Intelligent identification implementation method and device for cutter fracture condition

Abstract

The invention relates to the technical field of image processing, and discloses an intelligent recognition realization method and device for a cutter fracture condition, and the method comprises the steps: determining a target ROI region containing a to-be-detected cutter according to a cutter image, and carrying out the gray conversion operation of the target ROI region, and obtaining an original gray image; executing a predetermined image processing operation on the original grayscale image to obtain a processed grayscale image; after all the edge contours of the processed grayscale image are extracted, determining a central point corresponding to each edge contour, and calculating an average central point of all the central points; and according to an area between the average center point and all edge points of the processed grayscale image, determining a pixel threshold value serving as a basis for detecting the fracture condition of the to-be-detected cutter. Therefore, the detection efficiency and accuracy of the cutter fracture condition can be improved, and the method is suitable for large-diameter and small-diameter cutters, has general applicability, and is beneficial to expanding the application scene of the detection method of the cutter fracture condition.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a method and a device for realizing intelligent recognition of tool fracture conditions. Background Art

[0002] In order to ensure that the quality of the tools used in processing and manufacturing meets the standards, and thus ensure the normal progress of processing and manufacturing and improve production efficiency, it is necessary to identify the fracture of the tool in a timely and accurate manner. At present, there are mainly two ways to identify the fracture of the tool in the machine tool: the first way is manual detection, which requires experienced personnel to judge whether the tool is broken by sound, size difference of the output parts and visual inspection. If it is broken, it will be replaced. This manual detection method relies on experience and requires production suspension detection. There is a problem of low detection efficiency. If the detection personnel are not experienced enough, there may be false detection and missed detection; the second way is to use corresponding sensors (such as power sensors, current sensors, force sensors, etc.) to monitor the tool processing process, that is, to use corresponding sensors to quantitatively record the machine tool processing process. When an abnormal signal appears during the machine tool processing, such as an abnormally high or abnormally low power signal, it is determined that the tool is broken. This method has limited application scenarios and cannot detect the fracture of small diameter tools. In addition, the debugging cycle is also long, which is not conducive to improving detection efficiency.

[0003] It can be seen that it is particularly important to provide a tool fracture detection method that has universal applicability and can also improve detection efficiency and detection accuracy. Summary of the invention

[0004] The present invention provides an intelligent identification implementation method and device for tool fracture conditions, which can help improve the detection efficiency and detection accuracy of tool fracture conditions, and can also be applied to large-diameter tools and small-diameter tools, and has universal applicability.

[0005] The first aspect of the present invention discloses a method for intelligently identifying a tool fracture condition, the method comprising:

[0006] After determining the target ROI region according to the tool image acquired by the image acquisition device, performing a grayscale conversion operation on the target ROI region to obtain an original grayscale image corresponding to the target ROI region; wherein the target ROI region is a region in the tool image that contains the tool to be detected;

[0007] Performing a predetermined image processing operation on the original grayscale image to obtain a processed grayscale image;

[0008] After extracting all edge contours of the processed grayscale image, determining a center point corresponding to each edge contour, and calculating an average center point of all the center points;

[0009] A target pixel threshold is determined according to an area between the average center point and all edge points of the processed grayscale image; wherein the target pixel threshold is used as a basis for detecting the fracture condition of the tool to be detected.

[0010] As an optional implementation, in the first aspect of the present invention, performing a predetermined image processing operation on the original grayscale image to obtain a processed grayscale image includes:

[0011] Performing a first edge detection operation on the original grayscale image or performing a filtering operation and a first edge detection operation in sequence to obtain a first edge detection result of the original grayscale image;

[0012] Performing a dilation operation on the first edge detection result of the original grayscale image to obtain an edge-dilated grayscale image as a processed grayscale image;

[0013] Wherein, the method further comprises:

[0014] After obtaining the grayscale image after edge dilation, a second edge detection operation is performed on the grayscale image after edge dilation to obtain a second edge detection result of the grayscale image after edge dilation; wherein the second edge detection result includes all the edge contours and all the edge points.

[0015] As an optional implementation, in the first aspect of the present invention, determining the target pixel threshold according to the area between the average center point and all edge points of the processed grayscale image includes:

[0016] Draw a straight line from each edge point in the second edge detection result to the average center point;

[0017] Performing a binarization operation on all straight line regions and non-straight line regions in the grayscale image after edge dilation;

[0018] Calculate the average pixel value of all pixels in all the straight line areas after binarization;

[0019] A target pixel threshold is determined according to the average pixel value.

[0020] As an optional implementation, in the first aspect of the present invention, the method further comprises:

[0021] Based on the target pixel threshold, a first number of pixel points in the original grayscale image whose pixel values ​​are lower than the target pixel threshold and a second number of pixel points whose pixel values ​​are not lower than the target pixel threshold are counted, and according to the size relationship between the first number and the second number, a target position area of ​​a key feature of a tool to be detected in the original grayscale image is determined from the original grayscale image;

[0022] Based on the target pixel threshold and the target position area, the fracture condition of the tool to be detected is judged to obtain a fracture condition judgment result corresponding to the tool to be detected.

[0023] As an optional implementation, in the first aspect of the present invention, judging the fracture condition of the tool to be detected based on the target pixel threshold and the position information to obtain the fracture condition judgment result corresponding to the tool to be detected includes:

[0024] Based on the target pixel threshold, performing a pixel statistical operation on the target position area in the original grayscale image to obtain a first pixel statistical result;

[0025] Based on the target pixel threshold, a pixel statistical operation is performed on a key tool feature area in a predetermined standard grayscale image to obtain a second pixel statistical result;

[0026] It is determined whether the tool to be detected is fractured according to the first pixel statistical result and the second pixel statistical result, and a fracture judgment result corresponding to the tool to be detected is obtained.

[0027] As an optional implementation, in the first aspect of the present invention, judging whether the tool to be detected is broken according to the first pixel statistical result and the second pixel statistical result, and obtaining the fracture judgment result corresponding to the tool to be detected, includes:

[0028] Calculating a ratio of the first pixel statistical result to the second pixel statistical result, and determining whether the ratio is greater than or equal to a preset threshold;

[0029] If the ratio is greater than or equal to the preset threshold, it is determined that the tool to be detected is broken; and / or, if the ratio is less than the preset threshold, it is determined that the tool to be detected is not broken.

