CN118115398B - Image feature enhancement method and system for machining tool - Google Patents
Image feature enhancement method and system for machining tool Download PDFInfo
- Publication number
- CN118115398B CN118115398B CN202410486798.9A CN202410486798A CN118115398B CN 118115398 B CN118115398 B CN 118115398B CN 202410486798 A CN202410486798 A CN 202410486798A CN 118115398 B CN118115398 B CN 118115398B
- Authority
- CN
- China
- Prior art keywords
- points
- point
- edge
- spiral
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 63
- 238000003754 machining Methods 0.000 title claims description 23
- 230000002708 enhancing effect Effects 0.000 claims abstract description 16
- 239000006185 dispersion Substances 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 230000006870 function Effects 0.000 claims description 7
- 238000003064 k means clustering Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 11
- 238000005286 illumination Methods 0.000 description 10
- 238000003708 edge detection Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 241001391944 Commicarpus scandens Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20172—Image enhancement details
- G06T2207/20192—Edge enhancement; Edge preservation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of image processing, in particular to an image characteristic enhancement method and system of a processing cutter, comprising the following steps: collecting a cutter image; acquiring a plurality of edges in a cutter image, and acquiring local pixel points of edge pixel points in the edges; acquiring a target point according to the curvature of the edge pixel points and the curvature of local pixel points of the edge pixel points; acquiring a reference distance and a slot length distance of the target point according to the distances between different target points; acquiring a third spiral factor of the target point according to the reference distance of the target point, the first spiral factor of the target point and the groove length distance; pixel points on the edge of the spiral groove according to a third spiral factor of the target point; and enhancing the pixel points on the edges of the spiral grooves. According to the method, firstly, the pixel points on the edge of the spiral groove in the cutter image are accurately obtained, then the contrast of the pixel points on the edge of the spiral groove in the cutter image is improved, and the image characteristic enhancement effect of the cutter image is improved.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to an image feature enhancement method and system for a processing cutter.
Background
Because the edges of the spiral grooves in the drill bit are important characteristics of the drill bit, the edges of the spiral grooves in the drill bit need to be enhanced in order to better detect the drill bit; however, the spiral groove exists in the structure of the drill bit, so that the illumination intensity received by different positions of the surface of the drill bit is different, and the edge pixel points which are obtained by the traditional method are caused by illumination influence, so that the enhancement effect of enhancing all the edge pixel points is not good, and the detection effect of the drill bit is poor.
Disclosure of Invention
The invention provides an image feature enhancement method and system for a processing cutter, which are used for solving the existing problems: the enhancement effect of directly enhancing all edge pixel points in the image is poor, so that the detection effect of the drill bit is poor.
The invention relates to an image characteristic enhancement method and system for a processing cutter, which adopts the following technical scheme:
An embodiment of the present invention provides an image feature enhancement method of a machining tool, the method including the steps of:
Collecting a cutter image;
Acquiring a plurality of edges in a cutter image, and acquiring local pixel points of edge pixel points in the edges; obtaining local intersection points of the edge pixel points and the discrete degree of the local intersection points according to the curvature of the edge pixel points and the local pixel points of the edge pixel points; according to the discrete degree of the local intersection point, combining the gray values of the edge pixel points to obtain a first spiral factor of the edge pixel points; acquiring a target point according to a first spiral factor of the edge pixel point;
Acquiring a reference distance and a slot length distance of the target point according to the distances between different target points; acquiring a second spiral factor of the target point according to the reference distance of the target point, the first spiral factor of the target point and the groove length distance; acquiring a third spiral factor of the target point according to the second spiral factor of the target point and the second spiral factor of the local pixel point of the target point; obtaining pixel points on the edge of the spiral groove according to a third spiral factor of the target point;
And enhancing the pixel points on the edges of the spiral grooves.
Preferably, the method for acquiring a plurality of edges in the cutter image and acquiring local pixel points of edge pixel points in the edges includes the following specific steps:
Acquiring a plurality of edges in a cutter image, and presetting the number of local pixel points ; For the first on any one edgeEdge pixel point to be distant from the firstThe nearest edge pixel pointThe edge pixel points are marked as the firstLocal pixel points of the edge pixel points.
