A root canal file cutting detection device and variable taper visual detection method

Abstract

The present invention relates to a root canal file blanking detection device and a variable taper visual detection method, comprising: obtaining root canal file images at different positions in the root canal file; extracting the edge contour of the root canal file image; splicing the edge contours corresponding to the root canal file images at different positions in the root canal file to obtain a complete root canal file edge contour curve; performing extreme value detection on the root canal file edge contour curve to obtain extreme value points; calculating the taper between adjacent extreme value points, and judging whether the root canal file is qualified according to the taper calculation result. The beneficial effect of the present invention is that the present invention can maintain a high contour extraction accuracy under the condition of high signal-to-noise ratio by obtaining images at different positions in the root canal file and extracting image contour information using the scanning pixel mean difference method. This method overcomes the problem of insufficient contour extraction accuracy in traditional detection methods.

Description

Technical Field

[0001] The invention relates to the technical field of root canal files, and more specifically, to a root canal file blanking detection device and a variable taper visual detection method. Background Art

[0002] As an indispensable tool for root canal treatment, the stability of the performance and quality of root canal files is directly related to the treatment effect and patient comfort. However, the current detection technology for root canal files in the market mainly focuses on basic parameters such as length, coaxiality, and pitch.

[0003] With the development of processing technology, new root canal files are gradually being widely adopted for the demand of high flexibility and high strength mechanical properties. Unlike traditional root canal files, their key dimensional parameters such as taper and pitch change with the axial direction. Existing inspection tools are insufficient in the inspection of the key feature of new root canal files, namely the variable taper parameters.

[0004] Traditional detection technologies, such as using ordinary panoramic cameras for image recognition, often have difficulty accurately capturing and measuring subtle changes in the axial direction of root canal files due to the limited field of view and insufficient precision of the camera, resulting in the detection results being unable to truly reflect the actual performance of the root canal files. On the other hand, although the use of wide-angle and high-precision cameras can improve the accuracy of image recognition to a certain extent, their high cost has become a huge obstacle to widespread application. Summary of the invention

[0005] The purpose of the present invention is to address the deficiencies of the prior art and to provide a root canal file blanking detection device and a variable taper visual detection method.

[0006] In a first aspect, a method for visually detecting the taper of a root canal file is provided, comprising:

[0007] S1, obtaining images of root canal files at different positions in the root canal file;

[0008] S2, scanning pixels of the root canal file image to extract edge contours of the root canal file image;

[0009] S3, splicing the edge contours corresponding to the root canal file images at different positions in the root canal file to obtain a complete root canal file edge contour curve;

[0010] S4, performing extreme value detection on the edge contour curve of the root canal file to obtain extreme value points;

[0011] S5. Calculate the taper between adjacent extreme value points, and determine whether the root canal file is qualified based on the taper calculation result.

[0012] Preferably, S2 comprises:

[0013] S201, performing grayscale conversion on the root canal file image, and scanning the target pixel in the root canal file image after the grayscale conversion along the x direction and the y direction, obtaining the distribution of a number of pixels around the target pixel, and respectively extracting the average difference of the scanned pixels of the target pixel along the x direction and the y direction;

[0014] S202, obtaining a square pixel mean difference according to the scanned pixel mean differences of the target pixel along the x direction and the y direction;

[0015] S203, obtaining a maximum point of the square pixel mean difference according to the square pixel mean difference; screening the maximum point of the square pixel mean difference to obtain an edge contour point;

[0016] S204: Determine an edge contour corresponding to the root canal file image according to the edge contour points.

[0017] Preferably, S3 includes:

[0018] S301, storing edge contours corresponding to root canal file images at adjacent positions by using an 8-field chain code;

[0019] S302, obtaining an optimal matching position according to the matching similarity, and splicing root canal file images at adjacent positions through the optimal matching position;

[0020] S303, repeat S301-S302 until all root canal file images are spliced ​​together to obtain a complete root canal file edge contour curve.

