CN111801709A - Circular feature detection method, processing system and device with storage function - Google Patents

Circular feature detection method, processing system and device with storage function Download PDF

Info

Publication number
CN111801709A
CN111801709A CN201880088735.0A CN201880088735A CN111801709A CN 111801709 A CN111801709 A CN 111801709A CN 201880088735 A CN201880088735 A CN 201880088735A CN 111801709 A CN111801709 A CN 111801709A
Authority
CN
China
Prior art keywords
polar
image
detection
parameter
obtaining
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.)
Granted
Application number
CN201880088735.0A
Other languages
Chinese (zh)
Other versions
CN111801709B (en
Inventor
李洪杰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen A&E Intelligent Technology Institute Co Ltd
Original Assignee
Shenzhen A&E Intelligent Technology Institute Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen A&E Intelligent Technology Institute Co Ltd filed Critical Shenzhen A&E Intelligent Technology Institute Co Ltd
Publication of CN111801709A publication Critical patent/CN111801709A/en
Application granted granted Critical
Publication of CN111801709B publication Critical patent/CN111801709B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Geometry (AREA)
  • Image Analysis (AREA)

Abstract

A circular feature detection method, a processing system and a device with a storage function are provided, wherein the detection method comprises the following steps: receiving an image to be processed, wherein the image to be processed comprises a circular feature (S101); extracting an interested area of the image to be processed, and obtaining a first parameter corresponding to the interested area, wherein the circular feature is located in the interested area, and the interested area is a circular ring (S102); detecting the circular feature by using the first parameter to obtain a detection parameter corresponding to the circular feature (S103); adjusting the first parameter by using the detection parameter, returning to the step of detecting the circular feature by using the first parameter, and recording the detection parameter obtained after each detection until the distance between the first circle center coordinate and the detection circle center coordinate is less than or equal to a preset threshold (S104); final parameters of the circular feature are determined based on the recorded plurality of detected parameters and the first predetermined policy, the final parameters including circle center coordinates and a radius of the circular feature (S105). By the mode, the detection method can improve the accuracy of the detection result.