Preferably, the obtaining the local intersection point of the edge pixel point and the discrete degree of the local intersection point according to the curvature of the edge pixel point and the local pixel point of the edge pixel point includes the following specific methods:
Acquisition of the first Normal of each edge pixel pointThe normal line of the local pixel points of the edge pixel points is the vertical line of the tangent line of the pixel point; acquisition of the firstNormal of each edge pixel pointThe intersection point between the normals of the local pixel points of the edge pixel points is recorded as the firstLocal intersection points of the edge pixel points are obtainedThe discrete degree of the local intersection point of each edge pixel point is specifically calculated according to the following formula:
In the method, in the process of the invention, Represent the firstThe degree of dispersion of the local intersection points of the edge pixel points; Represent the first The number of local intersections of the edge pixels; Represent the first The first edge pixel pointThe lateral position of the local intersection points in the tool image; Represent the first The first edge pixel pointLongitudinal positions of the local intersection points in the tool image; Represent the first The average value of the transverse positions of all local intersection points of the edge pixel points in the cutter image; Represent the first The longitudinal position average of all local intersection points of the edge pixel points in the cutter image.
Preferably, the obtaining the first spiral factor of the edge pixel point according to the discrete degree of the local intersection point and combining the gray value of the edge pixel point comprises the following specific methods:
For the first Edge pixel points according to the firstEdge pixel points and the firstGray value of local pixel point of each edge pixel point and the firstThe degree of dispersion of the local intersection points of the edge pixel points is obtainedThe specific calculation formula of the first probability factor that each edge pixel point is a spiral groove edge is as follows:
In the method, in the process of the invention, Represent the firstA first spiral factor for each edge pixel; Represent the first The degree of dispersion of the local intersection points of the edge pixel points; representing the number of preset local pixel points; Represent the first Gray values of the edge pixels; Represent the first Of edge pixelsGray values of the local pixel points; Representing an absolute value operation; Representing a maximum minimum normalization function; An exponential function based on a natural constant is represented.
Preferably, the specific method for obtaining the target point according to the first spiral factor of the edge pixel point includes:
Presetting a first probability factor threshold For the firstThe first pixel point isThe first spiral factor of each edge pixel point is greater than or equal toWill be the firstThe edge pixels are noted as target points.
Preferably, the method for obtaining the reference distance and the slot length distance of the target point according to the distance between different target points includes the following specific steps:
For the first Target points, in the vertical direction and the firstThe nearest target point of the target points is marked as the firstReference points of the target points, will beTarget point numberThe distance between the datum points of the target points is recorded as the firstReference distances of the target points; and obtaining the reference distances of all the target points, and recording the numbers in the reference distances of all the target points as the slot length distances.
Preferably, the method for obtaining the second spiral factor of the target point according to the reference distance of the target point, the first spiral factor of the target point and the slot length distance includes the following specific steps:
For the first The target points are combined according to the reference distance and the groove length distance of all the target pointsA first spiral factor of each target point is obtainedThe specific calculation formula of the second spiral factor of each target point is as follows:
In the method, in the process of the invention, Represent the firstA second helix factor for each target point; Represent the first A first helix factor for each target point; Represent the first Reference distances of the target points; Representing the groove length distance; Representing an absolute value operation.
Preferably, the obtaining the third spiral factor of the target point according to the second spiral factor of the target point and the second spiral factor of the local pixel point of the target point includes the specific steps:
For the first Target point, according toSecond spiral factor of each target point and the firstThe second spiral factor of the local pixel point of each target point is obtained, and the third spiral factor of the target point is obtained, wherein the specific calculation formula is as follows:
In the method, in the process of the invention, Represent the firstA third helix factor for each target point; Represent the first First of target pointsA second spiral factor for each local pixel; representing the number of preset local pixel points; Represent the first A second helix factor for each target point; Representing an absolute value operation.
Preferably, the obtaining the pixel point on the edge of the spiral groove according to the third spiral factor of the target point includes the following specific steps:
Using k-means clustering algorithm and making k-means clustering algorithm And clustering the third spiral factors of all the target points to obtain two clusters, wherein the target point in the cluster with the largest average value of the third spiral factors of all the target points in the cluster is used as the pixel point on the edge of the spiral groove.