[0021] Preferably, S4 includes:

[0022] S401, performing least square method on the edge contour curve of the root canal file to obtain the minimum inertia axis;

[0023] S402, performing affine transformation on the edge contour curve of the root canal file and the minimum inertia axis according to the slope of the minimum inertia axis to obtain a horizontal minimum inertia axis and edge contour point set;

[0024] S403, dividing the edge contour curve of the root canal file into an upper contour curve and a lower contour curve according to the horizontal minimum inertia axis;

[0025] S404, performing minimum value detection on the upper contour curve and maximum value detection on the lower contour curve to obtain extreme value points.

[0026] Preferably, S5 includes:

[0027] S501, calculating the minimum circumscribed circle radius and the root canal file pitch according to the extreme point;

[0028] S502, calculating the taper between adjacent extreme points according to the minimum circumscribed circle radius and the root canal file pitch;

[0029] S503: Compare the taper between adjacent extreme value points with the root canal file generation process standard to determine whether the root canal file is qualified.

[0030] In a second aspect, a root canal file taper visual detection system is provided, which is used to perform any root canal file taper visual detection method described in the first aspect, comprising:

[0031] An acquisition module, used for acquiring images of the root canal file at different positions in the root canal file;

[0032] A scanning module, used for scanning pixels of the root canal file image and extracting edge contours of the root canal file image;

[0033] A splicing module, used for splicing edge contours corresponding to root canal file images at different positions in the root canal file to obtain a complete root canal file edge contour curve;

[0034] A detection module, used for performing extreme value detection on the edge contour curve of the root canal file to obtain extreme value points;

[0035] The calculation module is used to calculate the taper between adjacent extreme value points and judge whether the root canal file is qualified according to the taper calculation result.

[0036] In a third aspect, a computer storage medium is provided, wherein a computer program is stored in the computer storage medium; when the computer program is executed on a computer, the computer executes the method for visually detecting the tapered degree of a root canal file as described in any one of the first aspects.

[0037] In a fourth aspect, a root canal file blanking detection device is provided, which is used to perform any of the root canal file taper visual detection methods described in the first aspect, comprising: a device base, a backlight source, an image acquisition device, a root canal file clamping jaw, a clamping jaw power mechanism, a connecting plate and a two-dimensional moving mechanism;

[0038] Wherein, the root canal file clamping jaw, the clamping jaw power mechanism, and the connecting plate are arranged on the two-dimensional moving mechanism; the root canal file clamping jaw is connected to the clamping jaw power mechanism through the connecting plate; the root canal file clamping jaw is used to grasp the handle of the root canal file;

[0039] The backlight source and the two-dimensional moving mechanism are arranged on the base of the device; the image acquisition device faces the backlight source; the two-dimensional moving mechanism is used to drive the root canal file to move in the visual detection area; the visual detection area is the area between the backlight source and the image acquisition device; the image acquired by the image acquisition device is transmitted to the root canal file taper visual detection system described in the second aspect for processing.

[0040] The beneficial effects of the present invention are:

[0041] 1. The present invention obtains images of different positions in the root canal file and uses the scanning pixel mean difference method to extract image contour information, which can maintain a high contour extraction accuracy under the condition of high signal-to-noise ratio. This method overcomes the problem of insufficient contour extraction accuracy in traditional detection methods.

[0042] 2. The method of local image stitching using chain code matching in the present invention significantly shortens the calculation time compared with the general image stitching method. At the same time, compared with panoramic image acquisition, it has higher pixel accuracy and avoids the distortion problem caused by panoramic shooting. The detection result of root canal file is more accurate.

[0043] 3. The present invention adopts a fully automatic material feeding and non-contact visual inspection method. Compared with the traditional manual inspection method, it greatly shortens the inspection time, avoids the risk of scratches caused by manual operation, and reduces the wear and contamination problems caused by contact inspection, thereby extending the service life of the root canal file. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 A schematic diagram of a visual inspection system flow chart provided by an embodiment of the present invention;

[0045] Figure 2 A schematic structural diagram of a root canal file feeding detection device provided by an embodiment of the present invention;

[0046] Figure 3 A schematic diagram of edge contour extraction by scanning pixel mean difference provided in an embodiment of the present invention;

[0047] Figure 4 A schematic diagram of the 8-field chain code provided by an embodiment of the present invention;