[0030] As an optional implementation, in the first aspect of the present invention, determining the target position area of ​​the key feature of the tool to be detected in the original grayscale image from the original grayscale image according to the size relationship between the first quantity and the second quantity includes:

[0031] Determine a minimum number from the first number and the second number, determine the key feature of the tool to be detected according to the pixel points corresponding to the minimum number, and identify the target position area of ​​the key feature of the tool to be detected in the original grayscale image;

[0032] Wherein, the identifying of the target position area of ​​the key feature of the tool to be detected in the original grayscale image includes:

[0033] Performing binary segmentation on the original grayscale image based on the target pixel threshold to obtain a binary image;

[0034] Performing an edge extraction operation on the binary image to obtain an edge extraction result;

[0035] Based on the edge extraction result, determine the vertical and horizontal coordinate values ​​corresponding to the edge of the binary image in the constructed coordinate system, wherein the vertical and horizontal coordinate values ​​include a minimum horizontal coordinate, a maximum horizontal coordinate, a minimum vertical coordinate and a maximum vertical coordinate;

[0036] A corresponding rectangular area is drawn in the binary image based on the vertical and horizontal coordinate values, and a target position area of ​​the key feature of the tool to be detected in the original grayscale image is identified according to the rectangular area.

[0037] The second aspect of the present invention discloses an intelligent identification device for a tool fracture condition, the device comprising:

[0038] A grayscale conversion module is used to perform a grayscale conversion operation on the target ROI area after determining the target ROI area according to the tool image acquired by the image acquisition device, so as to obtain an original grayscale image corresponding to the target ROI area; wherein the target ROI area is the area in the tool image that contains the tool to be detected;

[0039] An image processing module, used for performing a predetermined image processing operation on the original grayscale image to obtain a processed grayscale image;

[0040] A threshold determination module is used to determine the center point corresponding to each edge contour after extracting all edge contours of the processed grayscale image, calculate the average center point of all the center points, and determine the target pixel threshold based on the area between the average center point and all edge points of the processed grayscale image; wherein the target pixel threshold is used as a basis for detecting the fracture condition of the tool to be detected.

[0041] As an optional implementation, in the second aspect of the present invention, the image processing module performs a predetermined image processing operation on the original grayscale image to obtain a processed grayscale image in a specific manner including:

[0042] Performing a first edge detection operation on the original grayscale image or performing a filtering operation and a first edge detection operation in sequence to obtain a first edge detection result of the original grayscale image;

[0043] Performing a dilation operation on the first edge detection result of the original grayscale image to obtain an edge-dilated grayscale image as a processed grayscale image;

[0044] Wherein, the image processing module is also used to perform a second edge detection operation on the grayscale image after edge expansion after obtaining the grayscale image after edge expansion, so as to obtain a second edge detection result of the grayscale image after edge expansion; wherein, the second edge detection result includes all the edge contours and all the edge points.

[0045] As an optional implementation, in the second aspect of the present invention, the threshold determination module determines the target pixel threshold according to the area between the average center point and all edge points of the processed grayscale image in a specific manner including:

[0046] Draw a straight line from each edge point in the second edge detection result to the average center point;

[0047] Performing a binarization operation on all straight line regions and non-straight line regions in the grayscale image after edge dilation;

[0048] Calculate the average pixel value of all pixels in all the straight line areas after binarization;

[0049] A target pixel threshold is determined according to the average pixel value.

[0050] As an optional implementation, in the second aspect of the present invention, the device further includes a fracture detection module, wherein:

[0051] The fracture detection module is used to count, based on the target pixel threshold, a first number of pixels corresponding to the original grayscale image whose pixel values ​​are lower than the target pixel threshold and a second number of pixels corresponding to the pixel values ​​not lower than the target pixel threshold, and determine, from the original grayscale image, a target position area of ​​a key feature of a tool to be detected in the original grayscale image according to a size relationship between the first number and the second number; and, based on the target pixel threshold and the target position area, judge the fracture condition of the tool to be detected to obtain a fracture condition judgment result corresponding to the tool to be detected.

[0052] As an optional implementation, in the second aspect of the present invention, the fracture detection module judges the fracture condition of the tool to be detected based on the target pixel threshold and the position information, and the specific manner of obtaining the fracture condition judgment result corresponding to the tool to be detected includes:

[0053] Based on the target pixel threshold, performing a pixel statistical operation on the target position area in the original grayscale image to obtain a first pixel statistical result;

[0054] Based on the target pixel threshold, a pixel statistical operation is performed on a key tool feature area in a predetermined standard grayscale image to obtain a second pixel statistical result;

[0055] It is determined whether the tool to be detected is fractured according to the first pixel statistical result and the second pixel statistical result, and a fracture judgment result corresponding to the tool to be detected is obtained.

[0056] As an optional implementation, in the second aspect of the present invention, the fracture detection module determines whether the tool to be detected is fractured according to the first pixel statistical result and the second pixel statistical result, and a specific method for obtaining the fracture judgment result corresponding to the tool to be detected includes:

[0057] Calculating a ratio of the first pixel statistical result to the second pixel statistical result, and determining whether the ratio is greater than or equal to a preset threshold;

[0058] If the ratio is greater than or equal to the preset threshold, it is determined that the tool to be detected is broken; and / or, if the ratio is less than the preset threshold, it is determined that the tool to be detected is not broken.

[0059] As an optional implementation, in the second aspect of the present invention, the fracture detection module determines the target position area of ​​the key feature of the tool to be detected in the original grayscale image from the original grayscale image according to the size relationship between the first quantity and the second quantity. The specific method includes:

[0060] Determine a minimum number from the first number and the second number, determine the key feature of the tool to be detected according to the pixel points corresponding to the minimum number, and identify the target position area of ​​the key feature of the tool to be detected in the original grayscale image;

[0061] The specific manner in which the fracture detection module identifies the target position area of ​​the key feature of the tool to be detected in the original grayscale image includes:

[0062] Performing binary segmentation on the original grayscale image based on the target pixel threshold to obtain a binary image;

[0063] Performing an edge extraction operation on the binary image to obtain an edge extraction result;

[0064] Based on the edge extraction result, determine the vertical and horizontal coordinate values ​​corresponding to the edge of the binary image in the constructed coordinate system, wherein the vertical and horizontal coordinate values ​​include a minimum horizontal coordinate, a maximum horizontal coordinate, a minimum vertical coordinate and a maximum vertical coordinate;

[0065] A corresponding rectangular area is drawn in the binary image based on the vertical and horizontal coordinate values, and a target position area of ​​the key feature of the tool to be detected in the original grayscale image is identified according to the rectangular area.

