

In the step 6.4.23, the profile points are formed by screening the two set thresholds, namely, the high threshold is 4.3 for each point in the link, which is determined a priori whether the gradient modulus is greater than the set high threshold; if the gradient modulus value is greater than the set high threshold value, then verifying whether the gradient modulus value of the previous point linked with the point is greater than the set low threshold value, wherein the low threshold value in the embodiment is 0.8; if the contour point is larger than the set low threshold value, reserving the contour point; if the contour point mark is smaller than or equal to the set low threshold value, eliminating the contour point mark; and similarly, verifying the condition of the next contour point linked with the contour point; and finally, deleting the outline points with the rejection marks after traversing all the points, and reforming the links.

It should be noted that there may be a plurality of circle measurement types of feature information on the template artwork, and the above measurement flow is performed separately for each circle measurement type of feature information; the measurement procedure is also performed separately for the characteristic information of the arc, line and angle measurement types.

It should be noted that the steps of the arc measurement type measurement and the circle measurement type measurement of the map to be measured are identical.

As shown in fig. 19, the measurement procedure of the line measurement type of the graph to be measured in the step 6.2.5 includes the following steps:

step 6.5.1: extracting a line measurement type ROI in the to-be-detected graph according to the line measurement type characteristic information obtained by the template source graph;

step 6.5.2: carrying out Canny edge detection processing on the ROI gray level image in the image to be detected;

step 6.5.3: carrying out Hough straight line finding processing on the image subjected to Canny processing, and obtaining a plurality of straight line segments in the image to be detected;

step 6.5.4: comparing the straight line segment in the to-be-detected diagram obtained in the step 6.5.3 with the straight line segment of the template source diagram in an oblique angle manner, and judging whether the oblique angle deviation of at least one straight line segment in the to-be-detected diagram and at least one straight line segment in the template source diagram is smaller than a set value or not;

step 6.5.5: if no straight line segment smaller than the set oblique angle offset value exists in the graph to be tested, jumping to the step 6.5.3;

step 6.5.6: if the straight line segments smaller than the set oblique angle offset value exist in the to-be-measured graph, obtaining a plurality of Hough fitting straight line segments meeting the conditions in the step 6.5.4 in the oblique angle to-be-measured graph;

step 6.5.7: screening out the straight line segment with the longest length from the straight line segments obtained in the step 6.5.6;

step 6.5.8: performing Gaussian filtering processing on the ROI gray level map corresponding to the straight line segment obtained in the step 6.5.7;

Step 6.5.9: gradient is calculated on the Gaussian filtered image;

step 6.5.10: calculating sub-pixel edge points;

step 6.5.11: the edge points of the sub-pixels are connected into a contour;

step 6.5.12: screening sub-pixel edge points by using double threshold values, and reconstructing a contour point set;

step 6.5.13: according to the distance from the contour point to the screened straight line segment, screening out proper contour point to form new contour point set

Step 6.5.14: fitting a straight line to the new contour point set by using a least square method to obtain an oblique angle and coordinates of two end points;

step 6.5.15: the present flow is ended.

As shown in fig. 20, the measurement procedure of the angle measurement type of the graph to be measured in the step 6.2.5 includes the following steps:

step 6.6.1: extracting an angle measurement type ROI in the to-be-measured graph according to the circle measurement type characteristic information obtained by the template source graph;

step 6.6.2: carrying out Canny edge detection processing on the ROI gray level image in the image to be detected;

step 6.6.3: carrying out Hough straight line finding processing on the image subjected to Canny processing, and obtaining a plurality of straight line segments in the image to be detected;

step 6.6.4: according to the oblique angles of the two straight line segments forming the included angle in the template source diagram, the oblique angles comprise a first straight line segment oblique angle and a second straight line segment oblique angle, two groups of straight line segments are selected from the plurality of straight line segments obtained in the step 6.6.3, namely the first group of straight line segments and the second group of straight line segments, wherein the absolute value of the difference between the oblique angle of the straight line segment in the first group of straight line segments and the oblique angle of the first straight line segment in the mask characteristic information is smaller than a set value, 7.5 degrees is adopted in the embodiment, and the absolute value of the difference between the oblique angle of the straight line segment in the second group of straight line segments and the oblique angle of the second straight line segment in the mask characteristic information is smaller than the set value, and 7.5 degrees is adopted in the embodiment; if each group of straight line segments selected by the screening method at least comprises one straight line segment, the screening is successful, otherwise, the screening is failed;