[0048] Figure 5 A chain code demonstration diagram extracted from the actual profile provided by the embodiment of the present invention;

[0049] Figure 6 A schematic diagram of size parameters of a root canal file provided in an embodiment of the present invention;

[0050] Figure 7 A schematic diagram of extracting pixel mean differences in upper six directions provided by an embodiment of the present invention;

[0051] Figure 8 A graph of pixel mean difference extracted from six directions on a backlight image of a root canal file provided by an embodiment of the present invention;

[0052] Fig. 9 A graph of pixel mean difference and grayscale value in the fourth direction provided by an embodiment of the present invention;

[0053] Fig.10 A schematic diagram of the structure of a visual detection system for root canal file taper provided by an embodiment of the present invention;

[0054] Explanation of the reference numerals: device base 1 , backlight source 2 , image acquisition device 3 , root canal file clamping jaw 4 , clamping jaw power mechanism 5 , connecting plate 6 , two-dimensional moving mechanism 7 . DETAILED DESCRIPTION

[0055] The present invention is further described below in conjunction with embodiments. The description of the following embodiments is only used to help understand the present invention. It should be noted that for ordinary persons in the art, without departing from the principle of the present invention, the present invention can also be modified in some ways, and these improvements and modifications also fall within the scope of protection of the claims of the present invention.

[0056] Embodiment 1:

[0057] like Figure 1 As shown, Embodiment 1 of the present application provides a method for visually detecting the taper of a root canal file, comprising:

[0058] S1. Acquire images of the root canal file at different positions in the root canal file.

[0059] In an optional implementation, local root canal file images at different positions are obtained by video frame extraction. For example, the pixel distribution of the received image is monitored in the visual detection area. When the pixel distribution is disturbed, it means that the moving root canal file has entered the visual detection area, and the root canal file image signal is collected in a video manner until the pixel distribution stops being disturbed. Then, the obtained root canal file video is frame extracted to obtain images of the root canal file at different positions, and they are processed respectively.

[0060] S2. Scan pixels of the root canal file image to extract edge contours of the root canal file image.

[0061] S2 includes:

[0062] S201, performing grayscale conversion on the root canal file image, and scanning a target pixel in the root canal file image after the grayscale conversion along the x direction and the y direction, obtaining the distribution of a number of pixels around the target pixel, and respectively extracting the average difference of the scanned pixels of the target pixel along the x direction and the y direction.

[0063] In S201, the target pixel is any pixel in the root canal file image, and the expression formula of the average difference of the scanning pixels of the target pixel along the x direction and the y direction is:

[0064]

[0065]

[0066] in, for Direction pixel search window, is the pixel search window in the y direction, For along The average pixel difference extracted by scanning in the direction, is the average pixel difference extracted by scanning along the y direction, is in the image coordinate system The pixel value of .

[0067] like Figure 7 As shown in the figure, the pixel mean difference is extracted in the six y directions of the local image of the root canal file, as shown in Figure 8 Six one-dimensional mean difference curves can be obtained. Figure 8 In the above example, X (pixels) and Y (pixels) represent the number of pixels in the x and y directions respectively. Figure 7 The pixel mean difference and pixel value extraction in the fourth direction are as follows: Fig. 9 The position where the pixel value changes sharply corresponds to the peak position of the pixel mean difference. Compared with contour extraction methods such as Sobel and Canny, the scanning pixel mean difference method transforms the extraction of image edge contours from the retrieval of pixel gradients to the retrieval of pixel mean difference extreme values. By considering the influence of several pixel values ​​near the target pixel, it avoids identifying noise points as edge contours, thereby improving the contour extraction accuracy of the image under certain noise conditions.

[0068] S202, such as Figure 3 As shown, the square pixel mean difference is obtained according to the scanned pixel mean difference of the target pixel along the x direction and the y direction.

[0069] In S201, the expression formula of square pixel mean difference is:

[0070]

[0071] S203, obtaining a maximum point of the square pixel mean difference according to the square pixel mean difference; and screening the maximum point of the square pixel mean difference to obtain an edge contour point.

[0072] In S203, the screening criteria are:

[0073]

[0074] in, is the maximum value of the mean difference of square pixels, To determine the pixel mean difference threshold of edge points, is the edge contour point.

[0075] S204: Determine an edge contour corresponding to the root canal file image according to the edge contour points.

[0076] S3. splicing edge contours corresponding to root canal file images at different positions in the root canal file to obtain a complete root canal file edge contour curve.

[0077] S3 includes:

[0078] S301. Store edge contours corresponding to root canal file images at adjacent positions by using 8-field chain codes.

[0079] The edge contour obtained in S2 is Figure 4 Store it as a one-dimensional sequence as an 8-domain chain code. Figure 5 The conversion relationship between root canal file profile and chain code is demonstrated.

[0080] S302: Obtain an optimal matching position according to the matching similarity, and splice root canal file images at adjacent positions through the optimal matching position.

[0081] The calculation formula for matching similarity is:

[0082]

[0083] in, To match similarity, The best match is when and is the sequence of chain codes in the two contour matching windows to be spliced, To start sampling from the end of the previous contour chain sequence, Sampling starts from the first chain code of the back contour chain code sequence.

[0084] S303, repeat S301-S302 until all root canal file images are spliced ​​together to obtain a complete root canal file edge contour curve.

[0085] Specifically, after finding the optimal matching position, the chain code sequence is spliced ​​at the position, and the coordinate positions of all edge contour points are inferred based on the coordinates of the first point in the sequence, where the first point in the sequence is the first point of the contour chain code sequence in the previous image. All images are spliced ​​according to this method to obtain the complete edge contour of the root canal file.

[0086] S4. Perform extreme value detection on the edge contour curve of the root canal file to obtain extreme value points.

[0087] S4 includes:

[0088] S401, performing least square method on the edge contour curve of the root canal file to obtain the minimum inertia axis.

[0089] In S401, the contour of the root canal file is analyzed, and the center axis of the root canal file is approximated by the minimum inertia axis. The distribution of the contour points of the root canal file is further analyzed, and the minimum inertia axis is obtained by the least square method for the spliced ​​contour. The fitting target is:

[0090]

[0091] in, , , , to define the axis of minimum inertia The coefficient of , are the edge argument location parameters, is the set of all points of the edge contour.

[0092] S402: performing affine transformation on the edge contour curve of the root canal file and the minimum inertia axis according to the slope of the minimum inertia axis to obtain a horizontal minimum inertia axis and an edge contour point set.

[0093] Specifically, according to the slope of the inertia axis , the edge contour of the root canal file and the generated axis of minimum inertia Perform an affine transformation, and the minimum inertia axis after the transformation is Make the axis of minimum inertia horizontal and the edge contour point set , the transformation relationship is:

[0094]

[0095] S403: Divide the edge contour curve of the root canal file into an upper contour curve and a lower contour curve according to the horizontal minimum inertia axis.

[0096] S404, performing minimum value detection on the upper contour curve and maximum value detection on the lower contour curve to obtain extreme value points.

[0097] Specifically, the contour curve obtained by connecting the edge contour points is subjected to extreme value detection, and the point where the contour line is farthest from the local axis of minimum inertia is defaulted as the point where the radial distance of the spiral cutting edge of the root canal file is the largest, which is represented as a point on the circumscribed circle of the cross section in the axial direction. The minimum value of the contour curve is detected for the upper contour line, and the maximum value is detected for the lower contour point.

[0098] S5. Calculate the taper between adjacent extreme value points, and determine whether the root canal file is qualified based on the taper calculation result.

[0099] S5 includes:

[0100] S501. Calculate the minimum circumscribed circle radius and the root canal file pitch according to the extreme point.

[0101] like Figure 6 As shown, the distance from the extreme point to the minimum inertia axis after affine transformation represents the radius of the circumscribed circle of the cross-sectional shape of the root canal file in the current axial direction:

[0102]

[0103] in is the ordinate of the nth extreme point, It is the physical size corresponding to one pixel size after calibration.

[0104] like Figure 6 The root canal file pitch extracted from the edge contour in the direction shown is:

[0105]

[0106] in, is the horizontal coordinate of the nth extreme point.

[0107] S502: Calculate the taper between adjacent extreme points according to the minimum circumscribed circle radius and the root canal file pitch.