[0066] The third aspect of the present invention discloses another intelligent identification device for a tool fracture condition, the device comprising:

[0067] A memory storing executable program code;

[0068] a processor coupled to the memory;

[0069] The processor calls the executable program code stored in the memory to execute part or all of the steps in the method for intelligently identifying tool fracture conditions as described in any one of the first aspects of the present invention.

[0070] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute some or all of the steps in the intelligent identification method for tool fracture conditions described in any one of the first aspects of the present invention.

[0071] Compared with the prior art, the present invention has the following beneficial effects:

[0072] The present invention is applied to a scene (such as a processing workshop) where the fracture condition of a tool needs to be detected. After a target ROI area containing the tool to be detected is determined based on a tool image acquired by an image acquisition device (such as a pre-installed and debugged camera), a grayscale conversion operation is performed on the target ROI area to obtain an original grayscale image. A predetermined image processing operation is then performed on the original grayscale image to obtain a processed grayscale image. After all edge contours of the processed grayscale image are extracted, the center point corresponding to each edge contour is determined, and the average center point of all center points is calculated; a target pixel threshold used as a basis for detecting the fracture condition of the tool to be detected is determined based on the average center point and all edge points of the processed grayscale image. It can be seen that the present invention provides an intelligent method for determining the pixel threshold used as a basis for tool fracture detection. The method of determining the pixel threshold by the average center point corresponding to the edge contour and the edge point of the edge contour makes it possible to pay more attention to the edge features of the region of interest and the pixel values ​​within the edge contour when determining the pixel threshold, so that the determined pixel threshold is more reliable, that is, the reliability of the pixel threshold used as a basis for tool fracture detection is improved, which helps to improve the detection efficiency and accuracy of tool fractures. Compared with the method of using the signal collected by the corresponding sensor as a basis for tool fracture detection, the method of using the pixel threshold determined based on the method of the present invention as a basis for tool fracture detection is suitable for large and small diameter tools, has universal applicability, and is conducive to expanding the applicable scenarios of tool fracture detection methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0074] Figure 1 It is a flow chart of a method for realizing intelligent identification of tool fracture conditions disclosed in an embodiment of the present invention;

[0075] Figure 2 It is a flow chart of another intelligent identification method for a tool fracture condition disclosed in an embodiment of the present invention;

[0076] Figure 3 It is a flowchart of a method for image region segmentation based on a region of interest disclosed in an embodiment of the present invention;

[0077] Figure 4 It is a structural schematic diagram of a device for realizing intelligent identification of tool fracture conditions disclosed in an embodiment of the present invention;

[0078] Figure 5 It is a structural schematic diagram of another intelligent identification and realization device for tool fracture conditions disclosed in an embodiment of the present invention;

[0079] Figure 6 It is a structural schematic diagram of another intelligent identification and implementation device for tool fracture conditions disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0080] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0081] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or end including a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units inherent to these processes, methods, products or ends.

[0082] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0083] The present invention discloses a method and device for realizing intelligent identification of tool fracture conditions, and provides an intelligent determination method for pixel thresholds used as a basis for tool fracture detection. The method of determining the pixel threshold by the average center point corresponding to the edge contour and the edge point of the edge contour makes it possible to pay more attention to the edge features of the region of interest and the pixel values ​​within the edge contour when determining the pixel threshold, so that the determined pixel threshold is more reliable, that is, the reliability of the pixel threshold used as a basis for tool fracture detection is improved, which helps to improve the detection efficiency and accuracy of tool fracture conditions. Compared with the method of using the signal collected by the corresponding sensor as a basis for tool fracture detection, the method of using the pixel threshold determined based on the method of the present invention as a basis for tool fracture detection is applicable to large and small diameter tools, has universal applicability, and is conducive to expanding the applicable scenarios of the tool fracture detection method. The following are detailed descriptions.

[0084] Embodiment 1

[0085] See also Figure 1 , Figure 1 1 is a flow chart of a method for realizing intelligent identification of tool fracture conditions disclosed in an embodiment of the present invention. Figure 1 The method shown is applied to an intelligent identification device for tool fracture conditions, which can be integrated into a tool fracture detection device, which can be a local device or a cloud device (such as a cloud server), and the embodiments of the present invention are not limited thereto.

[0086] like Figure 1 As shown, the method may include the following steps:

[0087] 101. After determining a target ROI region according to a tool image acquired by an image acquisition device, a grayscale conversion operation is performed on the target ROI region to obtain an original grayscale image corresponding to the target ROI region.

[0088] In an embodiment of the present invention, the target ROI area determined is the area in the tool image that contains the tool to be detected. Specifically, an image acquisition device, such as a camera or other device capable of image acquisition, is pre-installed in an application scenario where tool fracture detection is required, and after the image acquisition device is installed, the relevant shooting parameters and / or relevant communication parameters of the image acquisition device can be further debugged, such as debugging at least one of its shooting angle, shooting resolution, and the relative position relationship between it and the tool to be detected, and establishing and debugging the communication relationship between the image acquisition device and the detection device for tool fracture conditions. It should be particularly noted that since the scene parameters corresponding to the application scenario are variable, the aforementioned shooting parameters and communication parameters are not fixed after debugging, and they can be adaptively adjusted according to actual conditions.

[0089] In an embodiment of the present invention, the image acquisition device can acquire one or more tool images. After the acquisition is completed, the acquired one or more images can be transmitted to a corresponding device, such as a tool fracture detection device or an industrial computer in an application scenario where tool fracture detection is required. Then, the aforementioned corresponding device that receives the tool image selects a suitable tool image, such as a tool image that captures the entire tool with a suitable shooting angle and is relatively clear; or, after the image acquisition device acquires one or more tool images, it can select a suitable tool image from the acquired images according to pre-set image requirement conditions (such as angle requirement conditions, clarity requirement conditions, tool feature requirement conditions, etc.), and transmit the selected tool image to the corresponding device. Furthermore, after determining a suitable tool image, a target ROI region (i.e., a target region of interest) containing the tool to be detected can be further automatically extracted from the tool image. Alternatively, the tool image can be displayed on an image operation interface by the aforementioned corresponding device, and an operator selects the target ROI region by placing a selection box in the image operation interface on the tool to be detected in the tool image. When placing the selection box, the center area of ​​the selection box can be made to coincide with the tool head position of the tool to be detected. If the tool to be detected in the tool image is too large, the operator can adjust the size of the selection box in the image operation interface or change the size of the ROI region by dragging the edge of the selection box. In this way, the selected target ROI region can contain the tool to be detected without containing too many background features, which is conducive to improving the rationality of the manually selected target ROI region.