Step 6.6.5: if the screening in the step 6.6.4 fails, changing the straight line parameter of the Hough finding, and jumping to the step 6.6.3 for execution;

step 6.6.6: if the screening in step 6.6.4 is successful, respectively calculating the distance from the end point of any one of the two straight-line segments forming the included angle in the template source diagram to the other straight-line segment, wherein the end point is the end far away from the included angle, so as to obtain two distance values, and taking a smaller distance value D'; traversing the first group of straight line segments obtained in the step 6.6.4, screening out straight line segments with the distance from the straight line segments to the set point smaller than the set point, and forming a new first group of straight line segments, wherein the set point is an end point of the first straight line segment far away from one end of an included angle in the template source diagram, in the embodiment, if D '/5 is greater than 70 pixels, the set point is 70 pixels, otherwise, the set point is D'/5; similarly, traversing the second set of straight line segments obtained in the step 6.6.4, screening out the straight line segments with the set point to straight line segment distance smaller than the set point, and forming a new second set of straight line segments, wherein the set point is an end point of the second straight line segment far away from one end of the included angle in the template source diagram, and the set point has the same value as the first set of straight line segments; if the new first group of straight line segments and the new second group of straight line segments meet the requirement of at least one straight line segment, the screening is successful, otherwise, the screening fails;

Step 6.6.7: if the screening in the step 6.6.6 fails, changing the straight line parameter of Hough finding, and jumping to the step 6.6.3;

step 6.6.8: if the screening in the step 6.6.6 is successful, traversing a random group of straight line segments in the new first group of straight line segments and the new second group of straight line segments in the step 6.6.6, and screening out the straight line segment with the longest length in the group of straight line segments;

step 6.6.9: obtaining the included angle between the straight line segment obtained in the step 6.6.8 and each straight line segment in the other group of straight line segments;

step 6.6.10: comparing the included angle obtained in the step 6.6.9 with the included angle selected in the template source diagram, screening out straight line segments meeting the conditions in the other group of straight line segments according to the fact that the difference value between the included angle and the degrees of the angles in the template source diagram is smaller than a set value, and judging whether the screening is successful or not; if at least one straight line segment is screened out from the other group of straight line segments, the screening is successful;

step 6.6.11: if the screening in the step 6.6.10 fails, changing the straight line parameter of the Hough finding, and jumping to the step 6.6.3 for execution;

step 6.6.12: if the screening in the step 6.6.10 is successful, screening the straight line segment with the longest length in the other group of straight line segments;

step 6.6.13: obtaining the longest straight line segment in each group of straight line segments, calculating the included angle between the two straight line segments, comparing the included angle with the included angle of the corresponding straight line segment in the template source diagram, and judging whether the deviation is smaller than a set value; in this embodiment, the set value is 10 degrees;

Step 6.6.14: if the deviation is greater than or equal to the set value, indicating that the angle measurement type fails to measure, jumping to the step 6.6.23 to execute;

step 6.6.15: if the deviation is smaller than the set value, performing Gaussian filtering on the ROI gray-scale image;

step 6.6.16: gradient is calculated on the Gaussian filtered image;

step 6.6.17: calculating sub-pixel edge points;

step 6.6.18: the edge points of the sub-pixels are connected into a contour;

step 6.6.19: screening sub-pixel edge points by using double threshold values, and reconstructing a contour point set;

step 6.6.20: screening two contour point sets according to the distance from the contour point to the two straight line segments;

step 6.6.21: fitting straight lines to the two contour point sets by using a least square method to obtain two end point coordinates and an oblique angle;

step 6.6.22: obtaining an included angle and vertex coordinates of the two straight line segments;

step 6.6.23: the present flow is ended.

The above description is only one specific example of the present invention and does not constitute any limitation on the present invention. It will be apparent to those skilled in the art that various modifications and changes in form and details may be made without departing from the principles and construction of the invention, but these modifications and changes based on the inventive concept are still within the scope of the appended claims.

Claims

1. The size measurement scoring device is characterized by comprising a fixing frame, an operation table, a detection table, a light source and a camera; the detection table, the light source and the camera are arranged on the fixing frame; the middle part of the detection table is provided with a through hole, the through hole is provided with a carrying plate, and the carrying plate is made of transparent materials; the light source is arranged below the detection table and corresponds to the object carrying plate; the camera is arranged on the camera fixing plate right above the object carrying plate; the operation desk is electrically connected with the light source and the camera; a standard flat crystal is arranged between the camera and the detection table; a telecentric coaxial lens is arranged at the lens of the camera, a He-Ne laser is arranged on the side surface of the telecentric coaxial lens, and a standard flat crystal is arranged on the sliding rail adjusting device; the sliding rail adjusting device comprises a vertical plate and a horizontal plate; the vertical plate passes through the detection table; two mutually parallel vertical tracks are arranged on one surface of the vertical plate, which is close to the detection table, and the horizontal plate is arranged on the vertical tracks of the vertical plate; a horizontal track is arranged on one surface of the horizontal plate, which is close to the detection table, and a standard flat crystal is arranged on the horizontal track; the top of riser is provided with the camera backup pad, and the bottom of riser is provided with the light source backup pad.

2. A sizing scoring device according to claim 1, wherein a fine adjustment knob is provided between the carrier plate and the inspection station.

3. A sizing scoring device according to claim 2, wherein the test table is provided with a support, the support being located on the carrier plate; the middle part of the bracket is provided with a groove.

4. A sizing scoring device according to claim 3, wherein a vertical high-precision adjustment slide is provided between the inspection station and the mount; the vertical high-precision adjusting sliding rail is positioned at four corners of the detection table.

5. The sizing scoring device of claim 4, wherein a laser ranging device is disposed between the camera mounting plate and the inspection station; the laser ranging device comprises a laser ranging sensor transmitting head and a laser ranging receiver; the laser range finding receiver is arranged on four corners of the detection table, the laser range finding sensor transmitting head is arranged on four corners of the camera fixing plate, and the laser sensor transmitting head is arranged over against the laser range finding receiver.

6. The size measurement scoring device according to claim 5, wherein the fixing frame is in a shape of a straight quadrangular prism, the inside of the fixing frame is hollow, the fixing frame is arranged above the optical shock insulation table, and the four corners of the bottom of the optical shock insulation table are provided with fuma wheels; the detection table is also provided with a transparent checkerboard and an identity card reader; the operation panel sets up in the top of camera fixed plate, and the operation panel includes display module.

7. A method of adjusting a sizing scoring device, comprising the steps of:

8. The method for adjusting and measuring the size measurement scoring device according to claim 7, wherein in the third step, the lower surface of the standard flat crystal is adjusted to be parallel to the upper surface of the object carrying plate, first, the light rays emitted by the He-Ne laser are required to obtain interference fringes through the camera, after the interference fringes are processed, information difference values of adjacent interference fringes are obtained, and four fine adjustment knobs are continuously adjusted according to the difference values until the information difference values of the adjacent interference fringes are reduced to a set value, so that the interference fringes are approximately parallel and equidistant.

9. A method of sizing scoring comprising the steps of:

The identification card in the step 3 depends on an identification card reader.