Another embodiment of the present invention provides an image feature enhancement system for a machining tool, including a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor implementing the steps of any one of the above-mentioned image feature enhancement methods for a machining tool when executing the computer program.
The technical scheme of the application has the beneficial effects that: the application collects the cutter image; acquiring a plurality of edges in a cutter image, and acquiring local pixel points of edge pixel points in the edges; acquiring target points according to curvatures of edge pixel points and local pixel points of the edge pixel points, primarily screening all the edge pixel points by analyzing shape characteristics of the edges of the spiral grooves, and preparing data for subsequently acquiring the pixel points on the edges of the spiral grooves; acquiring a reference distance and a slot length distance of the target point according to the distances between different target points; acquiring a third spiral factor of the target point according to the reference distance of the target point, the first spiral factor of the target point and the groove length distance; according to the pixel points on the edge of the spiral groove of the third spiral factor of the target point, the distances between different spiral groove edges in the drill bit are always equal and the pixel points on the edge of the spiral groove are always continuous, so that the pixel points on the edge of the spiral groove can be accurately acquired based on the distances; and the pixel points on the edge of the spiral groove are enhanced, so that the image characteristic enhancement effect of the cutter image is finally improved, and the detection effect of the drill bit is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of steps of a method for enhancing image features of a machining tool according to the present invention;
fig. 2 is a schematic view of a machining tool image of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following detailed description refers to the specific implementation, structure, characteristics and effects of the image feature enhancement method and system for the processing tool according to the invention in combination with the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of an image feature enhancement method and system for a processing tool provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a method for enhancing image features of a processing tool according to an embodiment of the invention is shown, the method includes the following steps:
step S001: and acquiring a cutter image.
It should be noted that, since the machining tool directly affects the quality and accuracy of the machined part. If the machining tool has defects or is unqualified, the problems of rough surface, inaccurate size, cracks and the like of the machined part can be caused, the product quality is influenced, the qualified machining tool can ensure the good cutting performance of the tool, the friction resistance and the energy loss in the machining process are reduced, the machining efficiency is improved, the energy consumption is reduced, and meanwhile, the unqualified machining tool is easy to break and has potential safety hazards, so that the machining tool needs to be detected. The drill bit is used as a processing cutter of a special piece, and the drill bit needs to be detected, namely, the surface image of the drill bit needs to be acquired first.
Specifically, the drill bit is made to be perpendicular to the horizontal plane, the industrial camera collects the surface of the drill bit in the horizontal direction, the surface image of the drill bit is subjected to gray-scale processing, and the image after the gray-scale processing is recorded as a cutter image, as shown in fig. 2.
So far, a tool image is obtained.
Step S002: acquiring a plurality of edges in a cutter image, and acquiring local pixel points of edge pixel points in the edges; obtaining local intersection points of the edge pixel points and the discrete degree of the local intersection points according to the curvature of the edge pixel points and the local pixel points of the edge pixel points; according to the discrete degree of the local intersection point, combining the gray values of the edge pixel points to obtain a first spiral factor of the edge pixel points; and acquiring a target point according to the first spiral factor of the edge pixel point.
It should be noted that the spiral groove edge in the drill bit is an important feature of the drill bit, so in order to better detect the drill bit, the spiral groove edge in the drill bit needs to be obtained; because the spiral groove exists in the structure of the drill, when the surface image of the drill is collected under normal conditions, the condition that the illumination intensity received by different positions of the surface of the drill is different occurs, so that the image quality of the cutter image obtained in the step S001 is poor.
Specifically, a canny edge detection operator is used to obtain a plurality of edges in the tool image, and the canny edge detection operator is used as a well-known prior art, so that a detailed description is omitted in this embodiment.
It should be noted that, because the canny edge detection operator obtains edges according to the gradient value of the pixel points, but because the illumination intensity received by different positions of the surface of the drill bit is different, the edges obtained by the canny edge detection operator include edges generated due to illumination influence, namely, the spiral groove edge pixel points and non-spiral groove edge pixel points exist in the edges in the cutter image; in order to be able to accurately reinforce the helical flute edges in the drill bit and to enhance the helical flute edges in the drill bit, it is therefore necessary to distinguish between helical flute edge pixels and non-helical flute edge pixels present in several edges in the cutter image.