[0090] 102. Perform a predetermined image processing operation on the original grayscale image to obtain a processed grayscale image.

[0091] In an embodiment of the present invention, the predetermined image processing operation at least includes an edge detection operation. Optionally, the aforementioned image processing operation may also include a filtering operation. Further optionally, the edge detection operation may include one edge detection operation or multiple edge detection operations. Further optionally, when the edge detection operation includes multiple edge detection operations, after executing the current edge detection operation, a dilation operation may be performed on the edge detected by the current edge detection operation before the next edge detection operation is performed, which is beneficial to enhancing edge features and further beneficial to improving the accuracy and reliability of subsequent operations. It should be particularly noted that the aforementioned edge detection operation and filtering operation may respectively adopt the edge detection algorithm and filtering algorithm of the prior art, and when multiple edge detection operations are performed, the multiple edge detection operations may adopt the same edge detection algorithm or different edge detection algorithms, preferably the same edge detection algorithm.

[0092] 103. After extracting all edge contours of the grayscale image processed above, determine the center point corresponding to each edge contour, and calculate the average center point of all center points.

[0093] In the embodiment of the present invention, a corresponding coordinate system may be pre-established. Optionally, the coordinate system may be created based on the processed grayscale image, so that each pixel point in the processed grayscale image has a corresponding pixel coordinate (x n ,y n ), where x n Represents the horizontal coordinate of the nth pixel in the aforementioned coordinate system, y n After extracting all edge contours of the grayscale image processed above, the center point of each edge contour can be calculated respectively, and then the average center point can be calculated based on the center points of all edge contours. The position coordinates of the average center point are (c x , c y ).

[0094] Optionally, the embodiment of the present invention may obtain the center point of the edge contour through Hu moment.

[0095] 104. Determine a target pixel threshold value according to an area between an average center point and all edge points of the processed grayscale image; wherein the target pixel threshold value is used as a basis for detecting the fracture condition of the tool to be detected.

[0096] It can be seen that the embodiment of the present invention provides an intelligent method for determining the pixel threshold used as a basis for tool fracture detection. The method of determining the pixel threshold by the average center point corresponding to the edge contour and the edge point of the edge contour makes it possible to pay more attention to the edge features of the region of interest and the pixel values ​​within the edge contour when determining the pixel threshold, so that the determined pixel threshold is more reliable, that is, the reliability of the pixel threshold used as a basis for tool fracture detection is improved, which helps to improve the detection efficiency and accuracy of tool fracture. Compared with the method of using the signal collected by the corresponding sensor as the basis for tool fracture detection, the method of using the pixel threshold determined based on the method of the present invention as the basis for tool fracture detection is suitable for large and small diameter tools, has universal applicability, and is conducive to expanding the applicable scenarios of tool fracture detection methods.

[0097] Embodiment 2

[0098] See also Figure 2 , Figure 2 1 is a flow chart of another intelligent identification method for tool fracture disclosed in an embodiment of the present invention. Figure 2The method shown is applied to an intelligent identification device for tool fracture conditions, which can be integrated into a tool fracture detection device, which can be a local device or a cloud device (such as a cloud server), and the embodiments of the present invention are not limited thereto.

[0099] like Figure 2 As shown, the method may include the following steps:

[0100] 201. After determining a target ROI region according to the tool image acquired by the image acquisition device, perform a grayscale conversion operation on the target ROI region to obtain an original grayscale image corresponding to the target ROI region.

[0101] The determined target ROI area is the area in the tool image that contains the tool to be detected.

[0102] 202. Perform a first edge detection operation on the original grayscale image or perform a filtering operation and a first edge detection operation in sequence to obtain a first edge detection result of the original grayscale image.

[0103] 203. Perform a dilation operation on the first edge detection result of the original grayscale image to obtain a grayscale image after edge dilation as a processed grayscale image.

[0104] In the embodiment of the present invention, performing a dilation operation on the first edge detection result is beneficial to enhancing edge features, thereby facilitating improving the accuracy of the edge detection result corresponding to the second edge detection operation.

[0105] 204. After obtaining the edge-dilated grayscale image, perform a second edge detection operation on the edge-dilated grayscale image to obtain a second edge detection result of the edge-dilated grayscale image; wherein the second edge detection result includes all edge contours and all edge points.

[0106] 205. After all edge contours of the processed grayscale image are extracted, a center point corresponding to each edge contour is determined, and an average center point of all center points is calculated.

[0107] 206. Draw a straight line from each edge point in the second edge detection result to the average center point.

[0108] 207. Perform a binarization operation on all straight line areas and non-straight line areas in the grayscale image after edge dilation.

[0109] 208. Calculate the average pixel value of all pixels in all straight line areas after binarization, and determine the target pixel threshold value according to the average pixel value.

[0110] It can be seen that the embodiment of the present invention provides an intelligent method for determining the pixel threshold used as a basis for tool fracture detection. The method of determining the pixel threshold by the average center point corresponding to the edge contour and the edge point of the edge contour makes it possible to pay more attention to the edge features of the region of interest and the pixel values ​​within the edge contour when determining the pixel threshold, so that the determined pixel threshold is more reliable, that is, the reliability of the pixel threshold used as a basis for tool fracture detection is improved, which helps to improve the detection efficiency and accuracy of tool fracture. Compared with the method of using the signal collected by the corresponding sensor as the basis for tool fracture detection, the method of using the pixel threshold determined based on the method of the present invention as the basis for tool fracture detection is suitable for large and small diameter tools, has universal applicability, and is conducive to expanding the applicable scenarios of tool fracture detection methods.

[0111] In the embodiment of the present invention, optionally, the above-mentioned determining the target pixel threshold according to the average pixel value may include:

[0112] The calculated average pixel value is determined as the desired target pixel threshold; or,

[0113] According to the determined influencing factors, a pixel value correction parameter is determined, and the calculated average pixel value is adjusted based on the determined pixel value correction parameter to obtain an adjusted pixel value, and the adjusted pixel value is determined as the required target pixel threshold. Optionally, the determined influencing factors may be the proportion of the partial noise area considered when calculating the average pixel value compared to the entire noise area; or,

[0114] The average pixel value is adjusted according to the pixel value adjustment instruction triggered by the operator to obtain an adjusted pixel value, and the adjusted pixel value is determined as the required target pixel threshold.