[0108] The taper between each pitch is set by default to the taper value at half of the distance between adjacent extreme points. Finally, the taper generatrix fitting function and taper variation function of the variable-taper root canal file are obtained based on the size parameters measured by the above method. The taper formula between adjacent extreme points is:

[0109]

[0110] S503: Compare the taper between adjacent extreme value points with the root canal file generation process standard to determine whether the root canal file is qualified.

[0111] Specifically, the extreme point positions of the same root canal file may be different during detection. The variable-taper root canal file light cone generatrix fitting function and taper change function obtained by fitting the measured extreme point parameters can obtain the axial change trends of key parameters such as taper, minimum circumscribed circle diameter, and pitch, which can be compared with the processing parameter standards to determine whether the root canal file processing is qualified.

[0112] Embodiment 2:

[0113] Based on Example 1, Example 2 of the present application provides a root canal file taper visual detection system, such as Fig.10 As shown, including:

[0114] An acquisition module, used for acquiring images of the root canal file at different positions in the root canal file;

[0115] A scanning module, used for scanning pixels of the root canal file image and extracting edge contours of the root canal file image;

[0116] A splicing module, used for splicing edge contours corresponding to root canal file images at different positions in the root canal file to obtain a complete root canal file edge contour curve;

[0117] A detection module, used for performing extreme value detection on the edge contour curve of the root canal file to obtain extreme value points;

[0118] The calculation module is used to calculate the taper between adjacent extreme value points and judge whether the root canal file is qualified according to the taper calculation result.

[0119] Specifically, the root canal file taper visual detection system provided in this embodiment is a system corresponding to the method provided in Example 1. Therefore, the parts in this embodiment that are the same or similar to those in Example 1 can be referenced to each other and will not be repeated in this application.

[0120] Embodiment 3:

[0121] On the basis of embodiments 1 and 2, embodiment 3 of the present application provides a root canal file feeding detection device, such as Figure 2 As shown, it includes: a device base 1, a backlight source 2, an image acquisition device 3, a root canal file clamping jaw 4, a clamping jaw power mechanism 5, a connecting plate 6 and a two-dimensional moving mechanism 7.

[0122] Specifically, the device base 1 is made of aluminum alloy with a thickness of 8 mm, and a 4 mm threaded hole is designed thereon for mounting the two-dimensional moving mechanism 7 and the backlight source 2. In addition, the device base 1 is mounted on the outer ring of the root canal file grinder to facilitate the transfer of the root canal file after cutting and subsequent screening.

[0123] The two-dimensional moving mechanism 7 can smoothly move in the processing area and the detection area of ​​the root canal file grinder. The root canal file clamping jaw 4 realizes the closing and relaxation of the clamping jaw under the action of the clamping jaw power mechanism 5. The two-dimensional moving mechanism 7 and the clamping jaw power mechanism 5 are pneumatic, and the driving air pressure of the two-dimensional moving mechanism 7 is 0.5-0.8MPa, and the driving air pressure of the clamping jaw power mechanism 5 is 0.3-0.6MPa.

[0124] The connecting plate 6 is used to connect the two-dimensional moving mechanism 7 and the clamping claw power mechanism 5. The backlight source 2 can provide a stable and uniform light source, so that the image acquisition device 3 can acquire an effective backlight image of the root canal file and cooperate with the automatic visual detection module to complete accurate visual detection. The light source intensity requirement of the backlight source 2 is set to ensure that the contour contrast of the root canal file under the backlight is guaranteed, and the reflection of the spiral groove on the backlight is avoided, resulting in a highlight area in the foreground of the acquired backlight image. For the root canal file entering the visual detection area, the image acquisition device 3 continuously acquires images of it to obtain a video signal at a rate of 60p, from which a local image is obtained.

[0125] The method for executing the feeding movement of the root canal file feeding detection device is as follows:

[0126] Step 1: The host computer receives a signal indicating that the root canal file processing is completed, and sends a material unloading signal to the two-dimensional moving mechanism 7, and the initial position of the two-dimensional moving mechanism 7 is in the visual detection area.

[0127] Step 2: The two-dimensional moving mechanism 7 pushes the clamping device to the root canal file processing area, and under the action of the clamping jaw power mechanism 5, the root canal file clamping jaw 4 closes and holds the root canal file handle.

[0128] Step 3: The two-dimensional moving mechanism 7 returns to the visual inspection area and starts image acquisition.

[0129] Step 4: After the test is completed, the root canal file jaws 4 are relaxed to allow the root canal file to fall into the conveyor belt and enter the next screening step. The measured parameters are compared with the root canal file processing technology standards, and the accuracy error of 5% is used as the screening standard.

[0130] The detection objects of the present invention include: medical dental tools with conical spiral cutting edges, such as traditional stainless steel root canal files and new nickel-titanium root canal files.

Claims

1. A method for visually detecting the taper of a root canal file, characterized in that: include: S1, obtaining images of root canal files at different positions in the root canal file; S2, scanning pixels of the root canal file image to extract edge contours of the root canal file image; S2 includes: S201, performing grayscale conversion on the root canal file image, and scanning the target pixel in the root canal file image after the grayscale conversion along the x direction and the y direction, obtaining the distribution of a number of pixels around the target pixel, and respectively extracting the average difference of the scanned pixels of the target pixel along the x direction and the y direction; S202, obtaining a square pixel mean difference according to the scanned pixel mean differences of the target pixel along the x direction and the y direction; S203, obtaining a maximum point of the square pixel mean difference according to the square pixel mean difference; screening the maximum point of the square pixel mean difference to obtain an edge contour point; S204, determining an edge contour corresponding to the root canal file image according to the edge contour point; S3, splicing the edge contours corresponding to the root canal file images at different positions in the root canal file to obtain a complete root canal file edge contour curve; S4, performing extreme value detection on the edge contour curve of the root canal file to obtain extreme value points; S4 includes: S401, performing least square method on the edge contour curve of the root canal file to obtain the minimum inertia axis; S402, performing affine transformation on the edge contour curve of the root canal file and the minimum inertia axis according to the slope of the minimum inertia axis to obtain a horizontal minimum inertia axis and edge contour point set; S403, dividing the edge contour curve of the root canal file into an upper contour curve and a lower contour curve according to the horizontal minimum inertia axis; S404, performing minimum value detection on the upper contour curve and maximum value detection on the lower contour curve to obtain extreme value points; S5. Calculate the taper between adjacent extreme value points, and determine whether the root canal file is qualified based on the taper calculation result.

2. The method for visually detecting the taper of a root canal file according to claim 1, wherein S3 include: S301, storing edge contours corresponding to root canal file images at adjacent positions by using an 8-field chain code; S302, obtaining an optimal matching position according to the matching similarity, and splicing root canal file images at adjacent positions through the optimal matching position; S303, repeat S301-S302 until all root canal file images are spliced ​​together to obtain a complete root canal file edge contour curve.

3. The method for visually detecting the taper of a root canal file according to claim 2, wherein S5 include: S501, calculating the minimum circumscribed circle radius and the root canal file pitch according to the extreme point; S502, calculating the taper between adjacent extreme points according to the minimum circumscribed circle radius and the root canal file pitch; S503: Compare the taper between adjacent extreme value points with the root canal file generation process standard to determine whether the root canal file is qualified.

4. A root canal file taper visual detection system, characterized in that: The method for visually detecting the tapered degree of a root canal file according to any one of claims 1 to 3 comprises: An acquisition module, used for acquiring images of the root canal file at different positions in the root canal file; A scanning module, used for scanning pixels of the root canal file image and extracting edge contours of the root canal file image; A splicing module, used for splicing edge contours corresponding to root canal file images at different positions in the root canal file to obtain a complete root canal file edge contour curve; A detection module, used for performing extreme value detection on the edge contour curve of the root canal file to obtain extreme value points; The calculation module is used to calculate the taper between adjacent extreme value points and judge whether the root canal file is qualified according to the taper calculation result.

5. A computer storage medium, characterized in that: The computer storage medium stores a computer program; when the computer program is executed on a computer, the computer executes the method for visually detecting the tapered degree of a root canal file according to any one of claims 1 to 3.

Images