Description

Circular feature detection method, processing system and device with storage function Technical Field
The present disclosure relates to the field of image processing technologies, and in particular, to a method and a system for detecting a circular feature.
Background
When the machine vision technology is adopted to detect the image to be processed, the whole image to be processed does not necessarily need to be detected, but only a part of the image to be processed needs to be detected, for example, only the edge of the image to be processed needs to be detected.
For example, when the edge is a circular feature, a region to be processed, which is called a region of interest (ROI), can be delineated on the image to be processed in a manner of a box, a circle, an ellipse, an irregular polygon, or the like. By performing circular feature detection on the region of interest, the circular feature detection time can be shortened. However, due to the randomness of the region of interest, the detection result of the circular feature has a large difference, and the accuracy and stability of the result cannot be ensured.
Disclosure of Invention
The application provides a circular feature detection method, a processing system and a device with a storage function, which can improve the accuracy and stability of a circular feature detection result.
In order to solve the technical problem, the application adopts a technical scheme that: providing a circular feature detection method, wherein the circular feature detection method comprises the steps of receiving an image to be processed, wherein the image to be processed comprises a circular feature; extracting an interested area of the image to be processed, and obtaining a first parameter corresponding to the interested area, wherein the circular feature is located in the interested area, the interested area is a circular ring, and the first parameter comprises a first circle center coordinate, an inner diameter and an outer diameter corresponding to the interested area; detecting the circular feature by using the first parameter to obtain a detection parameter corresponding to the circular feature, wherein the detection parameter comprises a detection circle center coordinate and a detection radius; adjusting the first parameter by using the detection parameter, returning to the step of detecting the circular feature by using the first parameter, and recording the detection parameter obtained after each detection until the distance between the first circle center coordinate and the detection circle center coordinate is less than or equal to a preset threshold value; and determining final parameters of the circular feature according to the recorded detection parameters and a first preset strategy, wherein the final parameters comprise the circle center coordinate and the radius of the circular feature.
In order to solve the above technical problem, another technical solution adopted by the present application is: provided is a circular feature detection method including: receiving an image to be processed, wherein the image to be processed comprises a circular feature; extracting an interested area of the image to be processed, and obtaining a first parameter corresponding to the interested area, wherein the circular feature is located in the interested area, the interested area is a circular ring, and the first parameter comprises a first circle center coordinate, an inner diameter and an outer diameter corresponding to the interested area; detecting the circular feature by using the first parameter to obtain a detection parameter corresponding to the circular feature, wherein the detection parameter comprises a detection circle center coordinate and a detection radius; adjusting the first parameter by using the detection parameter, returning to the step of detecting the circular feature by using the first parameter, recording the detection parameter obtained after each detection, and updating the value of the iteration parameter after each detection until the value of the iteration parameter exceeds a preset range; and determining final parameters of the circular feature according to the recorded detection parameters and a first preset strategy, wherein the final parameters comprise the circle center coordinate and the radius of the circular feature.
In order to solve the above technical problem, another technical solution adopted by the present application is: there is provided a circular feature detection processing system, comprising a processor, a memory, a transceiver and a display, wherein the transceiver is configured to receive an image to be processed and transmit the image to be processed to the processor, the display is configured to display a detection result, and the memory stores program instructions that can be loaded by the processor and execute the circular feature detection method according to any of the embodiments.
In order to solve the above technical problem, the present application adopts another technical solution: there is provided a device having a storage function, on which program data are stored, which program data, when executed by a processor, implement the steps in the circular feature detection method of any of the above embodiments.
The beneficial effect of this application is: different from the prior art, the circular feature detection method provided by the application comprises the following steps: obtaining detection parameters corresponding to the detected circular features by using first parameters corresponding to the region of interest; adjusting a first parameter by using the detection parameter, returning to the step of detecting the circular feature by using the first parameter, and recording the detection parameter obtained after each detection until the distance between the first circle center coordinate and the detection circle center coordinate is less than or equal to a preset threshold value; and determining final parameters of the circular feature according to the recorded multiple detection parameters and a first preset strategy, wherein the final parameters comprise the circle center coordinate and the radius of the circular feature. On one hand, the region of interest and the circular feature are closer and closer through the iteration mode, and the center of the region of interest and the center of the circular feature are closer and closer, so that the randomness of the region of interest is reduced, and the accuracy of the detection result of the circular feature is improved; on the other hand, in the method, a relatively average result can be given by using a plurality of detection parameters and a first predetermined strategy to obtain the final parameters of the circular feature, so that the accuracy and stability of the detection result of the circular feature are further improved, and in an application scene, the detection result of the circle can reach several pixels at zero point.
[ description of the drawings ]
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without inventive efforts, wherein:
FIG. 1 is a schematic flow chart diagram illustrating an embodiment of a circular feature detection method according to the present application;
FIG. 2 is a schematic flow chart illustrating an embodiment of step S103 in FIG. 1;
FIG. 3a is a schematic structural diagram of an embodiment of a region-of-interest image in a rectangular coordinate system;
FIG. 3b is a schematic structural diagram of an embodiment of converting the image of the region of interest in the rectangular coordinate system in FIG. 3a into a first image in a polar coordinate system;
FIG. 4 is a schematic flowchart illustrating an embodiment of step S203 in FIG. 2;
FIG. 5 is a flowchart illustrating an embodiment of screening the second plurality of apertures to reserve at most one second plurality of apertures in step S206 of FIG. 2;
FIG. 6 is a flowchart illustrating an embodiment of screening a plurality of third apertures to reserve at most one third aperture in step S207 in FIG. 2;
FIG. 7 is a schematic flow chart diagram illustrating another embodiment of a circular feature detection method according to the present application;
FIG. 8 is a schematic structural diagram of an embodiment of a circular feature detection system according to the present application;
fig. 9 is a schematic structural diagram of an embodiment of a device with a storage function according to the present application.
[ detailed description ] embodiments
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
Referring to fig. 1, fig. 1 is a schematic flow chart illustrating an embodiment of a circular feature detection method according to the present application, the detection method including:
s101: receiving an image to be processed, the image to be processed including a circular feature.
Specifically, the image to be processed may be provided by an image pickup device having a photographing function such as a camera, and the image to be processed may be a black-and-white image or a color image. The image to be processed includes a circular feature, for example, a circular hole, a cylinder, etc. of the workpiece, and in this embodiment, the circular feature may be an outer edge of the workpiece or an inner hollow area edge of the workpiece. In the practical application process, the circular features include a non-noise standard circular feature, a noise standard circular feature and a non-standard circular feature (i.e., a less-regular circular feature), and the processor can receive the image to be processed provided by the camera device and further perform subsequent processing on the image.
S102: and extracting an interested area of the image to be processed, and obtaining a first parameter corresponding to the interested area, wherein the circular feature is positioned in the interested area, and the interested area is a circular ring.
In particular, in one application scenario, a region of interest (ROI) may be selected using a variety of PEEK tools (e.g., face PEEK, line PEEK, and dot PEEK) established in the existing machine vision software sherlock. The user can input the circle center coordinate, the excircle diameter, the inner circle diameter and the like of the ring on the PEEK tool interface. The first parameters comprise a first circle center coordinate, an inner diameter and an outer diameter corresponding to the interested area.
S103: and detecting the circular feature by using the first parameter to obtain a detection parameter corresponding to the circular feature.
Specifically, the detection parameters include a detection circle center coordinate and a detection radius corresponding to the circular feature.
In an application scenario, as shown in fig. 2, fig. 2 is a schematic flowchart of an embodiment of step S103 in fig. 1, where the step S103 specifically includes:
s201: and converting the image of the region of interest in the rectangular coordinate system into a first image in the polar coordinate system, wherein the image of the region of interest contains circular features.
Specifically, the abscissa of the first image in the polar coordinate system is the polar diameter, and the ordinate is the polar angle. In the present embodiment, senseThe region of interest is a ring with an inner diameter R1Outer diameter of R2And the circular characteristic of the circular characteristic in the image to be detected is positioned in the circular ring. As shown in fig. 3, fig. 3a is a schematic structural diagram of an embodiment of an image of a region of interest in a rectangular coordinate system, and fig. 3b is a schematic structural diagram of an embodiment of converting the image of the region of interest in the rectangular coordinate system in fig. 3a into a first image in a polar coordinate system. The rectangular coordinate system in fig. 3a and the polar coordinate system in fig. 3b have the same origin and positive direction, which can be determined by the user. For example, as shown in FIG. 3b, the abscissa of the graph is the polar diameter r and the ordinate is the polar angle θ; the origin is the upper left corner of the figure, the positive direction of the abscissa is to the right, and the ordinate is to the down.
Assuming that under a rectangular coordinate system (or an image coordinate system), the coordinates of each point on the circular feature are I (x, y), the point is converted into a polar coordinate system, the coordinates of each point are I' (R, theta), and the outer diameter of the region of interest is R2Inner diameter of R1Then I' (r, θ) satisfies the following relationship:
i' (r, θ) ═ I (rcos θ, rsin θ), where: r is an element of [0, R ∈2-R1]，θ∈[0，359]。
S202: and obtaining a one-dimensional histogram corresponding to the first image, a first gradient image corresponding to the first image and a second gradient image corresponding to the one-dimensional histogram.
In an application scenario, the step S202 specifically includes: first-order derivation is carried out on the first image to obtain a corresponding first gradient image; obtaining a row vector image by calculating the average value of the pixel gray levels of the first image according to columns, wherein the row vector image is a one-dimensional histogram; the one-dimensional histogram is first order derived to obtain a second gradient image. Of course, in other application scenarios, the second order derivation may be performed on the first image or the one-dimensional histogram. The second gradient image in step S202 is used to find the abrupt change portion of the image, so as to obtain the edge information of the image.
S203: first polar paths corresponding to a plurality of extreme values in the second gradient image are obtained.
Specifically, in an application scenario, please refer to fig. 4, where fig. 4 is a schematic flowchart illustrating an embodiment of step S203 in fig. 2, where the step S203 specifically includes:
s301: and obtaining corresponding gradient values at the current position in the second gradient image according to a preset sequence.
Specifically, the predetermined sequence may be from left to right or from right to left, or other specified sequence, which is not limited in this application.
S302: and judging whether the gradient value is an extreme value.
Specifically, the extreme values include a maximum value and a minimum value; the step S302 specifically includes: obtaining a first gradient value and a second gradient value corresponding to two adjacent pixel positions at the left and right of the current position; judging whether the gradient value at the current position is greater than or equal to a first gradient value or not, and whether the gradient value at the current position is greater than or equal to a second gradient value or not, if so, the gradient value at the current position is the maximum value; if not, further judging whether the gradient value at the current position is smaller than or equal to a first gradient value or not, and whether the gradient value at the current position is smaller than or equal to a second gradient value or not, if so, the gradient value at the current position is a minimum value; otherwise, the gradient value at the current position is not an extreme value.
For example, assume that the pole diameter at the current position is r1Gradient value of T1(ii) a The polar diameters of the positions of two adjacent pixels at the left and the right are r respectively1-1、r1+1, and r1-1 and r1The gradient value corresponding to +1 is T2And T3When T is1≥T2And T is1≥T3While, the current pole diameter r1Corresponding gradient value T1Is a maximum value; when T is1≤T2And T is1≤T3While, the current pole diameter r1Corresponding gradient value T1Is a minimum value. Otherwise, the current pole diameter r1Corresponding gradient value T1Is not an extreme value.
S303: if so, obtaining a first polar diameter corresponding to the current position; otherwise, go directly to step S304;
s304: and judging whether the current position is the last position in the second gradient image, if so, ending, and otherwise, obtaining a gradient value corresponding to the next position of the current position and returning to the step S302.
Specifically, when the radius corresponding to the current position in the second gradient image is obtained in the order from left to right, it may be determined whether the radius value corresponding to the current position is smaller than the maximum radius value in the second gradient image, and if so, it is determined that the current position is not the last position in the second gradient image; if so, judging that the current position is the last position in the second gradient image.
Of course, in other application scenarios, the step S203 may also be implemented in other manners, for example, the step of "determining whether the current position is the last position in the second gradient image" in the step S304 may also be located before the step of "determining whether the gradient value corresponding to the current position is an extreme value" in the step S302.
S204: and obtaining a maximum point in the first gradient image within a preset range from each first polar diameter, wherein the polar diameter and the polar angle corresponding to the maximum point are defined as a first local polar diameter and a first polar angle.
Specifically, the second gradient image in step S203 is used to indicate where the edge information appears, and only the position range can be known, and the positioning cannot be performed accurately; and the precise positioning can be performed from the first gradient image through the above step S204. The predetermined range may be artificially predefined, and may be 3 or 5 pixels wide, for example, and the maximum value point or the minimum value point within the predetermined range and the first local polar diameter and the first polar angle corresponding to the maximum value point or the minimum value point are obtained from the first gradient image. For example, the first image in FIG. 3b is illustrated as the first gradient image, r1The first polar path obtained from the second gradient image is a predetermined range in the middle of the two dotted lines, and the point P in the graph is the maximum point in the predetermined range.
S205: and obtaining a second polar angle and a third polar angle corresponding to each first polar angle in the first gradient image, wherein the first polar angle, the second polar angle and the third polar angle meet a first preset condition.
Specifically, in an application scenario, the meeting of the first preset condition among the first polar angle, the second polar angle, and the third polar angle includes: the absolute value of the difference between the second polar angle and the first polar angle is 180 °, and the absolute value of the difference between the third polar angle and the first polar angle is 90 °. The three points that are not collinear may uniquely define a circle.
S206: and obtaining a plurality of second polar paths corresponding to the second polar angles from the first gradient image, and screening the plurality of second polar paths to reserve at most one second polar path.
Specifically, in an application scenario, the process of obtaining a plurality of second polar paths corresponding to the second polar angles from the first gradient image in step S206 includes: and obtaining a row vector corresponding to the second polar angle in the first gradient image, and searching from the leftmost side or the rightmost side of the row vector to obtain a plurality of extreme points (the extreme points are edge points) appearing on the row vector so as to obtain a plurality of second polar paths.
In this embodiment, since the absolute value of the difference between the second polar angle and the first polar angle is 180 °, when the region of interest and the circular feature are not the same circle center, the point corresponding to the first polar angle is the closest or farthest point on the circular feature from the circle center of the region of interest; the point corresponding to the second polar angle is the point farthest from or closest to the center of the region of interest, the two points just form the diameter of the circle, and a circle can be determined by the two points on the diameter. The process of screening the plurality of second pole diameters to reserve at most one second pole diameter in step S206 includes: fitting the current second polar diameter and second polar angle with the previously found first local polar diameter and first polar angle to obtain a second fitting circle, and then judging whether the second fitting circle really exists, wherein if the extreme points corresponding to the second polar diameter and the second polar angle are points on the circular feature, the second fitting circle really exists, and the second polar diameter is reserved; if the extreme point corresponding to the second polar radius and the second polar angle is not a point on the circular feature, is a noise point or an interference point, then this second fitted circle is not present and the second polar radius is filtered out. The process will screen out at most one of the second pole diameters.
Referring to fig. 5, fig. 5 is a flowchart illustrating an embodiment of screening a plurality of second poles to reserve at most one second pole in step S206 of fig. 2. The step S206 of screening the plurality of second polar diameters to reserve at most one second polar diameter, that is, the method for specifically determining whether the second fitting circle really exists includes:
s401: and fitting all the second polar diameters and the second polar angles with the first local polar diameters and the first polar angles respectively to obtain a plurality of second fitting circles and fourth parameters corresponding to the second fitting circles.
Specifically, in an application scenario, the first polar angle, the first local polar diameter, the second polar angle, and the second polar diameter may be converted into a first coordinate value and a second coordinate value corresponding to a rectangular coordinate system; and obtaining a second fitting circle according to the first coordinate value and the second coordinate value, and obtaining a fourth parameter corresponding to the second fitting circle under the rectangular coordinate system. The fourth parameter includes a circle center coordinate and a radius corresponding to the second fitting circle in the rectangular coordinate system.
S402: and acquiring a first local image within a first preset range from the second fitting circle from the region of interest by using the fourth parameter corresponding to the second fitting circle.
Specifically, the first predetermined range may be set by the user, and may be generally 1-10 (e.g., 1, 3, 5, 7, 10, etc.) pixel widths;
s403: and obtaining a third gradient image corresponding to the first partial image.
Specifically, in one application scenario, the first local image may be converted into a second image in a polar coordinate system; and calculating the average sum of the pixel gray levels of the second image according to the columns to obtain a one-dimensional histogram corresponding to the second image, and performing first-order derivation on the one-dimensional histogram to obtain a corresponding third gradient image.
S404: a first contrast of the second fitted circle is obtained by the third gradient image.
In particular, the first contrast may be obtained by any of the prior art. For example, the first contrast is the maximum of the absolute values of the gradient values in the third gradient image.
S405: the second fitted circle is scored using a first contrast, the first contrast being proportional to the first score.
Specifically, in an application scenario, the first contrast may be multiplied by a scaling factor to obtain a first score; of course, in other application scenarios, the first score may also be obtained in other manners, which is not limited in this application.
S406: and obtaining a second polar diameter corresponding to a second fitting circle with the first score exceeding a first threshold value and the highest score.
In particular, the first threshold value may be set by the user.
S207: and obtaining a plurality of third apertures corresponding to the third aperture angles from the first gradient image, and screening the plurality of third apertures to reserve at most one third aperture.
Specifically, in an application scenario, the process of obtaining a plurality of third apertures corresponding to the third polar angles from the first gradient image in step S207 includes: and obtaining a row vector corresponding to the third polar angle in the first gradient image, and searching from the leftmost side or the rightmost side of the row vector to obtain a plurality of extreme points (the extreme points are edge points) appearing on the row vector, so as to obtain a plurality of third polar paths.
In this embodiment, since the absolute value of the difference between the third polar angle and the first polar angle is 90 °, the process of screening a plurality of third polar paths in step S207 to reserve at most one third polar path includes: fitting the current third pole diameter and the current third pole angle with the first local pole diameter, the first pole angle, the second pole diameter and the second pole angle found in the previous step to obtain a third fitting circle, and then judging whether the third fitting circle really exists or not, wherein if the extreme points corresponding to the third pole diameter and the third pole angle are points on the circular feature, the third fitting circle really exists, and the third pole diameter is reserved; if the extreme points corresponding to the third aperture and the third angle are not points on the circular feature, noise points or interference points, the third fitting circle does not exist, and the third aperture is screened out. The above process will screen out a maximum of one third aperture.
Referring to fig. 6, fig. 6 is a flowchart illustrating an embodiment of screening a plurality of third apertures to reserve at most one third aperture in step S207 in fig. 2. In the step S207, the method for screening the plurality of third apertures to reserve at most one third aperture, that is, specifically determining whether the third fitting circle really exists includes:
s501: and fitting all the third polar diameters and the third polar angles with the first local polar diameters, the first polar angles and the second polar angles which are screened and reserved after the step S206 respectively to obtain a plurality of third fitting circles and fifth parameters corresponding to the third fitting circles.
Specifically, in an application scenario, the current third polar diameter, the current third polar angle, the first local polar diameter, the current first polar angle, the second polar diameter and the second polar angle which are screened and retained after step S206 may be converted into a first coordinate value, a second coordinate value and a third coordinate value corresponding to a rectangular coordinate system; and obtaining a third fitting circle according to the first coordinate value, the second coordinate value and the third coordinate value, and a fifth parameter corresponding to the third fitting circle in the rectangular coordinate system. The fifth parameter includes a circle center coordinate and a radius corresponding to the third fitting circle in the rectangular coordinate system.
S502: and acquiring a second local image within a second preset range from the third fitting circle from the region of interest by using a fifth parameter corresponding to the third fitting circle.
Specifically, the second predetermined range may be set by the user, and may be generally 1-10 (e.g., 1, 3, 5, 7, 10, etc.) pixel widths;
s503: and obtaining a fourth gradient image corresponding to the second local image.
Specifically, in an application scenario, the second local image may be converted into a third image in a polar coordinate system; and calculating the average sum of the pixel gray levels of the third image according to columns to obtain a one-dimensional histogram corresponding to the third image, and performing first-order derivation on the one-dimensional histogram to obtain a fourth gradient image corresponding to the one-dimensional histogram.
S504: a second contrast of the third fitted circle is obtained from the fourth gradient image.
In particular, the second contrast may be obtained by any of the methods of the prior art. For example, the second contrast is the maximum of the absolute values of the gradient values in the fourth gradient image.
S505: the third fitted circle is scored using a second contrast, the second contrast being proportional to the second score.
Specifically, in an application scenario, the second contrast may be multiplied by a scaling factor to obtain a second score; of course, in other application scenarios, the second score may also be obtained in other manners, which is not limited in this application.
S506: and obtaining a third aperture corresponding to a third fitting circle with the second score exceeding a second threshold and the highest second score.
In particular, the second threshold value may be set by the user.
To this end, through the step S207, a first local pole diameter corresponds to a second pole diameter and a third pole diameter.
S208: and obtaining a plurality of first fitting circles corresponding to the screened groups of first polar angles, first local polar diameters, second polar angles, second polar diameters, third polar angles and third polar diameters, and a plurality of third parameters corresponding to the first fitting circles.
Specifically, in an application scenario, the step S208 specifically includes: and obtaining third fitting circles corresponding to all the first polar angles and the first local polar diameters, wherein the third polar angles and the first local polar diameters are reserved, the first fitting circles are third fitting circles, and the third parameters are fifth parameters. The third parameter includes a center coordinate and a radius of the first fitting circle corresponding to the rectangular coordinate system.
S209: and obtaining detection parameters by using the plurality of first fitting circles, the plurality of third parameters and a second preset strategy.
Specifically, in an application scenario, the step S209 specifically includes: and obtaining a circle with the highest score, or a circle with the largest radius, or a circle with the smallest radius in the plurality of first fitting circles, and taking a third parameter corresponding to the circle as a detection parameter.
S104: and adjusting the first parameter by using the detection parameter, returning to the step of detecting the circular feature by using the first parameter, and recording the detection parameter obtained after each detection until the distance between the first circle center coordinate and the detection circle center coordinate is less than or equal to a preset threshold value.
Specifically, in an application scenario, the adjusting the first parameter of the region of interest by using the detection parameter in step S104 specifically includes: and taking the detection circle center coordinate in the detection parameters obtained by the last detection as a first circle center coordinate corresponding to the region of interest to adjust the position of the region of interest. The purpose of this step is to adjust the position of the region of interest so that the center of the region of interest coincides as much as possible with the center of the circular feature. Of course, in other application scenarios, while adjusting the position of the region of interest, the size of the region of interest may be further adjusted, for example, the inner diameter and the outer diameter corresponding to the region of interest are adjusted according to the radius in the detection parameter obtained by the last detection, so as to narrow the range of the region of interest. It should be noted that when adjusting the size of the region of interest, it is necessary to ensure that the circular feature is located within the region of interest.