[0115] Further optionally, the pixel value correction parameter may include: a pixel value correction coefficient, and / or a pixel value correction offset, which is not limited in the embodiment of the present invention.

[0116] It can be seen that the embodiments of the present invention also provide a variety of implementation methods for determining the final target pixel threshold based on the average pixel value after the average pixel value is determined, which is not only conducive to expanding the application scenarios of the pixel threshold determination method described in the embodiments of the present invention, but also conducive to further improving the accuracy and flexibility of determining the pixel threshold.

[0117] In an optional embodiment, the method may further include the following steps:

[0118] 209. Based on the target pixel threshold, count a first number of pixel points in the original grayscale image whose pixel values ​​are lower than the target pixel threshold and a second number of pixel points whose pixel values ​​are not lower than the target pixel threshold.

[0119] 210. Determine a target position region of a key feature of the tool to be detected in the original grayscale image based on a size relationship between the first quantity and the second quantity.

[0120] 211. Based on the target pixel threshold and the target position area, the fracture condition of the tool to be detected is judged to obtain a fracture condition judgment result corresponding to the tool to be detected.

[0121] In this optional embodiment, the target pixel threshold is used as the detection basis of the fracture of the tool to be detected, which mainly involves using the target pixel threshold as the segmentation of the binary image. At present, the binary segmentation method with better segmentation effect is the Otsu threshold segmentation method, which uses the principle of maximum inter-class variance to obtain the optimal threshold for segmentation. However, after actual testing and application, it is found that compared with the method for binary segmentation based on the pixel threshold determined by the embodiment of the present invention, the Otsu threshold segmentation method has the situation of over-segmentation, and does not consider the influence of noise, that is: the Otsu threshold segmentation method will affect the prediction of the pixel threshold because the noise area is too large, and it has high requirements for the environment. When determining the pixel threshold, the embodiment of the present invention will appropriately consider the pixel value in the part of the noise area according to the extracted edge contour, effectively reducing the influence of noise on the pixel threshold, that is: compared with the simple color difference comparison method in the Otsu threshold segmentation method, the embodiment of the present invention pays more attention to the pixel value of the pixel point in the edge feature of the central area when determining the pixel threshold. In addition, when detecting the fracture of the tool, only one image is needed as a template, which further improves the convenience of detecting the fracture of the tool. In addition, it is not only suitable for fracture detection of large-diameter tools, but also for fracture detection of small-diameter tools. It does not have too high requirements on the detection environment and has strong applicability.

[0122] It can be seen that after determining the required pixel threshold, this optional embodiment can further realize intelligent detection of tool breakage based on the determined pixel threshold, which not only expands the intelligent function of the intelligent identification device of tool breakage, but also helps to improve the detection efficiency of tool breakage.

[0123] In another optional embodiment, the above-mentioned determining the target position area of ​​the key feature of the tool to be detected in the original grayscale image according to the size relationship between the first quantity and the second quantity may include:

[0124] Based on the target pixel threshold, a pixel statistical operation is performed on the target position area in the original grayscale image to obtain a first pixel statistical result;

[0125] Based on the target pixel threshold, a pixel statistical operation is performed on a key tool feature area in a predetermined standard grayscale image to obtain a second pixel statistical result;

[0126] According to the first pixel statistical result and the second pixel statistical result, it is judged whether the tool to be detected has a fracture, and a fracture judgment result corresponding to the tool to be detected is obtained.

[0127] It can be seen that after determining the pixel threshold and the key features of the tool to be detected, this optional embodiment can directly detect / judge the tool breakage condition based on the number of pixels, thereby improving the detection accuracy of the tool breakage condition and the convenience of detecting the tool breakage condition.

[0128] In this optional embodiment, the above-mentioned pixel statistical operation is used to count the number of corresponding pixel points in the corresponding image, and the corresponding pixel points are pixel points in the corresponding image whose pixel values ​​are lower than or not lower than the above-mentioned target pixel threshold, which are specifically determined according to the relationship between the above-mentioned first number and the above-mentioned second number. More specifically, if the first number corresponding to the pixel points in the original grayscale image whose pixel values ​​are lower than the target pixel threshold is greater than the second number corresponding to the pixel points whose pixel values ​​are not lower than the target pixel threshold, then the corresponding pixel points are specifically the pixel points in the corresponding image whose pixel values ​​are not lower than the above-mentioned target pixel threshold; if the first number corresponding to the pixel points in the original grayscale image whose pixel values ​​are lower than the target pixel threshold is less than the second number corresponding to the pixel points whose pixel values ​​are not lower than the target pixel threshold, then the corresponding pixel points are specifically the pixel points in the corresponding image whose pixel values ​​are lower than the above-mentioned target pixel threshold.

[0129] Furthermore, judging whether the tool to be detected is broken according to the first pixel statistical result and the second pixel statistical result, and obtaining the fracture judgment result corresponding to the tool to be detected, may include:

[0130] Calculating a ratio of a first pixel statistical result to a second pixel statistical result, and determining whether the ratio is greater than or equal to a preset threshold;

[0131] If the ratio is greater than or equal to a preset threshold, it is determined that the tool to be detected is broken; and / or, if the ratio is less than the preset threshold, it is determined that the tool to be detected is not broken.

[0132] It should be noted that the preset threshold value compared with the above ratio can be adaptively adjusted according to actual conditions.

[0133] It can be seen that this optional embodiment can also realize intelligent identification of the fracture of the tool to be detected through the size relationship between the ratio of the pixel statistical results corresponding to the tool to be detected and the pixel statistical results corresponding to the key tool feature area in the standard grayscale image and the corresponding threshold, thereby improving the detection accuracy of the tool fracture and further improving the convenience of detecting the tool fracture.

[0134] In yet another optional embodiment, the above-mentioned determining the target position area of ​​the key feature of the tool to be detected in the original grayscale image according to the size relationship between the first quantity and the second quantity may include:

[0135] A minimum number is determined from the first number and the second number, a key feature of the tool to be detected is determined according to the pixel points corresponding to the minimum number, and a target position area of ​​the key feature of the tool to be detected in the original grayscale image is identified.