It should be further noted that, since the helix angle in the drill bit is fixed, the curvature of each pixel point on the edge of the helical flute is close in a local area, so the possibility that each pixel point in a plurality of edges is the pixel point of the edge of the helical flute can be obtained.
Specifically, the number of local pixel points is preset，The specific value of (2) can be set by combining with the actual situation, the embodiment does not have hard requirement, in the embodiment, the method usesDescription is made; for the first on any one edgeEdge pixel point to be distant from the firstThe nearest edge pixel pointThe edge pixel points are marked as the firstLocal pixel points of the edge pixel points are obtainedNormal of each edge pixel pointThe normal line of the local pixel point of each edge pixel point is the perpendicular line of the tangent line of the pixel point, and the method for obtaining the normal line is a well-known prior art, so that redundant description is omitted in this embodiment; acquisition of the firstNormal of each edge pixel pointThe intersection point between the normals of the local pixel points of the edge pixel points is recorded as the firstLocal intersection points of the edge pixel points are obtainedThe discrete degree of the local intersection point of each edge pixel point is specifically calculated according to the following formula:
In the method, in the process of the invention, Represent the firstThe degree of dispersion of the local intersection points of the edge pixel points; Represent the first The number of local intersections of the edge pixels; Represent the first The first edge pixel pointThe lateral position of the local intersection points in the tool image; Represent the first The first edge pixel pointLongitudinal positions of the local intersection points in the tool image; Represent the first The average value of the transverse positions of all local intersection points of the edge pixel points in the cutter image; Represent the first The longitudinal position average of all local intersection points of the edge pixel points in the cutter image.
Note that, the firstThe more concentrated the local intersection points of the edge pixel points, the description of the firstCurvature and the first edge pixel pointThe more similar the curvature of the local pixel of the edge pixels is, and thereforeThe greater the value of (2)The greater the likelihood that each edge pixel is a spiral slot edge pixel.
It should be further noted that, since the edge of the spiral groove in the drill bit is located at the outermost side of the drill bit, there is no light shielding situation, i.e. the gray values of the pixels located at the edge of the spiral groove are similar, so the first probability factor that the edge pixel is the edge of the spiral groove can be obtained according to the degree of dispersion of the local intersection point of the combined edge pixel.
Specifically, for the firstEdge pixel points according to the firstEdge pixel points and the firstGray value of local pixel point of each edge pixel point and the firstThe degree of dispersion of the local intersection points of the edge pixel points is obtainedThe specific calculation formula of the first probability factor that each edge pixel point is a spiral groove edge is as follows:
In the method, in the process of the invention, Represent the firstA first spiral factor for each edge pixel; Represent the first The degree of dispersion of the local intersection points of the edge pixel points; representing the number of preset local pixel points; Represent the first Gray values of the edge pixels; Represent the first Of edge pixelsGray values of the local pixel points; Representing an absolute value operation; representing maximum value and minimum value normalization function, normalizing object to all pixel points ；Representing an exponential function based on natural constants, the present embodiment employsThe model presents an inverse proportion and normalized relationship,For model input, the implementer can set inverse proportion and normalization function according to actual situation.
Note that, the firstThe smaller the degree of dispersion of the local intersection points of the edge pixel points is, and at the same timeEdge pixel points and the firstThe smaller the difference of the local pixel points of the edge pixel points in the gray value is, the firstThe more likely an edge pixel is a pixel on the edge of a spiral groove, thusThe greater the value of (a)The more likely that each edge pixel is a pixel on the edge of the spiral groove; after the first probability factor that the edge pixel point is the edge of the spiral groove is obtained, all the edge pixel points can be initially screened according to the first probability factor that the edge pixel point is the edge of the spiral groove, and the edge pixel point generated by illumination and the pixel point on the edge of the spiral groove are distinguished.
Specifically, a first probability factor threshold is preset，The specific value of (2) can be set by combining with the actual situation, the embodiment does not have hard requirement, in the embodiment, the method usesTo describe, for the firstThe first pixel point isThe first spiral factor of each edge pixel point is smaller thanThen (1)The edge pixels are those generated by illumination effect, if the firstThe first spiral factor of each edge pixel point is greater than or equal toWill be the firstThe edge pixels are noted as target points.