In addition, in this embodiment, after the first parameter is adjusted by using the detection parameter, the detection method provided by the present application further includes: obtaining the distance between the first circle center coordinate and the detected circle center coordinate, and judging whether the distance is smaller than or equal to a preset threshold value; if yes, go to the subsequent step S105; otherwise, return to step S103. The preset threshold mentioned above can be set by the user.
S105: and determining final parameters of the circular feature according to the recorded multiple detection parameters and a first preset strategy, wherein the final parameters comprise the circle center coordinate and the radius of the circular feature.
Specifically, in an application scenario, the step S105 includes: and taking the average value of a plurality of detection parameters as the final parameter of the circular feature, wherein the center coordinate of the circular feature is equal to the average value of all the detection center coordinates, and the radius of the center feature is equal to the average value of all the detection radii.
Referring to fig. 7, fig. 7 is a schematic flowchart illustrating another embodiment of a circular feature detection method according to the present application, the detection method including:
s601: an image to be processed is received, the image to be processed including a circular feature. Specifically, this step is the same as step S101 in the above embodiment, and is not described herein again.
S602: extracting an interested area of the image to be processed, and obtaining a first parameter corresponding to the interested area, wherein the circular feature is located in the interested area, the interested area is a circular ring, and the first parameter comprises a first circle center coordinate, an inner diameter and an outer diameter corresponding to the interested area. Specifically, the step is the same as step S102 in the above embodiment, and is not described herein again.
S603: and detecting the circular feature by using the first parameter to obtain a detection parameter corresponding to the circular feature, wherein the detection parameter comprises a detection circle center coordinate and a detection radius. Specifically, this step is the same as step S103 in the above embodiment, and is not described again here.
S604: and adjusting the first parameter by using the detection parameter, returning to the step of detecting the circular feature by using the first parameter, recording the detection parameter obtained after each detection, and updating the value of the iteration parameter after each detection until the value of the iteration parameter exceeds a preset range.
Specifically, the adjusting of the first parameter of the region of interest by using the detection parameter in step S604 is the same as the related content in step S104 in the foregoing embodiment, and is not repeated here.
In this embodiment, the iteration parameter is the number of times of detecting the circular feature by using the first parameter, and the value of the iteration parameter exceeding the preset range is that the number of times of detection is greater than or equal to a preset value, or is less than or equal to a preset value. The initial value of the iteration parameter can also be any positive integer, and the iteration parameter can be increased by a set value after each detection until the value of the iteration parameter is greater than or equal to a preset value; of course, after each detection, the iterative parameter may also be subtracted by a set value until the value of the iterative parameter is less than or equal to the preset value.
In other embodiments, the iteration parameter may also be an angle value on the circular feature, which is detected by using the first parameter, and the value of the iteration parameter exceeds the preset range, where the angle value is greater than or equal to the preset angle, or less than or equal to the preset angle. The initial value of the iteration parameter can be any angle, and the iteration parameter can be increased by a set value after each detection until the value of the iteration parameter is greater than or equal to a preset angle; of course, after each detection, the iteration parameter may also be subtracted by a set value until the value of the iteration parameter is less than or equal to the preset angle. For example, the initial value of the iteration parameter may be 0 °, the set value may be 45 °, and the preset angle may be 360 °.
In another embodiment, after the adjusting the first parameter by using the detection parameter, the detection method provided by the present application further includes: judging whether the value of the current iteration parameter exceeds a preset range or not; if yes, go to the subsequent step S605; otherwise, the process returns to step S603, and the value of the iteration parameter is updated (e.g., a set value is added or subtracted).
S605: and determining final parameters of the circular feature according to the recorded multiple detection parameters and a first preset strategy, wherein the final parameters comprise the circle center coordinate and the radius of the circular feature. Specifically, this step is the same as step S105 in the above embodiment, and is not described herein again.
In another embodiment, the detection methods presented in FIGS. 1 and 7 of the present application can also be combined. For example, the method in fig. 1 may be performed first, where the method in fig. 1 is equivalent to a process of roughly searching for a circular feature, and initially, the circular feature may not be concentric with the region of interest or may be severely eccentric, and the distance between the first circle center coordinate corresponding to the region of interest and the detected circle center coordinate of the circular feature may be smaller than or equal to a preset threshold value by the method in fig. 1, so that the circular feature is substantially concentric with the moved region of interest; then, the method in fig. 7 may be performed, where the method in fig. 7 is equivalent to a process of finely searching for a circular feature, and the number of times of detecting the circular feature is controlled by iterative parameters, so as to ensure accuracy and stability of the circular feature.
In practical applications, the circular features include noiseless standard circular features, noisy standard circular features, and non-standard circular features (i.e., less regular circular features). For the noiseless standard circular feature, because the noiseless standard circular feature has high-quality edge information, the detection parameters of the edge can be accurately calculated through two or three iterations, and the accuracy can reach 0.03 pixel; for the noisy standard circular feature, because the existence of noise usually has the condition of oscillation and non-convergence in circular feature detection, the influence of noise can be well avoided by using a mode of multiple iterations and then averaging, and the accuracy and stability of final parameters are ensured; for the non-standard circular feature, the parameters of the non-standard circular feature cannot be given theoretically (parameters such as no center, no radius and the like because of the non-circular feature), but the average center coordinate and radius parameters of the non-standard circular feature can be given by detecting and calculating the non-standard circular feature omnidirectionally, so that the method is very useful for practical application because many circular features in an actual picture are non-standard circular features. In addition, the iterative idea in the circular feature detection method provided by the present application can also be used in the detection process of other specific shapes, such as a straight line, and the like, which is not described in the present application too much.
Referring to fig. 8, fig. 8 is a schematic structural diagram of an embodiment of a circular feature detection processing system according to the present application. The circular feature detection processing system 1 comprises a processor 10, a memory 12, a transceiver 14 and a display 16, wherein the transceiver 14 is configured to receive an image to be processed and transmit the image to be processed to the processor 10, the display 16 is configured to display a detection result, of course, the display 16 may also display the image to be processed and a region of interest, and the memory 12 stores program instructions, which can be loaded by the processor 10 and executed by the circular feature detection method in any of the above embodiments.
Referring to fig. 9, fig. 9 is a schematic structural diagram of an embodiment of a device with storage function according to the present application, in which program data 20 is stored on the device with storage function 2, and when the program data 20 is executed by a processor, the steps in the circular feature detection method in any of the embodiments described above are implemented.
In summary, unlike the prior art, the circular feature detection method provided by the present application includes: obtaining detection parameters corresponding to the detected circular features by using first parameters corresponding to the region of interest; adjusting a first parameter by using the detection parameter, returning to the step of detecting the circular feature by using the first parameter, and recording the detection parameter obtained after each detection until the distance between the first circle center coordinate and the detection circle center coordinate is less than or equal to a preset threshold value; and determining final parameters of the circular feature according to the recorded multiple detection parameters and a first preset strategy, wherein the final parameters comprise the circle center coordinate and the radius of the circular feature. On one hand, the region of interest and the circular feature are closer and closer through the iteration mode, and the center of the region of interest and the center of the circular feature are closer and closer, so that the randomness of the region of interest is reduced, and the accuracy of the detection result of the circular feature is improved; on the other hand, in the method, a relatively average result can be given by using a plurality of detection parameters and a first predetermined strategy to obtain the final parameters of the circular feature, so that the accuracy and stability of the detection result of the circular feature are further improved, and in an application scene, the detection result of the circle can reach a few tenths of pixels.