[0136] In this optional embodiment, identifying the target position area can be understood as segmenting the target position area of ​​the key features of the tool to be detected in the original grayscale image. The corresponding image segmentation process can be referred to in Figure 3 , Figure 3 FIG. 1 is a flow chart of a method for segmenting an image region based on a region of interest disclosed in an embodiment of the present invention. Figure 3 As shown, the image region segmentation method may include the following steps:

[0137] 301. Perform binary segmentation on the original grayscale image based on the target pixel threshold to obtain a binary image.

[0138] 302. Perform an edge extraction operation on the binary image to obtain an edge extraction result.

[0139] 303. Based on the edge extraction result, determine the vertical and horizontal coordinate values ​​corresponding to the edge of the binary image in the constructed coordinate system.

[0140] The vertical and horizontal coordinate values ​​include the minimum horizontal coordinate, the maximum horizontal coordinate, the minimum vertical coordinate and the maximum vertical coordinate.

[0141] 304. Draw a corresponding rectangular area in the binary image based on the vertical and horizontal coordinate values, and identify the target position area of ​​the key feature of the tool to be detected in the original grayscale image according to the rectangular area.

[0142] In this optional embodiment, after the corresponding rectangular area is drawn in the binary image based on the vertical and horizontal coordinate values, the non-rectangular area is the mask area that does not need to be considered.

[0143] In this optional embodiment, after the target ROI area is determined, there will be some background noise in the target ROI area, which will interfere with the extraction of tool features and the identification of the position area, thereby affecting the detection of tool fracture. Figure 3 The process shown realizes the automatic segmentation of the key area (that is, the target position area of ​​the key features of the tool to be detected in the original grayscale image) and automatically retains the best feature area for corresponding pixel statistical operations, instead of requiring the operator to manually make a mask to block the non-feature area. This is not only beneficial to improving the recognition accuracy of the target position area of ​​the key features of the tool to be detected in the original grayscale image, but also beneficial to improving the recognition efficiency of the target position area of ​​the key features of the tool to be detected in the original grayscale image.

[0144] Embodiment 3

[0145] See also Figure 4 , Figure 4 1 is a schematic diagram of a structure of an intelligent identification device for a tool fracture condition disclosed in an embodiment of the present invention. Figure 4 The method device shown can be integrated into a tool breakage detection device and used to implement any of the methods described in Example 1 or Example 2. The detection device can be a local device or a cloud device (such as a cloud server), which is not limited by the embodiments of the present invention.

[0146] like Figure 4 As shown, the device may include:

[0147] The grayscale conversion module 401 is used to perform a grayscale conversion operation on the target ROI area after determining the target ROI area according to the tool image acquired by the image acquisition device, so as to obtain an original grayscale image corresponding to the target ROI area; wherein the target ROI area is the area in the tool image that contains the tool to be detected;

[0148] An image processing module 402 is used to perform a predetermined image processing operation on the original grayscale image to obtain a processed grayscale image;

[0149] The threshold determination module 403 is used to determine the center point corresponding to each edge contour after extracting all edge contours of the processed grayscale image, calculate the average center point of all center points, and determine the target pixel threshold based on the area between the average center point and all edge points of the processed grayscale image; wherein the target pixel threshold is used as a basis for detecting the fracture condition of the tool to be detected.

[0150] It can be seen that implementation Figure 4The described device provides an intelligent method for determining a pixel threshold used as a basis for detecting tool fracture. The method of determining the pixel threshold by using the average center point corresponding to the edge contour and the edge point of the edge contour makes it possible to pay more attention to the edge features of the region of interest and the pixel values ​​within the edge contour when determining the pixel threshold, thereby making the determined pixel threshold more reliable, that is, improving the reliability of the pixel threshold used as a basis for detecting tool fracture. This helps to improve the detection efficiency and accuracy of tool fracture. Compared with the method of using the signal collected by the corresponding sensor as a basis for detecting tool fracture, the method of using the pixel threshold determined based on the method of the present invention as a basis for detecting tool fracture is suitable for large and small diameter tools, has universal applicability, and is conducive to expanding the applicable scenarios of the tool fracture detection method.

[0151] In an optional embodiment, the image processing module 402 performs a predetermined image processing operation on the original grayscale image to obtain the processed grayscale image in a specific manner including:

[0152] Performing a first edge detection operation on the original grayscale image or performing a filtering operation and a first edge detection operation in sequence to obtain a first edge detection result of the original grayscale image;

[0153] A dilation operation is performed on the first edge detection result of the original grayscale image to obtain a grayscale image after edge dilation as a processed grayscale image.

[0154] Further optionally, the image processing module 402 is also used to perform a second edge detection operation on the grayscale image after edge expansion after obtaining the grayscale image after edge expansion, so as to obtain a second edge detection result of the grayscale image after edge expansion; wherein the second edge detection result includes all edge contours and all edge points.

[0155] It can be seen that this optional embodiment first performs a dilation operation on the edge detected by the current edge detection operation, and then performs the next edge detection operation, which is beneficial to enhancing edge features and further beneficial to improving the accuracy and reliability of subsequent operations.

[0156] In another optional embodiment, the threshold determination module 403 determines the target pixel threshold according to the area between the average center point and all edge points of the processed grayscale image in a specific manner including:

[0157] Draw a straight line from each edge point in the second edge detection result to the average center point;

[0158] Binarization operation is performed on all straight line areas and non-straight line areas in the grayscale image after edge dilation;

[0159] Calculate the average pixel value of all pixels in all straight line areas after binarization;

[0160] According to the average pixel value, the target pixel threshold is determined.

[0161] It can be seen that this optional embodiment determines the pixel threshold by using the average center point corresponding to the edge contour and the edge point of the edge contour. This allows more attention to be paid to the edge features of the region of interest and the pixel values ​​within the edge contour when determining the pixel threshold, making the determined pixel threshold more reliable. This improves the reliability of the pixel threshold used as a basis for tool breakage detection, which helps to improve the efficiency and accuracy of tool breakage detection.

[0162] In yet another optional embodiment, Figure 5 As shown, the device further includes a fracture detection module 404, wherein:

[0163] The fracture detection module 404 is used to count, based on a target pixel threshold, a first number of pixel points in the original grayscale image whose pixel values ​​are lower than the target pixel threshold and a second number of pixel points whose pixel values ​​are not lower than the target pixel threshold, and determine, from the original grayscale image, a target position area of ​​a key feature of the tool to be detected in the original grayscale image according to the size relationship between the first number and the second number; and, based on the target pixel threshold and the target position area, judge the fracture condition of the tool to be detected to obtain a fracture condition judgment result corresponding to the tool to be detected.