So far, all target points are obtained.
Step S003: acquiring a reference distance and a slot length distance of the target point according to the distances between different target points; acquiring a second spiral factor of the target point according to the reference distance of the target point, the first spiral factor of the target point and the groove length distance; acquiring a third spiral factor of the target point according to the second spiral factor of the target point and the second spiral factor of the local pixel point of the target point; and acquiring the pixel point on the edge of the spiral groove according to the third spiral factor of the target point.
In step S002, the characteristics of the pixels located at the edge of the spiral groove are analyzed, and the target point is obtained by primarily screening all the edge pixels, but there are still some edge pixels generated due to the influence of illumination in the target point, and in order to accurately distinguish the edge pixels generated due to the illumination from the pixels on the edge of the spiral groove, further analysis is required for the target point. Since the distances between the edges of different spiral grooves in the drill bit are always equal and the pixel points on the edges of the spiral grooves are always continuous, the further analysis of the target point can be based on the distances, and the accurate distinction between the edge pixel points generated by illumination and the pixel points on the edges of the spiral grooves can be realized.
Specifically, for the firstTarget points, in the vertical direction and the firstThe nearest target point of the target points is marked as the firstReference points of the target points, will beTarget point numberThe distance between the datum points of the target points is recorded as the firstReference distances of the target points; obtaining reference distances of all target points, recording the numbers in the reference distances of all the target points as slot length distances, and combining the first target points according to the reference distances of all the target points and the slot length distancesA first spiral factor of each target point is obtainedThe specific calculation formula of the second spiral factor of each target point is as follows:
In the method, in the process of the invention, Represent the firstA second helix factor for each target point; Represent the first A first helix factor for each target point; Represent the first Reference distances of the target points; Representing the groove length distance; Representing an absolute value operation.
It should be noted that the distance between each pixel point on the spiral groove edge and the nearest pixel point on the upper spiral groove edge in the vertical direction is equal, so that the more similar the reference distance and the groove length distance of the target point, the more likely the target point is located on the spiral groove edge, and thusThe greater the value of (2)The more likely the target points are pixel points on the edges of the spiral groove.
It should be further noted that, since the spiral groove edge is a continuous curve, that is, if a pixel is on the spiral groove edge, the second spiral factor of the pixel and the second spiral factor of the local pixel of the pixel are both large, so that the third spiral factor of the target point can be obtained according to this.
Specifically, for the firstTarget point, according toSecond spiral factor of each target point and the firstThe second spiral factor of the local pixel point of each target point is obtained, and the third spiral factor of the target point is obtained, wherein the specific calculation formula is as follows:
In the method, in the process of the invention, Represent the firstA third helix factor for each target point; Represent the first First of target pointsA second spiral factor for each local pixel; representing the number of preset local pixel points; Represent the first A second helix factor for each target point; Representing an absolute value operation.
It should be noted that the number of the substrates,Representing the firstA second spiral factor of all local pixels of the target point, whenThe larger the value of the second spiral factor of all local pixel points of the target point is, the description of the firstThe better the continuity of the target points, and whenThe better the continuity of the individual target points and the firstThe larger the second spiral factor of the target point isThe more likely the target points are pixel points on the edges of the spiral groove, soThe greater the value of (2)The more likely the target points are pixel points on the edges of the spiral groove. After the third spiral factor of the target point is obtained, the pixel point on the edge of the spiral groove can be obtained according to the third spiral factor of the target point.
Specifically, a k-means clustering algorithm is utilized, and the k-means clustering algorithm is utilizedThe value is 2, the third spiral factors of all the target points are clustered to obtain two clusters, and the target point in the cluster with the largest average value of the third spiral factors of all the target points in the cluster is used as the pixel point on the edge of the spiral groove, and the k-means clustering algorithm is used as a well-known prior art, so that redundant description is omitted in the embodiment.
Thus, the pixel point on the edge of the spiral groove is obtained.
Step S004: and enhancing the pixel points on the edges of the spiral grooves.
After the pixel points on the edge of the spiral groove are obtained in step S003, the purpose of enhancing the image features of the processing tool in this embodiment can be achieved by enhancing the pixel points on the edge of the spiral groove.
