Image measuring instrument, feature point extraction method and tool

Abstract

The invention relates to an image measuring instrument and a feature point extraction method and tool, and the image measuring instrument comprises a carrying platform, an imaging module which is used for obtaining an image of a to-be-measured workpiece, a display module which is used for presenting the image, a feature extraction module which is used for extracting features from the image, and a measuring module which is used for obtaining the physical quantity of the to-be-measured workpiece based on the features, the feature extraction module comprises a feature point extraction unit, the feature point extraction unit is used for extracting feature points, and the feature point extraction comprises the following steps: drawing a frame selection area center line on an image of a to-be-detected workpiece, and determining a corresponding frame selection area and a center scanning line according to the frame selection area center line; in the frame selection area, identifying at least one edge point through a scanning line which is formed in the frame selection area and is parallel to the central scanning line; edge fitting is carried out based on the at least one edge point to obtain the edge fitting line, and the target feature point located on the central scanning line is determined and extracted based on the edge fitting line, so that feature points are extracted for different test scenes.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of measurement, in particular to an image measurement instrument, a feature point extraction method and a tool. BACKGROUND

[0002] Image measurement instruments such as a video measuring machine, a flash measuring machine, a white light interferometer or a confocal microscope are used to obtain two-dimensional information or three-dimensional information of a workpiece and present corresponding two-dimensional images or three-dimensional images, and can realize precision measurement of surface size, contour, angle and position, geometric and position tolerances of various complex parts. Generally, an image measurement instrument has multiple feature extraction tools for extracting line features, point features or circle features, etc. The feature extraction tools can be used to create a feature measurement area for identifying features, and identify features of a workpiece to be measured in the feature measurement area during measurement.

[0003] Since a point feature can only select one point, it is impossible to obtain a point feature by fitting. If the feature measurement area of the workpiece to be measured has conditions such as burrs, pits or blurring, the existing feature point extraction tool will not be able to extract a suitable feature point. SUMMARY

[0004] Therefore, it is necessary to provide an image measurement instrument, a feature point extraction method and a tool.

[0005] An image measurement instrument comprises:

[0006] a stage for placing a workpiece to be measured;

[0007] an imaging module for obtaining an image of the workpiece to be measured;

[0008] a display module for presenting the image;

[0009] a feature extraction module for extracting a feature in the image;

[0010] a measurement module for obtaining a physical quantity of the workpiece to be measured based on the feature;

[0011] The feature extraction module comprises a feature point extraction unit, which is configured to:

[0012] draw a frame selection area center line on the image of the workpiece to be measured, and determine a corresponding frame selection area and a center scanning line according to the frame selection area center line;

[0013] identify at least one edge point in the frame selection area through a scanning line formed in the frame selection area and parallel to the center scanning line;

[0014] perform edge fitting based on the at least one edge point to obtain an edge fitting line,

[0015] Based on the edge fitting line, the target feature points located on the center scan line are determined and extracted.

[0016] A feature point extraction method, characterized by comprising:

[0017] Draw the center line of the selection area on the image of the workpiece to be tested, and determine the corresponding selection area and center scan line based on the center line of the selection area;

[0018] Within the selected area, at least one edge point is identified by a scan line formed within the selected area that is parallel to the center scan line;

[0019] Edge fitting is performed based on at least one edge point to obtain an edge fitting line.

[0020] Based on the edge fitting line of the at least one edge point, the target feature point located on the center scan line is determined and extracted.

[0021] In another embodiment, a plurality of scan lines are formed within the selected area, and the identification of at least one edge point by scanning lines formed within the selected area parallel to the central scan line includes:

[0022] The edge points distributed within the selected area and located on each of the scan lines are identified by corresponding scan lines.

[0023] The at least one edge point is identified based on the multiple scan lines.