[0164] It can be seen that after determining the required pixel threshold, this optional embodiment can further realize intelligent detection of tool breakage based on the determined pixel threshold, which not only expands the intelligent function of the intelligent identification device of tool breakage, but also helps to improve the detection efficiency of tool breakage.

[0165] In another optional embodiment, the fracture detection module 404 determines the fracture condition of the tool to be detected based on the target pixel threshold and the position information, and the specific method of obtaining the fracture condition judgment result corresponding to the tool to be detected includes:

[0166] Based on the target pixel threshold, a pixel statistical operation is performed on the target position area in the original grayscale image to obtain a first pixel statistical result;

[0167] Based on the target pixel threshold, a pixel statistical operation is performed on a key tool feature area in a predetermined standard grayscale image to obtain a second pixel statistical result;

[0168] According to the first pixel statistical result and the second pixel statistical result, it is judged whether the tool to be detected has a fracture, and a fracture judgment result corresponding to the tool to be detected is obtained.

[0169] It can be seen that after determining the pixel threshold and the key features of the tool to be detected, this optional embodiment can directly detect / judge the tool breakage condition based on the number of pixels, thereby improving the detection accuracy of the tool breakage condition and the convenience of detecting the tool breakage condition.

[0170] In this optional embodiment, further optionally, the above-mentioned pixel statistical operation is used to count the number of corresponding pixel points in the corresponding image, and the corresponding pixel points are pixel points in the corresponding image whose pixel values ​​are lower than or not lower than the above-mentioned target pixel threshold, which are specifically determined according to the relationship between the above-mentioned first number and the above-mentioned second number. More specifically, if the first number corresponding to the pixel points in the original grayscale image whose pixel values ​​are lower than the target pixel threshold is greater than the second number corresponding to the pixel points whose pixel values ​​are not lower than the target pixel threshold, then the corresponding pixel points are specifically the pixel points in the corresponding image whose pixel values ​​are not lower than the above-mentioned target pixel threshold; if the first number corresponding to the pixel points in the original grayscale image whose pixel values ​​are lower than the target pixel threshold is less than the second number corresponding to the pixel points whose pixel values ​​are not lower than the target pixel threshold, then the corresponding pixel points are specifically the pixel points in the corresponding image whose pixel values ​​are lower than the above-mentioned target pixel threshold.

[0171] The fracture detection module 404 determines whether the tool to be detected is fractured according to the first pixel statistical result and the second pixel statistical result. The specific method of obtaining the fracture judgment result corresponding to the tool to be detected includes:

[0172] Calculating a ratio of a first pixel statistical result to a second pixel statistical result, and determining whether the ratio is greater than or equal to a preset threshold;

[0173] If the ratio is greater than or equal to a preset threshold, it is determined that the tool to be detected is broken; and / or, if the ratio is less than the preset threshold, it is determined that the tool to be detected is not broken.

[0174] It should be noted that the preset threshold value compared with the above ratio can be adaptively adjusted according to actual conditions.

[0175] It can be seen that this optional embodiment can also realize intelligent identification of the fracture of the tool to be detected through the size relationship between the ratio of the pixel statistical results corresponding to the tool to be detected and the pixel statistical results corresponding to the key tool feature area in the standard grayscale image and the corresponding threshold, thereby improving the detection accuracy of the tool fracture and further improving the convenience of detecting the tool fracture.

[0176] In yet another optional embodiment, the fracture detection module 404 determines the target position area of ​​the key feature of the tool to be detected in the original grayscale image according to the size relationship between the first quantity and the second quantity, and the specific manner includes:

[0177] A minimum number is determined from the first number and the second number, a key feature of the tool to be detected is determined according to the pixel points corresponding to the minimum number, and a target position area of ​​the key feature of the tool to be detected in the original grayscale image is identified.

[0178] Optionally, the specific manner in which the fracture detection module 404 identifies the target position area of ​​the key feature of the tool to be detected in the original grayscale image includes:

[0179] Binarize and segment the original grayscale image based on the target pixel threshold to obtain a binary image;

[0180] Perform edge extraction operation on the binary image to obtain edge extraction results;

[0181] Based on the edge extraction result, determine the vertical and horizontal coordinate values ​​corresponding to the edge of the binary image in the constructed coordinate system, the vertical and horizontal coordinate values ​​include the minimum horizontal coordinate, the maximum horizontal coordinate, the minimum vertical coordinate and the maximum vertical coordinate;

[0182] A corresponding rectangular area is drawn in the binary image based on the vertical and horizontal coordinate values, and the target position area of ​​the key feature of the tool to be detected in the original grayscale image is identified according to the rectangular area.

[0183] It can be seen that this optional embodiment realizes the automatic segmentation of the key area (that is, the target position area of ​​the key features of the tool to be detected in the original grayscale image) and automatically retains the best feature area for corresponding pixel statistical operations, instead of requiring the operator to manually make a mask to block the non-feature area. This is not only beneficial to improving the recognition accuracy of the target position area of ​​the key features of the tool to be detected in the original grayscale image, but also beneficial to improving the recognition efficiency of the target position area of ​​the key features of the tool to be detected in the original grayscale image.

[0184] Embodiment 4

[0185] See also Figure 6 , Figure 6 1 is a schematic diagram of the structure of another intelligent identification device for tool fracture disclosed in an embodiment of the present invention. Figure 6 The device shown can be integrated into a tool breakage detection device, which can be a local device or a cloud device (such as a cloud server), which is not limited in the embodiments of the present invention. Figure 6 As shown, the device may include:

[0186] A memory 501 storing executable program codes;

[0187] a processor 502 coupled to the memory 501;

[0188] The processor 502 calls the executable program code stored in the memory 501 to execute part or all of the steps in any one of the intelligent identification methods for tool fracture conditions described in the first or second embodiment of the present invention.

[0189] Embodiment 5

[0190] An embodiment of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute part or all of the steps in any one of the intelligent identification methods for tool fracture conditions described in Embodiment 1 or Embodiment 2 of the present invention.

[0191] Embodiment 6

[0192] An embodiment of the present invention discloses a tool fracture detection device, which is used to execute part or all of the steps in any one of the intelligent identification implementation methods of tool fracture conditions described in embodiment 1 or embodiment 2 of the present invention; alternatively, the tool fracture detection device can be integrated with any one of the intelligent identification implementation devices of tool fracture conditions described in embodiment 3, and further, the tool fracture detection device can also be integrated with an image acquisition device for acquiring tool images.