The embodiment provides an optional method, and the method is as follows:
Obtaining a plurality of spiral groove edge lines through pixel points on the spiral groove edge to construct one A size enhancement window, saidIs the groove length distance; for the firstA spiral groove edge line, according to the firstThe first of the spiral groove edge linesConstructing an enhancement window with each pixel point as the center, and then taking the first pixel point as the centerThe first of the spiral groove edge linesConstructing an enhancement window by taking pixel points as the center, and then taking the first pixel point as the centerThe first of the spiral groove edge linesConstructing an enhancement window by taking the pixel points as the center; and so on until the firstAll pixel points in the edge line of the spiral groove are provided with an enhancement window to obtain the firstA plurality of enhancement windows in the edge lines of the spiral grooves; Rounding up the symbol;
For the first The first of the edge lines of the spiral grooveIn the enhancement windowPixel points on the edges of the spiral grooves are to beThe first of the edge lines of the spiral grooveIn the enhancement windowThe third spiral factor of the pixel points on the edges of the spiral grooves is multiplied by 255 to obtain the product after enhancementThe first of the edge lines of the spiral grooveIn the enhancement windowGray values of pixel points on the edges of the spiral grooves;
For the first The first of the edge lines of the spiral grooveIn the enhancement windowA pixel point not on the edge of the spiral groove, the firstThe first of the edge lines of the spiral grooveIn the enhancement windowThe gray values of the pixel points which are not on the edges of the spiral grooves are recorded asObtain the firstThe gray scale of the pixel point on the edge of the spiral groove with the maximum gray scale value and the gray scale of the pixel point with the minimum gray scale value in each enhancement window are respectively recorded asAnd (3) with；
If it isLess thanWill be the firstThe first of the edge lines of the spiral grooveIn the enhancement windowConversion of gray values of pixels other than on the edges of the spiral grooves into；
If it isGreater than or equal toWill be the firstThe first of the edge lines of the spiral grooveIn the enhancement windowConversion of gray values of pixels other than on the edges of the spiral grooves into。
It should be noted that, in this embodiment, by calculating the spiral factor of each edge pixel point in the tool image, the possibility that each edge pixel point is a pixel point on the edge of the spiral groove is obtained, and the pixel point on the edge of the spiral groove in the tool image is accurately obtained, and by improving the contrast of the pixel point on the edge of the spiral groove in the tool image, the image feature enhancement effect of the tool image is improved.
Another embodiment of the present invention provides an image feature enhancement system for a machining tool, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements an image feature enhancement method for a machining tool in steps S001 to S004 when executing the computer program.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the invention, but any modifications, equivalent substitutions, improvements, etc. within the principles of the present invention should be included in the scope of the present invention.
Claims (7)
1. A method of enhancing image features of a machining tool, the method comprising the steps of:
Collecting a cutter image;
Acquiring a plurality of edges in a cutter image, and acquiring local pixel points of edge pixel points in the edges; obtaining local intersection points of the edge pixel points and the discrete degree of the local intersection points according to the curvature of the edge pixel points and the local pixel points of the edge pixel points; according to the discrete degree of the local intersection point, combining the gray values of the edge pixel points to obtain a first spiral factor of the edge pixel points; acquiring a target point according to a first spiral factor of the edge pixel point;
Acquiring a reference distance and a slot length distance of the target point according to the distances between different target points; acquiring a second spiral factor of the target point according to the reference distance of the target point, the first spiral factor of the target point and the groove length distance; acquiring a third spiral factor of the target point according to the second spiral factor of the target point and the second spiral factor of the local pixel point of the target point; obtaining pixel points on the edge of the spiral groove according to a third spiral factor of the target point;
Enhancing pixel points on the edges of the spiral grooves;
According to the discrete degree of the local intersection point, combining the gray values of the edge pixel points to obtain a first spiral factor of the edge pixel points, comprising the following specific methods:
For the first Edge pixel points according to the firstEdge pixel points and the firstGray value of local pixel point of each edge pixel point and the firstThe degree of dispersion of the local intersection points of the edge pixel points is obtainedThe specific calculation formula of the first probability factor that each edge pixel point is a spiral groove edge is as follows:
In the method, in the process of the invention, Represent the firstA first spiral factor for each edge pixel; Represent the first The degree of dispersion of the local intersection points of the edge pixel points; representing the number of preset local pixel points; Represent the first Gray values of the edge pixels; Represent the first Of edge pixelsGray values of the local pixel points; Representing an absolute value operation; Representing a maximum minimum normalization function; An exponential function based on a natural constant;