[0024] In another embodiment, a plurality of scan lines are formed within the selected area, and the identification of at least one edge point by scanning lines formed within the selected area parallel to the central scan line includes:

[0025] Determine the target recognition area for each of the scan lines;

[0026] The target recognition area distributed within the selected area and the edge point located on each of the scan lines are identified by the corresponding scan lines.

[0027] The at least one edge point is identified based on the multiple scan lines.

[0028] In another embodiment, edge points on the scan line are identified based on the grayscale gradient on the scan line.

[0029] In another embodiment, after identifying at least one edge point by scanning lines formed within the selected area that are parallel to the center scan line, the method further includes:

[0030] Based on the edge intensity of the central scan line, noise reduction is performed on the edge points of other scan lines besides the central scan line.

[0031] In another embodiment, based on the edge fitting line, determining and extracting target feature points located on the center scan line includes:

[0032] Among the edge points identified by the central scan line, edge points that meet the preset conditions are identified as target feature points and extracted.

[0033] Among them, the edge points that satisfy the preset conditions include any one of the edge points closest to the fitting line and the edge points located at the intersection of the edge fitting line and the center scan line.

[0034] In another embodiment, determining and extracting target feature points located on the center scan line based on the edge fitting line further includes:

[0035] The edge points whose deviation from the edge fitting line is greater than a threshold are filtered out to obtain an updated at least one edge point, where the threshold is the maximum allowed distance between the edge point and the fitting line, and the edge fitting line is determined based on the at least one edge point.

[0036] Based on at least one updated edge point and the edge fitting line, the target feature point located on the center scan line is determined and extracted.

[0037] In another embodiment, determining and extracting target feature points based on the at least one edge point includes:

[0038] Among the edge points identified by the central scan line, edge points that meet the preset conditions are identified as target feature points and extracted.

[0039] Among them, the edge points that meet the preset conditions include either the foremost edge point along the direction of the central scan line or the edge point with the largest gray-scale gradient.

[0040] A feature point extraction tool that performs the method described in any one of the above embodiments.

[0041] The aforementioned image measurement instruments, feature point extraction methods, and tools enable the extraction of feature points for different test scenarios. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the embodiments of this application or the conventional technology, the drawings used in the description of the embodiments or the conventional technology will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 This is a schematic diagram of the modules of an image measuring instrument according to one embodiment;

[0044] Figure 2 This is a schematic diagram illustrating the functional steps of the extraction unit in one embodiment;

[0045] Figure 3 This is a schematic diagram of the interface for a feature point extraction method according to another embodiment;

[0046] Figure 4 This is a schematic diagram illustrating the effect of edge point extraction in another embodiment;

[0047] Figure 5 A schematic diagram of the interface for edge point extraction in another embodiment;

[0048] Figure 6 This is a schematic diagram illustrating the effect of a feature point extraction method according to another embodiment;

[0049] Figure 7 This is a schematic diagram illustrating the effect of a feature point extraction method according to another embodiment;

[0050] Figure 8 This is a schematic diagram of the structure of a feature point extraction tool according to one embodiment;

[0051] Figure 9 This is an internal structural diagram of a computer device according to one embodiment.

[0052] Explanation of reference numerals in the attached figures:

[0053] 101. Stage; 102. Imaging module; 103. Display module; 104. Feature extraction module; 1041. Feature point extraction unit; 105. Measurement module; 801. Drawing module; 802. Edge point recognition module; 803. Edge fitting line extraction module; 804. Feature point extraction module. Detailed Implementation

[0054] To facilitate understanding of this application, a more complete description will be provided below with reference to the accompanying drawings, which illustrate embodiments of the present application. However, the present application can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that the disclosure of this application will be thorough and complete.

[0055] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.

[0056] It is understandable that "at least one" refers to one or more, and "multiple" refers to two or more. "At least a part of an element" refers to part or all of an element.