[0193] The device embodiments described above are only illustrative, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, i.e., they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0194] Through the specific description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solution can be essentially or partly contributed to the prior art in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0195] Finally, it should be noted that the intelligent identification method and device for tool fracture conditions disclosed in the embodiments of the present invention only disclose the preferred embodiments of the present invention, which are only used to illustrate the technical scheme of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical schemes described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical schemes from the spirit and scope of the technical schemes of the embodiments of the present invention.

Claims

1. A method for intelligently identifying tool fracture conditions, characterized in that: The method comprises: After determining the target ROI region according to the tool image acquired by the image acquisition device, performing a grayscale conversion operation on the target ROI region to obtain an original grayscale image corresponding to the target ROI region; wherein the target ROI region is a region in the tool image that contains the tool to be detected; Performing a predetermined image processing operation on the original grayscale image to obtain a processed grayscale image; After extracting all edge contours of the processed grayscale image, determining a center point corresponding to each edge contour, and calculating an average center point of all the center points; A target pixel threshold is determined according to an area between the average center point and all edge points of the processed grayscale image; wherein the target pixel threshold is used as a basis for detecting the fracture condition of the tool to be detected.

2. The intelligent identification method for tool fracture according to claim 1 is characterized in that: The performing a predetermined image processing operation on the original grayscale image to obtain a processed grayscale image includes: Performing a first edge detection operation on the original grayscale image or performing a filtering operation and a first edge detection operation in sequence to obtain a first edge detection result of the original grayscale image; Performing a dilation operation on the first edge detection result of the original grayscale image to obtain an edge-dilated grayscale image as a processed grayscale image; Wherein, the method further comprises: After obtaining the grayscale image after edge dilation, a second edge detection operation is performed on the grayscale image after edge dilation to obtain a second edge detection result of the grayscale image after edge dilation; wherein the second edge detection result includes all the edge contours and all the edge points.

3. The intelligent identification method for tool fracture according to claim 2 is characterized in that: Determining the target pixel threshold according to the area between the average center point and all edge points of the processed grayscale image includes: Draw a straight line from each edge point in the second edge detection result to the average center point; Performing a binarization operation on all straight line regions and non-straight line regions in the grayscale image after edge dilation; Calculate the average pixel value of all pixels in all the straight line areas after binarization; A target pixel threshold is determined according to the average pixel value.

4. The intelligent identification method for tool fracture according to any one of claims 1 to 3, characterized in that: The method further comprises: Based on the target pixel threshold, a first number of pixel points in the original grayscale image whose pixel values ​​are lower than the target pixel threshold and a second number of pixel points whose pixel values ​​are not lower than the target pixel threshold are counted, and according to the size relationship between the first number and the second number, a target position area of ​​a key feature of a tool to be detected in the original grayscale image is determined from the original grayscale image; Based on the target pixel threshold and the target position area, the fracture condition of the tool to be detected is judged to obtain a fracture condition judgment result corresponding to the tool to be detected.

5. The intelligent identification method for tool fracture according to claim 4 is characterized in that: The step of judging the fracture condition of the tool to be detected based on the target pixel threshold and the position information to obtain a fracture condition judgment result corresponding to the tool to be detected includes: Based on the target pixel threshold, performing a pixel statistical operation on the target position area in the original grayscale image to obtain a first pixel statistical result; Based on the target pixel threshold, a pixel statistical operation is performed on a key tool feature area in a predetermined standard grayscale image to obtain a second pixel statistical result; It is determined whether the tool to be detected is fractured according to the first pixel statistical result and the second pixel statistical result, and a fracture judgment result corresponding to the tool to be detected is obtained.

6. The intelligent identification method for tool fracture according to claim 5 is characterized in that: The step of judging whether the tool to be detected is broken according to the first pixel statistical result and the second pixel statistical result, and obtaining a judgment result of the broken condition of the tool to be detected, comprises: Calculating a ratio of the first pixel statistical result to the second pixel statistical result, and determining whether the ratio is greater than or equal to a preset threshold; If the ratio is greater than or equal to the preset threshold, it is determined that the tool to be detected is broken; and / or, if the ratio is less than the preset threshold, it is determined that the tool to be detected is not broken.

7. The intelligent identification method for tool fracture according to claim 4 is characterized in that: The step of determining, from the original grayscale image, a target location region of a key feature of the tool to be detected in the original grayscale image according to the size relationship between the first quantity and the second quantity includes: Determine a minimum number from the first number and the second number, determine the key feature of the tool to be detected according to the pixel points corresponding to the minimum number, and identify the target position area of ​​the key feature of the tool to be detected in the original grayscale image; Wherein, the identifying of the target position area of ​​the key feature of the tool to be detected in the original grayscale image includes: Performing binary segmentation on the original grayscale image based on the target pixel threshold to obtain a binary image; Performing an edge extraction operation on the binary image to obtain an edge extraction result; Based on the edge extraction result, determine the vertical and horizontal coordinate values ​​corresponding to the edge of the binary image in the constructed coordinate system, wherein the vertical and horizontal coordinate values ​​include a minimum horizontal coordinate, a maximum horizontal coordinate, a minimum vertical coordinate and a maximum vertical coordinate; A corresponding rectangular area is drawn in the binary image based on the vertical and horizontal coordinate values, and a target position area of ​​the key feature of the tool to be detected in the original grayscale image is identified according to the rectangular area.

8. An intelligent identification device for tool fracture, characterized in that: The device comprises: A grayscale conversion module is used to perform a grayscale conversion operation on the target ROI area after determining the target ROI area according to the tool image acquired by the image acquisition device, so as to obtain an original grayscale image corresponding to the target ROI area; wherein the target ROI area is the area in the tool image that contains the tool to be detected; An image processing module, used for performing a predetermined image processing operation on the original grayscale image to obtain a processed grayscale image; A threshold determination module is used to determine the center point corresponding to each edge contour after extracting all edge contours of the processed grayscale image, calculate the average center point of all the center points, and determine the target pixel threshold based on the area between the average center point and all edge points of the processed grayscale image; wherein the target pixel threshold is used as a basis for detecting the fracture condition of the tool to be detected.

9. An intelligent identification device for tool fracture, characterized in that: The device comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the intelligent identification method for tool fracture conditions as described in any one of claims 1-7.

10. A computer storage medium, characterized in that: The computer storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the intelligent identification implementation method of the tool fracture condition as described in any one of claims 1-7.

Images