The method for obtaining the second spiral factor of the target point according to the reference distance of the target point, the first spiral factor of the target point and the groove length distance comprises the following specific steps:
For the first The target points are combined according to the reference distance and the groove length distance of all the target pointsA first spiral factor of each target point is obtainedThe specific calculation formula of the second spiral factor of each target point is as follows:
In the method, in the process of the invention, Represent the firstA second helix factor for each target point; Represent the first A first helix factor for each target point; Represent the first Reference distances of the target points; Representing the groove length distance; Representing an absolute value operation;
The method for obtaining the third spiral factor of the target point according to the second spiral factor of the target point and the second spiral factor of the local pixel point of the target point comprises the following specific steps:
For the first Target point, according toSecond spiral factor of each target point and the firstThe second spiral factor of the local pixel point of each target point is obtained, and the third spiral factor of the target point is obtained, wherein the specific calculation formula is as follows:
In the method, in the process of the invention, Represent the firstA third helix factor for each target point; Represent the first First of target pointsA second spiral factor for each local pixel; representing the number of preset local pixel points; Represent the first A second helix factor for each target point; Representing an absolute value operation.
2. The method for enhancing image features of a machining tool according to claim 1, wherein the steps of obtaining a plurality of edges in an image of the tool and obtaining local pixel points of edge pixel points in the edges comprise the following specific steps:
Acquiring a plurality of edges in a cutter image, and presetting the number of local pixel points ; For the first on any one edgeEdge pixel point to be distant from the firstThe nearest edge pixel pointThe edge pixel points are marked as the firstLocal pixel points of the edge pixel points.
3. The method for enhancing image features of a machining tool according to claim 1, wherein the obtaining the local intersection point of the edge pixel point and the degree of dispersion of the local intersection point according to the curvature of the edge pixel point and the local pixel point of the edge pixel point comprises the following specific steps:
Acquisition of the first Normal of each edge pixel pointThe normal line of the local pixel points of the edge pixel points is the vertical line of the tangent line of the pixel point; acquisition of the firstNormal of each edge pixel pointThe intersection point between the normals of the local pixel points of the edge pixel points is recorded as the firstLocal intersection points of the edge pixel points are obtainedThe discrete degree of the local intersection point of each edge pixel point is specifically calculated according to the following formula:
In the method, in the process of the invention, Represent the firstThe degree of dispersion of the local intersection points of the edge pixel points; Represent the first The number of local intersections of the edge pixels; Represent the first The first edge pixel pointThe lateral position of the local intersection points in the tool image; Represent the first The first edge pixel pointLongitudinal positions of the local intersection points in the tool image; Represent the first The average value of the transverse positions of all local intersection points of the edge pixel points in the cutter image; Represent the first The longitudinal position average of all local intersection points of the edge pixel points in the cutter image.
4. The method for enhancing image features of a processing tool according to claim 1, wherein the acquiring the target point according to the first spiral factor of the edge pixel comprises the following specific steps:
Presetting a first probability factor threshold For the firstThe first pixel point isThe first spiral factor of each edge pixel point is greater than or equal toWill be the firstThe edge pixels are noted as target points.
5. The method for enhancing image features of a machining tool according to claim 1, wherein the step of obtaining the reference distance and the groove length distance of the target point according to the distance between different target points comprises the following specific steps:
For the first Target points, in the vertical direction and the firstThe nearest target point of the target points is marked as the firstReference points of the target points, will beTarget point numberThe distance between the datum points of the target points is recorded as the firstReference distances of the target points; and obtaining the reference distances of all the target points, and recording the numbers in the reference distances of all the target points as the slot length distances.
6. The method for enhancing image features of a machining tool according to claim 1, wherein the step of obtaining the pixel point on the edge of the spiral groove according to the third spiral factor of the target point comprises the following specific steps:
Using k-means clustering algorithm and making k-means clustering algorithm And clustering the third spiral factors of all the target points to obtain two clusters, wherein the target point in the cluster with the largest average value of the third spiral factors of all the target points in the cluster is used as the pixel point on the edge of the spiral groove.