[0057] When used herein, the singular forms of “a,” “an,” and “the” may also include the plural forms unless the context clearly indicates otherwise. It should also be understood that the terms “comprising / including” or “having,” etc., specify the presence of the stated features, wholes, steps, operations, components, parts, or combinations thereof, but do not preclude the possibility of the presence or addition of one or more other features, wholes, steps, operations, components, parts, or combinations thereof. Meanwhile, the term “and / or” as used in this specification includes any and all combinations of the associated listed items.

[0058] This application proposes an image measuring instrument capable of acquiring and measuring image information of a workpiece. For example, the image measuring instrument can be a video measuring instrument, a flash measuring instrument, a confocal microscope, a white light interferometer, or other measuring instruments capable of acquiring two-dimensional or three-dimensional image information of a workpiece.

[0059] like Figure 1 As shown, the image measuring instrument includes:

[0060] Stage 101 is used to place the workpiece to be tested.

[0061] The imaging module 102 is used to acquire images of the workpiece under test. The imaging module 102 may consist of an optical lens, an image sensor, and an information transmission unit, and can capture images of the workpiece under test and output these images.

[0062] Display module 103 is used to present an image of the workpiece to be measured. Display module 103 can be a high-definition display panel fixed to the image measuring instrument, or a portable display screen that wirelessly communicates with the image measuring instrument. It is used to receive the image of the workpiece to be measured from the imaging module and present it to the user. Optionally, the display module also includes an interactive unit to facilitate user interaction with the image of the workpiece to be measured.

[0063] The feature extraction module 104 extracts features from the image of the workpiece to be tested. These features include, but are not limited to, point features, line features, and circle features.

[0064] The measurement module 105 acquires the physical quantities of the workpiece under test based on features. These physical quantities can be surface roughness, distance, radius, and other topographic, dimensional, and positional information.

[0065] The feature extraction module 104 includes a feature point extraction unit 1041, which is used for:

[0066] A center line of a bounding box is drawn on the image of the workpiece to be tested, and the corresponding bounding box and center scan line are determined based on the center line of the bounding box. Within the bounding box, at least one edge point is identified by a scan line formed within the bounding box that is parallel to the center scan line. Edge fitting is performed based on the at least one edge point to obtain an edge fitting line. Based on the edge fitting line, the target feature point located on the center scan line is determined and extracted.

[0067] Depending on the field, image measuring instruments may include, but are not limited to:

[0068] Image measuring instruments are used to inspect the two-dimensional or three-dimensional dimensions and geometric tolerances of mechanical parts, molds and other workpieces.

[0069] Semiconductor / electronic assembly inspection equipment is used for the positioning and inspection of solder joints, pins, etc. on wafers and chips.

[0070] Microscope measurement systems are used to observe and measure feature points of microstructures.

[0071] In some specific embodiments, during the measurement process, a measurement program can be created using a feature extraction module and a measurement module. This program can be executed within the workpiece image, identifying features and calculating geometric quantities such as surface dimensions, contours, angles and positions, and form and position tolerances. Alternatively, before creating the measurement program, a workpiece image can be obtained by measuring a physical workpiece or by importing a model. After obtaining a similar workpiece image through subsequent measurements, the measurement program can be executed within that image, thereby quickly acquiring the geometric quantities set in the program.

[0072] like Figure 2 As shown, this application also proposes a feature point extraction method, including steps 201, 202, 203 and 204.

[0073] Step 201: Draw the center line of the selection area on the image of the workpiece to be tested, and determine the corresponding selection area and center scan line based on the center line of the selection area.

[0074] For example, the selection area includes a rectangular selection area, such as... Figure 3As shown, the dark area represents the workpiece, and the light area represents the background. Taking a rectangular selection area as an example, the user can first draw the center line of the selection area. This can be done by selecting two points in the image to define a straight line, which is then used as the center line of the selection area. Simultaneously, a center scan line is displayed, coinciding with the perpendicular bisector of the selection area's center line, and has an adjustable scanning direction. At the same time, a rectangular selection area is displayed, with one center line coinciding with the overall selection area's center line, and the other coinciding with the center scan line. To improve the effectiveness of the feature point extraction method, such as... Figure 3 As shown, the center line of the selection area can be drawn along the edge of the workpiece. In addition, users can freely move and rotate the selection area or adjust the length or width of the selection area. They can also set the distance between the selection area and any straight line to limit the position of the selection area.

[0075] For example, the selection area also includes an arc-shaped selection area. When drawing the center line of the selection area, the user can choose the selection area type as an arc-shaped selection area. If no selection area type is selected, the default is a rectangular selection area. The arc is determined by selecting at least three points and used as the center line of the selection area. Based on the same concept, the selection area can also include a polygonal selection area, a circular selection area, or a selection area with a user-defined shape; this embodiment does not limit this.

[0076] Step 202: Within the selected area, at least one edge point is identified by scan lines formed within the selected area that are parallel to the center scan line.

[0077] Step 203: Perform edge fitting based on at least one edge point to obtain the edge fitting line.

[0078] Based on at least one edge point, a straight line or curve is fitted to obtain an edge fitting line that best represents the spatial distribution trend of these points. The fitting method can be linear fitting, nonlinear fitting, piecewise fitting, regularized fitting, etc., and this embodiment is not limited to any particular method.

[0079] Step 204: Based on the edge fitting line, determine and extract the target feature points located on the center scan line. After determining the edge fitting line, the system uses preset rules or algorithms to determine and extract feature points as the result of this feature point extraction.

[0080] Generally, the feature points to be extracted are located near a certain edge. The image measurement instrument in this embodiment obtains a bounding box and a central scan line by drawing the center line of the bounding box, and identifies at least one edge point by a scan line formed within the bounding box parallel to the central scan line. Based on preset rules or algorithms, an edge fitting line is obtained, and the target feature point located on the central scan line is determined and extracted. This allows for accurate extraction of appropriate feature points for different test scenarios.

[0081] In some other embodiments, the acquired image may be processed before step 101, including denoising, smoothing, contrast enhancement, and sharpening, in order to initially remove noise from the image.

[0082] In another embodiment, a plurality of scan lines are formed within the selected area, and the step of identifying at least one edge point by means of the scan lines formed within the selected area includes:

[0083] Edge points distributed within the selected area and located on each of the scan lines are identified accordingly; at least one edge point is identified based on the multiple scan lines. The effect of identifying at least one edge point is... Figure 4 For example, for the sake of simplicity, Figure 4 The area near the central scan line was magnified, and some scan lines and edge points within that area were marked. Understandably, edge points outside the magnified area were also obtained using the same method.

[0084] Specifically, after forming the selection area, multiple parallel scan lines perpendicular to the center line of the selection area can be created within the selection area, and the edge points on each scan line can be identified. The number of scan lines can be generated by a preset algorithm, or the number and spacing of the scan lines can be adjusted by the user.

[0085] After generating multiple scan lines, the system locates edge points on each scan line according to step 102. Since the workpiece edge is continuous within the selection area, typically one scan line will identify one edge point at its intersection with the workpiece edge. However, in some cases, multiple edges may exist within the selection area, or the edge surface may have burrs. Therefore, each scan line will usually identify at least one edge point at its intersection with the workpiece edge. Finally, the system aggregates the edge points identified on all scan lines, forming an edge point set containing multiple spatially distributed points.

[0086] This embodiment can obtain at least one edge point by forming multiple parallel scan lines in the selected area. This allows the edge point to be used to assist in the extraction of target feature points, such as reducing the impact of abnormal points like burrs and pits on the accuracy of feature point extraction.

[0087] In another embodiment, a plurality of scan lines are formed within the selected area, and at least one edge point is identified by the scan lines formed within the selected area, including:

[0088] Determine the target recognition area for each scan line.

[0089] The target recognition area distributed within the selected area is identified by each scan line, and the edge points located on each scan line are identified; at least one edge point is identified based on the multiple scan lines.

[0090] In this embodiment, the user can select the target recognition area, i.e., the location of the edge points, from the drop-down menu. The location of the edge points includes, but is not limited to, near the top, near the center line, and near the bottom. Specifically, "near the top" refers to identifying edge points within a preset segment close to the beginning of each scan line; "near the center line" refers to preferentially identifying edge points within a preset segment surrounding the midpoint of each scan line (or within a preset segment close to the center line of the selected area); and "near the bottom" refers to preferentially identifying edge points within a preset segment close to the end of each scan line.

[0091] This embodiment introduces a target recognition region, which ensures that the system identifies edge points on each scan line according to the target recognition region selected by the user. This avoids measurement deviations caused by different edge features mixed in the sampling points, and improves the stability and accuracy of the feature point extraction method.

[0092] In other embodiments, the selection of the target recognition region further includes selecting the point with the highest edge intensity. This means identifying all candidate points within the range of each scan line and selecting the point with the highest grayscale gradient value as the edge point of that scan line. Since the point with the highest edge intensity in each scan line may be located on different edges if there are multiple different edges in the selected area, this option can be used when the edges are relatively clear or there is only one edge.

[0093] In another embodiment, step 102 includes: identifying edge points on the scan line based on the grayscale gradient on the scan line.

[0094] This embodiment essentially utilizes the unique gray-level abrupt changes in edge regions of an image to accurately locate edge feature points on the scan line by quantifying the intensity and direction of gray-level changes. The steps can be divided into:

[0095] Grayscale data extraction: Along the scan line path, extract the grayscale value of each pixel and obtain the grayscale value sequence g(x).

[0096] Gradient value calculation: For the nth pixel on the scan line, its gradient magnitude can be expressed as |g(n+1)–g(n)|, which is the absolute value of the grayscale difference between adjacent pixels. The larger this value is, the more drastic the grayscale change at that location, and the more likely it is to be close to an edge region. When this value exceeds a certain preset gradient threshold, the x-position is determined as a candidate edge point. Alternatively, the location of the edge point can be determined based on the derivative of the grayscale value.

[0097] In other embodiments, discrete difference operators such as Sobel are used for convolution calculations to enhance noise immunity.

[0098] The above embodiments employ a method for identifying edge points based on grayscale gradients on the scan line, which can effectively capture low-contrast or blurred edges and improve the detection rate of feature points. Furthermore, due to the simplicity and efficiency of this algorithm, it can effectively meet the real-time requirements of industrial image measurement.

[0099] In another embodiment, after identifying at least one edge point by scan lines formed within the selected area, the method further includes:

[0100] Based on the edge intensity of the center scan line within the selected area, noise reduction is performed on the edge points of other scan lines besides the center scan line.

[0101] In some embodiments, such as Figure 5 As shown, an edge intensity map can be displayed on the image. This map includes an edge intensity curve, a first edge intensity threshold line, and a second edge intensity threshold line. The edge intensity curve describes the edge intensity at various locations along the centerline scan line. The first and second edge intensity threshold lines define the range of edge intensity for each edge point. Only edge points within this range will be displayed in the image. The first edge intensity threshold corresponding to the first edge intensity threshold line is greater than the second edge intensity threshold corresponding to the second edge intensity threshold line. Since multiple different edges may appear in the image, multiple edge points not on the same edge may be identified. If the edge line corresponding to the feature point the user wants to select has a weak edge intensity, interference can be eliminated by setting the first edge intensity threshold. Conversely, if the edge line corresponding to the feature point the user wants to select has a strong edge intensity, interference can be eliminated by setting the second edge intensity threshold. Because the feature point the user wants to select is located on the scan line, the edge intensity near the desired feature point can be determined based on the edge intensity curve. Therefore, the upper and lower limits of edge intensity can be adjusted to a suitable range and displayed intuitively through the edge intensity map in the image.

[0102] This embodiment introduces a visual intensity curve and adjustable first and second edge intensity threshold lines, allowing users to manually adjust the intensity according to the actual image conditions. This effectively filters out strong noise points that are not edges and false edge points in blurred areas, preserving the edge points of the real target to the greatest extent possible.

[0103] In another embodiment, based on the edge fitting line, determining and extracting target feature points located on the center scan line includes:

[0104] Among the edge points identified by the central scan line, edge points that meet the preset conditions are identified as target feature points and extracted.

[0105] Among them, such as Figure 6 and Figure 7 As shown, the edge points that satisfy the preset conditions include any one of the edge points closest to the fitting line and the edge points located at the intersection of the edge fitting line and the center scan line.

[0106] This embodiment determines feature points based on a fitted line, such as edge points closest to the fitted line or edge points located at the intersection of the edge fitted line and the center scan line. By fitting edge lines, the dependence on the randomness of individual edge point positions can be eliminated. Even with local noise, the fitted line remains stable, thus ensuring that the final feature point coordinates are robust, repeatable, and geometrically deterministic.

[0107] In another embodiment, determining and extracting target feature points based on at least one edge point further includes:

[0108] Edge points whose deviation from the fitted edge line is greater than a threshold are filtered out to obtain at least one updated edge point, where the threshold is the maximum allowable distance between the edge point and the fitted line. In some cases, such as when workpieces have defects during manufacturing that result in spikes, some edge points may deviate significantly from the fitted line. In such cases, filtering out the significantly deviated edge points can lead to a more accurate fitted line.

[0109] Based on at least one updated edge point, the target feature points are determined and extracted.

[0110] This embodiment filters out geometrically abnormal points based on the geometric deviation of each edge point from the edge fitting line. Combined with a noise reduction step based on edge strength, this effectively eliminates interference points from non-target edges or local defects on the target edge, thereby improving the geometric consistency of the edge point set used to determine the target feature points and ensuring the final fitting accuracy.

[0111] In another embodiment, it further includes:

[0112] Among the edge points identified by the central scan line, edge points that meet the preset conditions are identified as target feature points and extracted.

[0113] The edge points that meet the preset conditions include either the foremost edge point along the direction of the central scan line or the edge point with the largest grayscale gradient. The direction of the central scan line can be determined by the user.

[0114] This step provides two quick and direct point selection methods: "earliest point along the scan line direction" and "maximum edge intensity," as alternatives to point selection based on fitted lines. These two methods are logically simple, requiring no complex fitting calculations, and are suitable for rapid measurement scenarios with excellent image quality and clear, uniform edges. Under specific, simple conditions, they offer users a flexible choice that balances efficiency and basic accuracy, enhancing the tool's adaptability to various scenarios.

[0115] like Figure 8 As shown, this application also proposes a feature point extraction tool for performing the feature point extraction method described in any of the above embodiments. Related descriptions can be found in the above embodiments and will not be repeated here. The feature point extraction tool includes: a drawing module 801, an edge point recognition module 802, an edge fitting line extraction module 803, and a feature point extraction module 804.

[0116] The drawing module 801 is used to draw the center line of the selection area on the image of the workpiece to be measured, and to determine the corresponding selection area based on the center line of the selection area.

[0117] The edge point recognition module 802 is used to identify at least one edge point within the selected area by means of a scan line formed within the selected area.

[0118] The edge fitting line extraction module 803 is used to perform edge fitting based on the at least one edge point to obtain an edge fitting line.

[0119] The feature point extraction module 804 is used to determine and extract target feature points based on the at least one edge point.

[0120] This embodiment integrates the drawing module, edge point recognition module, and feature point extraction module into a single tool, enabling its integration into different image measurement systems or image processing platforms.

[0121] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 9As shown, the computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a feature point extraction method. The display screen can be an LCD screen or an e-ink display screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0122] Those skilled in the art will understand that Figure 9 The structure shown is merely a block diagram of a portion of the structure related to this application and does not constitute a limitation on the computer device to which the solution of this application is applied. A specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0123] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described in the above method embodiment.

[0124] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in the above method embodiment.

[0125] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the method described in the above method embodiments.

[0126] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0127] In the description of this specification, references to terms such as "some embodiments," "other embodiments," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative descriptions of the above terms do not necessarily refer to the same embodiments or examples.

[0128] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0129] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these modifications and improvements all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. An image measuring instrument, characterized in that, include: A stage, used to hold the workpiece to be tested; An imaging module is used to acquire an image of the workpiece under test; Display module, used to present the image; A feature extraction module is used to extract features from the image; A measurement module is used to acquire the physical quantities of the workpiece under test based on the features; The feature extraction module includes a feature point extraction unit, which is used to: draw a center line of a selection area on the image of the workpiece to be tested, and determine the corresponding selection area and center scan line based on the center line of the selection area; identify at least one edge point within the selection area by scanning lines formed within the selection area that are parallel to the center scan line; perform edge fitting based on the at least one edge point to obtain an edge fitting line; and determine and extract target feature points located on the center scan line based on the edge fitting line.

2. A feature point extraction method, characterized in that, include: Draw the center line of the selection area on the image of the workpiece to be tested, and determine the corresponding selection area and center scan line based on the center line of the selection area; Within the selected area, at least one edge point is identified by a scan line formed within the selected area that is parallel to the center scan line; Edge fitting is performed based on the at least one edge point to obtain an edge fitting line; Based on the edge fitting line of the at least one edge point, the target feature point located on the center scan line is determined and extracted.

3. The method according to claim 2, characterized in that, Multiple scan lines are formed within the selected area. Identifying at least one edge point using scan lines parallel to the central scan line formed within the selected area includes: The edge points distributed within the selected area and located on each of the scan lines are identified by corresponding scan lines. The at least one edge point is identified based on the plurality of scan lines.

4. The method according to claim 2, characterized in that, Multiple scan lines are formed within the selected area. Identifying at least one edge point using scan lines parallel to the central scan line formed within the selected area includes: Determine the target recognition area for each of the scan lines; The target recognition area distributed within the selected area and the edge point located on each of the scan lines are identified by the corresponding scan lines. The at least one edge point is identified based on the plurality of scan lines.

5. The method according to claim 2, characterized in that, Edge points on the scan line are identified based on the gray-level gradient on the scan line.

6. The method according to any one of claims 2-5, characterized in that, After identifying at least one edge point using scan lines formed within the selected area that are parallel to the center scan line, the method further includes: Based on the edge intensity of the central scan line, noise reduction is performed on the edge points of other scan lines besides the central scan line.

7. The method according to claim 2, characterized in that, Based on the edge fitting line, the target feature points located on the center scan line are determined and extracted, including: Among the edge points identified by the central scan line, edge points that meet the preset conditions are identified as target feature points and extracted. Among them, the edge points that satisfy the preset conditions include any one of the edge points closest to the fitting line and the edge points located at the intersection of the edge fitting line and the center scan line.

8. The method according to claim 7, characterized in that, Based on the edge fitting line, the target feature points located on the center scan line are determined and extracted, and the method further includes: The edge points whose deviation from the edge fitting line is greater than a threshold are filtered out to obtain an updated at least one edge point, where the threshold is the maximum allowed distance between the edge point and the fitting line, and the edge fitting line is determined based on the at least one edge point. Based on at least one updated edge point and the edge fitting line, the target feature point located on the center scan line is determined and extracted.

9. The method according to claim 2, characterized in that, Also includes: Among the edge points identified by the central scan line, edge points that meet the preset conditions are identified as target feature points and extracted. Among them, the edge points that meet the preset conditions include either the foremost edge point along the direction of the central scan line or the edge point with the largest gray-scale gradient.

10. A feature point extraction tool, characterized in that, Perform the method comprising any one of claims 2-9.

Images