Claims (20)

  1. A circular feature detection method, comprising:
    receiving an image to be processed, wherein the image to be processed comprises a circular feature;
    extracting an interested area of the image to be processed, and obtaining a first parameter corresponding to the interested area, wherein the circular feature is located in the interested area, the interested area is a circular ring, and the first parameter comprises a first circle center coordinate, an inner diameter and an outer diameter corresponding to the interested area;
    detecting the circular feature by using the first parameter to obtain a detection parameter corresponding to the circular feature, wherein the detection parameter comprises a detection circle center coordinate and a detection radius;
    adjusting the first parameter by using the detection parameter, returning to the step of detecting the circular feature by using the first parameter, and recording the detection parameter obtained after each detection until the distance between the first circle center coordinate and the detection circle center coordinate is less than or equal to a preset threshold value;
    and determining final parameters of the circular feature according to the recorded detection parameters and a first preset strategy, wherein the final parameters comprise the circle center coordinate and the radius of the circular feature.
  2. The method of claim 1, wherein the adjusting the first parameter using the detection parameter comprises:
    and taking the detection circle center coordinate in the detection parameters obtained by the last detection as a first circle center coordinate corresponding to the region of interest to adjust the position of the region of interest.
  3. The method of claim 2, wherein the adjusting the first parameter using the detection parameter further comprises:
    and adjusting the inner diameter and the outer diameter corresponding to the region of interest according to the detection radius in the detection parameters obtained by the last detection so as to narrow the range of the region of interest.
  4. The detection method according to claim 1, wherein the detecting the circular feature by using the first parameter to obtain a detection parameter corresponding to the circular feature comprises:
    converting the image of the region of interest in a rectangular coordinate system into a first image in a polar coordinate system, wherein the image of the region of interest comprises the circular feature, the abscissa of the first image is a polar diameter, and the ordinate of the first image is a polar angle;
    obtaining a one-dimensional histogram corresponding to the first image, a first gradient image corresponding to the first image and a second gradient image corresponding to the one-dimensional histogram;
    obtaining first polar diameters corresponding to a plurality of extreme values in the second gradient image;
    obtaining a maximum point in the first gradient image within a preset range from each first polar diameter, wherein the polar diameter and the polar angle corresponding to the maximum point are defined as a first local polar diameter and a first polar angle;
    obtaining a second polar angle and a third polar angle corresponding to the first polar angle in the first gradient image, wherein the first polar angle, the second polar angle and the third polar angle meet a first preset condition;
    obtaining a plurality of second polar diameters corresponding to the second polar angles in the first gradient image, and screening the plurality of second polar diameters to reserve at most one second polar diameter;
    obtaining a plurality of third apertures corresponding to the third aperture angles in the first gradient image, and screening the plurality of third apertures to reserve at most one third aperture;
    obtaining a plurality of sets of first fitting circles corresponding to the first polar angle, the first local polar diameter, the second polar angle, the second polar diameter, the third polar angle and the third polar diameter, and a plurality of third parameters corresponding to the first fitting circles;
    and obtaining the detection parameters by utilizing a plurality of first fitting circles, a plurality of third parameters and a second preset strategy.
  5. The detection method according to claim 4, wherein the obtaining of the corresponding first polar paths at the plurality of extrema in the second gradient image comprises:
    obtaining gradient values corresponding to the current position in the second gradient image according to a preset sequence;
    judging whether the gradient value is an extreme value or not;
    if so, obtaining a first polar diameter corresponding to the current position, and judging whether the current position is the last position in the second gradient image, if so, ending the step of obtaining the first polar diameters corresponding to the multiple extreme values in the second gradient image; otherwise, obtaining a gradient value corresponding to the position next to the current position, and returning to the step of judging whether the gradient value is an extremum value;
    otherwise, judging whether the current position is the last position in the second gradient image, if so, finishing the step of obtaining the first polar diameters corresponding to the multiple extreme values in the second gradient image; otherwise, obtaining a gradient value corresponding to the next position of the current position, and returning to the step of judging whether the gradient value is an extremum.
  6. The detection method of claim 5, wherein the extreme value comprises a maximum value and a minimum value, and wherein the determining whether the gradient value is an extreme value comprises:
    obtaining a first gradient value and a second gradient value corresponding to two adjacent pixel positions at the left and right of the current position;
    judging whether the gradient value at the current position is greater than or equal to the first gradient value or not and whether the gradient value at the current position is greater than or equal to the second gradient value or not;
    if so, the gradient value at the current position is a maximum value;
    otherwise, further judging whether the gradient value at the current position is smaller than or equal to the first gradient value or not, and whether the gradient value at the current position is smaller than or equal to the second gradient value or not;
    if so, the gradient value at the current position is a minimum value;
    otherwise, the gradient value at the current position is not an extremum.
  7. The detection method according to claim 4, wherein the first polar angle, the second polar angle and the third polar angle satisfy a first preset condition, and the method comprises:
    the absolute value of the difference between the second polar angle and the first polar angle is 180 °, and the absolute value of the difference between the third polar angle and the first polar angle is 90 °.
  8. The method of claim 7, wherein the screening the plurality of second pole diameters to retain at most one of the second pole diameters comprises:
    fitting all the second polar diameters and the second polar angles with the first local polar diameters and the first polar angles respectively to obtain a plurality of second fitting circles and fourth parameters corresponding to the second fitting circles, wherein the fourth parameters comprise circle center coordinates and radiuses corresponding to the second fitting circles;
    acquiring a first local image within a first preset range from a second fitting circle from the region of interest by using the fourth parameter corresponding to the second fitting circle;
    obtaining a third gradient image corresponding to the first partial image;
    obtaining a first contrast of the second fitted circle through the third gradient image;
    scoring the second fitted circle with the first contrast, the first contrast being proportional to a first score;
    and obtaining a second polar diameter corresponding to the second fitting circle with the first score exceeding a first threshold and the highest first score.
  9. The method of claim 8, wherein said screening the plurality of third apertures to retain at most one of the third apertures comprises:
    fitting all the third polar diameters and the third polar angles with the first local polar diameters, the first polar angles, the screened and reserved second polar diameters and the second polar angles respectively to obtain a plurality of third fitting circles and fifth parameters corresponding to the third fitting circles;
    acquiring a second local image within a second preset range from the third fitting circle from the region of interest by using the fifth parameter corresponding to the third fitting circle;
    obtaining a fourth gradient image corresponding to the second local image;
    obtaining a second contrast of the third fitted circle through the fourth gradient image;
    scoring the third fitted circle using the second contrast, the second contrast being proportional to a second score;
    and obtaining a third aperture corresponding to a third fitting circle with the second score exceeding a second threshold and the highest second score.
  10. The method of claim 9, wherein obtaining a plurality of sets of first fitting circles corresponding to the first polar angle, the first local polar diameter, the second polar angle, the second polar diameter, the third polar angle, the third polar diameter, and a plurality of third parameters corresponding to the plurality of first fitting circles comprises:
    and obtaining the third fitting circle corresponding to all the first polar angles and the first local polar diameter, wherein the third polar angles and the first local polar diameters are reserved, the first fitting circle is the third fitting circle, and the third parameter is the fifth parameter.
  11. The method of claim 10, wherein obtaining the detection parameters using the first fitting circles, the third parameters, and the second predetermined strategy comprises:
    and obtaining the circle with the highest second score, the circle with the largest radius, or the circle with the smallest radius in the plurality of first fitting circles, and taking the third parameter corresponding to the circle as a detection parameter.
  12. The method according to claim 8, wherein the fitting all the second polar diameters and second polar angles to the first local polar diameters and the first polar angles, respectively, to obtain a plurality of second fitting circles and fourth parameters corresponding to the plurality of second fitting circles includes:
    converting the second polar diameter, the second polar angle, the first polar angle and the first local polar diameter under a polar coordinate system into a corresponding first coordinate value and a corresponding second coordinate value under a rectangular coordinate system;
    and obtaining the second fitting circle according to the first coordinate value and the second coordinate value, and the fourth parameter corresponding to the second fitting circle in the rectangular coordinate system.
  13. The detection method according to claim 4,
    the obtaining of the one-dimensional histogram corresponding to the first image includes: calculating a pixel gray level average value of the first image in columns to obtain the one-dimensional histogram;
    the obtaining of the first gradient image corresponding to the first image includes: first-order derivation of the first image to obtain the first gradient image;
    the obtaining of the second gradient image corresponding to the one-dimensional histogram includes: first order derivation is performed on the one-dimensional histogram to obtain the second gradient image.
  14. The inspection method of claim 1, wherein said determining a final parameter of said circular feature based on said recorded plurality of inspection parameters and a first predetermined policy comprises:
    and taking the average value of a plurality of detection parameters as a final parameter of the circular feature.
  15. A circular feature detection method, comprising:
    receiving an image to be processed, wherein the image to be processed comprises a circular feature;
    extracting an interested area of the image to be processed, and obtaining a first parameter corresponding to the interested area, wherein the circular feature is located in the interested area, the interested area is a circular ring, and the first parameter comprises a first circle center coordinate, an inner diameter and an outer diameter corresponding to the interested area;
    detecting the circular feature by using the first parameter to obtain a detection parameter corresponding to the circular feature, wherein the detection parameter comprises a detection circle center coordinate and a detection radius;
    adjusting the first parameter by using the detection parameter, returning to the step of detecting the circular feature by using the first parameter, recording the detection parameter obtained after each detection, and updating the value of the iteration parameter after each detection until the value of the iteration parameter exceeds a preset range;
    and determining final parameters of the circular feature according to the recorded detection parameters and a first preset strategy, wherein the final parameters comprise the circle center coordinate and the radius of the circular feature.
  16. The detection method according to claim 15,
    the iteration parameter is the number of times of detecting the circular feature by using the first parameter, and the value of the iteration parameter exceeding a preset range is that the detection number is greater than or equal to a preset value.
  17. The method of claim 15, wherein the adjusting the first parameter using the detection parameter comprises: and taking the detection circle center coordinate in the detection parameters obtained by the last detection as a first circle center coordinate corresponding to the region of interest to adjust the position of the region of interest.
  18. The detecting method according to claim 15, wherein the detecting the circular feature by using the first parameter to obtain a detection parameter corresponding to the circular feature comprises:
    converting the image of the region of interest in a rectangular coordinate system into a first image in a polar coordinate system, wherein the image of the region of interest comprises the circular feature, the abscissa of the first image is a polar diameter, and the ordinate of the first image is a polar angle;
    obtaining a one-dimensional histogram corresponding to the first image, a first gradient image corresponding to the first image and a second gradient image corresponding to the one-dimensional histogram;
    obtaining first polar diameters corresponding to a plurality of extreme values in the second gradient image;
    obtaining a maximum point in the first gradient image within a preset range from each first polar diameter, wherein the polar diameter and the polar angle corresponding to the maximum point are defined as a first local polar diameter and a first polar angle;
    obtaining a second polar angle and a third polar angle corresponding to the first polar angle in the first gradient image, wherein the first polar angle, the second polar angle and the third polar angle meet a first preset condition;
    obtaining a plurality of second polar diameters corresponding to the second polar angles in the first gradient image, and screening the plurality of second polar diameters to reserve at most one second polar diameter;
    obtaining a plurality of third apertures corresponding to the third aperture angles in the first gradient image, and screening the plurality of third apertures to reserve at most one third aperture;
    obtaining a plurality of sets of first fitting circles corresponding to the first polar angle, the first local polar diameter, the second polar angle, the second polar diameter, the third polar angle and the third polar diameter, and a plurality of third parameters corresponding to the first fitting circles;
    and obtaining the detection parameters by utilizing a plurality of first fitting circles, a plurality of third parameters and a second preset strategy.
  19. A circular feature detection processing system comprising a processor, a memory, a transceiver for receiving an image to be processed and transmitting the image to be processed to the processor, and a display for displaying a detection result, the memory storing program instructions that are loadable by the processor and operable to perform the circular feature detection method according to any of claims 1-14 or any of claims 15-18.
  20. An apparatus having a storage function, on which program data are stored, characterized in that the program data, when executed by a processor, implement the steps in the circular feature detection method according to any of claims 1-14 or any of claims 15-18.
CN201880088735.0A 2018-12-29 2018-12-29 Circular feature detection method, processing system and device with storage function Active CN111801709B (en)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2018/125877 WO2020133538A1 (en) 2018-12-29 2018-12-29 Circular feature detection method, processing system and apparatus having storage function

Publications (2)

Publication Number Publication Date
CN111801709A true CN111801709A (en) 2020-10-20
CN111801709B CN111801709B (en) 2023-12-22

Family

ID=71128908

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201880088735.0A Active CN111801709B (en) 2018-12-29 2018-12-29 Circular feature detection method, processing system and device with storage function

Country Status (2)

Country Link
CN (1) CN111801709B (en)
WO (1) WO2020133538A1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113600868A (en) * 2021-06-29 2021-11-05 东风汽车集团股份有限公司 Method and device for determining circle center of cylinder hole and fine boring machine tool

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009259036A (en) * 2008-04-17 2009-11-05 Sharp Corp Image processing device, image processing method, image processing program, recording medium, and image processing system
KR101557271B1 (en) * 2014-06-26 2015-10-06 한밭대학교 산학협력단 Method for detecting a circle-type object and approximating a substitute circle based on Image processing
CN105678763A (en) * 2016-01-05 2016-06-15 吴晓军 A method for stably detecting straight line/ circle features
CN106204542A (en) * 2016-06-29 2016-12-07 上海晨兴希姆通电子科技有限公司 Visual identity method and system
CN106530347A (en) * 2016-09-28 2017-03-22 吴晓军 Stable high-performance circle feature detection method
CN106546174A (en) * 2016-10-26 2017-03-29 湖南大学 A kind of circle detection method based on model filtering

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6859555B1 (en) * 2000-09-19 2005-02-22 Siemens Corporate Research, Inc. Fast dominant circle detection through horizontal and vertical scanning
CN106204540B (en) * 2016-06-29 2018-12-11 上海晨兴希姆通电子科技有限公司 Visible detection method

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009259036A (en) * 2008-04-17 2009-11-05 Sharp Corp Image processing device, image processing method, image processing program, recording medium, and image processing system
KR101557271B1 (en) * 2014-06-26 2015-10-06 한밭대학교 산학협력단 Method for detecting a circle-type object and approximating a substitute circle based on Image processing
CN105678763A (en) * 2016-01-05 2016-06-15 吴晓军 A method for stably detecting straight line/ circle features
CN106204542A (en) * 2016-06-29 2016-12-07 上海晨兴希姆通电子科技有限公司 Visual identity method and system
CN106530347A (en) * 2016-09-28 2017-03-22 吴晓军 Stable high-performance circle feature detection method
CN106546174A (en) * 2016-10-26 2017-03-29 湖南大学 A kind of circle detection method based on model filtering

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113600868A (en) * 2021-06-29 2021-11-05 东风汽车集团股份有限公司 Method and device for determining circle center of cylinder hole and fine boring machine tool
CN113600868B (en) * 2021-06-29 2022-11-08 东风汽车集团股份有限公司 Method and device for determining circle center of cylinder hole and fine boring machine tool

Also Published As

Publication number Publication date
WO2020133538A1 (en) 2020-07-02
CN111801709B (en) 2023-12-22

Similar Documents

Publication Publication Date Title
US11790481B2 (en) Systems and methods for fusing images
US9418319B2 (en) Object detection using cascaded convolutional neural networks
JP5075757B2 (en) Image processing apparatus, image processing program, image processing method, and electronic apparatus
US9305360B2 (en) Method and apparatus for image enhancement and edge verification using at least one additional image
CN107316326B (en) Edge-based disparity map calculation method and device applied to binocular stereo vision
CN107292828B (en) Image edge processing method and device
WO2020083307A1 (en) Method, apparatus, and storage medium for obtaining depth image
Hua et al. Extended guided filtering for depth map upsampling
CN111368717A (en) Sight line determining method and device, electronic equipment and computer readable storage medium
CN110490886B (en) Automatic correction method and system for certificate image under oblique viewing angle
CN111210393A (en) Color image enhancement method and system based on edge extraction and storage medium
CN112150368A (en) Image processing method, image processing device, electronic equipment and computer readable storage medium
CN115457063A (en) Method, device and equipment for extracting edge of circular hole of PCB (printed Circuit Board) and storage medium
CN111179184B (en) Fish-eye image effective region extraction method based on random sampling consistency
CN111553940A (en) Depth image portrait edge optimization method and processing device
CN111801709B (en) Circular feature detection method, processing system and device with storage function
JP2009301181A (en) Image processing apparatus, image processing program, image processing method and electronic device
CN111192214B (en) Image processing method, device, electronic equipment and storage medium
CN113658153B (en) Contour data feature point detection method and device
US8472708B2 (en) Image processor, method for processing image and computer readable medium
CN114693546A (en) Image denoising method and device, electronic equipment and computer readable storage medium
JP5786838B2 (en) Image region dividing apparatus, method, and program
CN113177885A (en) Method, device, storage medium and electronic equipment for correcting image
JP2011171991A (en) Image processing apparatus, electronic device, image processing method and image processing program
CN113344988A (en) Stereo matching method, terminal and storage medium

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
CB02 Change of applicant information

Address after: 518000, Building A, Building 1, Shenzhen International Innovation Valley, Dashi 1st Road, Xili Community, Xili Street, Nanshan District, Shenzhen City, Guangdong Province 1701

Applicant after: Shenzhen Paitian Robot Technology Co.,Ltd.

Address before: 518063 23 Floor (Room 2303-2306) of Desai Science and Technology Building, Yuehai Street High-tech Zone, Nanshan District, Shenzhen City, Guangdong Province

Applicant before: SHENZHEN A&E INTELLIGENT TECHNOLOGY INSTITUTE Co.,Ltd.

CB02 Change of applicant information
GR01 Patent grant
GR01 Patent grant