7. An image feature enhancement system for a machining tool comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the computer program when executed by the processor implements the steps of an image feature enhancement method for a machining tool as claimed in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410486798.9A CN118115398B (en) | 2024-04-23 | 2024-04-23 | Image feature enhancement method and system for machining tool |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410486798.9A CN118115398B (en) | 2024-04-23 | 2024-04-23 | Image feature enhancement method and system for machining tool |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118115398A CN118115398A (en) | 2024-05-31 |
| CN118115398B true CN118115398B (en) | 2024-08-13 |
Family
ID=91219216
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410486798.9A Active CN118115398B (en) | 2024-04-23 | 2024-04-23 | Image feature enhancement method and system for machining tool |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118115398B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117036278A (en) * | 2023-08-09 | 2023-11-10 | 河南科技学院 | Cutting tool groove detection method based on machine vision |
| CN117078676A (en) * | 2023-10-16 | 2023-11-17 | 青岛盛鑫达机械有限公司 | Breaking hammer shell visual detection method based on image processing |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108876742B (en) * | 2018-06-25 | 2021-04-30 | Tcl华星光电技术有限公司 | Image color enhancement method and device |
| CN117078738B (en) * | 2023-10-17 | 2024-03-29 | 深圳市城市交通规划设计研究中心股份有限公司 | Linear crack width calculation method |
| CN117315289B (en) * | 2023-11-28 | 2024-02-09 | 苏州翰微材料科技有限公司 | Aeroengine blade contour edge detection method based on image processing |
-
2024
- 2024-04-23 CN CN202410486798.9A patent/CN118115398B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117036278A (en) * | 2023-08-09 | 2023-11-10 | 河南科技学院 | Cutting tool groove detection method based on machine vision |
| CN117078676A (en) * | 2023-10-16 | 2023-11-17 | 青岛盛鑫达机械有限公司 | Breaking hammer shell visual detection method based on image processing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118115398A (en) | 2024-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11580647B1 (en) | Global and local binary pattern image crack segmentation method based on robot vision | |
| CN117078672B (en) | Intelligent detection method for mobile phone screen defects based on computer vision | |
| CN116109644B (en) | Surface defect detection method for copper-aluminum transfer bar | |
| CN116823826A (en) | Numerical control machine tool tipping abnormity detection method | |
| CN116385472B (en) | Hardware stamping part deburring effect evaluation method | |
| CN117315289B (en) | Aeroengine blade contour edge detection method based on image processing | |
| CN114820625B (en) | Automobile top block defect detection method | |
| CN117237646B (en) | PET high-temperature flame-retardant adhesive tape flaw extraction method and system based on image segmentation | |
| CN117689655B (en) | Metal button surface defect detection method based on computer vision | |
| CN117808810B (en) | Hobbing cutter abrasion image recognition and measurement method and system | |
| CN109934278A (en) | A kind of high-dimensional feature selection method of information gain mixing neighborhood rough set | |
| CN112530592A (en) | Non-small cell lung cancer risk prediction method based on machine learning | |
| CN117541582A (en) | IGBT insulation quality detection method for high-frequency converter | |
| CN118115398B (en) | Image feature enhancement method and system for machining tool | |
| CN113139928A (en) | Training method of pulmonary nodule detection model and pulmonary nodule detection method | |
| CN102313740B (en) | Solar panel crack detection method | |
| CN117437228B (en) | Photovoltaic steel structure component fracture detection method based on image characteristics | |
| CN112258532B (en) | Positioning and segmentation method for callus in ultrasonic image | |
| CN118014994B (en) | Rice hull degradable meal box crack detection method | |
| CN112258536B (en) | Integrated positioning and segmentation method for calluses and cerebellum earthworm parts | |
| CN117934516B (en) | Automatic mitochondrial fluorescence image segmentation method and system | |
| CN116432052B (en) | Quality detection method for clamp for new energy automobile die | |
| JP3415342B2 (en) | Character cutout method | |
| CN113129314B (en) | Intelligent image processing method for lung shadows | |
| CN103778444A (en) | Pulmonary nodule benign and malignant identification method based on support vector machine sample reduction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |