CN113838122B - Circular high-temperature area positioning method with frequency domain verification - Google Patents
Circular high-temperature area positioning method with frequency domain verification Download PDFInfo
- Publication number
- CN113838122B CN113838122B CN202110846675.8A CN202110846675A CN113838122B CN 113838122 B CN113838122 B CN 113838122B CN 202110846675 A CN202110846675 A CN 202110846675A CN 113838122 B CN113838122 B CN 113838122B
- Authority
- CN
- China
- Prior art keywords
- circular
- image
- matrix
- average amplitude
- deviation
- 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
- 238000012795 verification Methods 0.000 title claims abstract description 26
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000001228 spectrum Methods 0.000 claims abstract description 41
- 238000004364 calculation method Methods 0.000 claims abstract description 16
- 239000011159 matrix material Substances 0.000 claims description 87
- 230000001131 transforming effect Effects 0.000 claims description 4
- 238000011426 transformation method Methods 0.000 claims description 3
- 238000012935 Averaging Methods 0.000 claims description 2
- 230000003595 spectral effect Effects 0.000 claims description 2
- 238000001514 detection method Methods 0.000 abstract description 13
- 238000004458 analytical method Methods 0.000 abstract description 5
- 238000013139 quantization Methods 0.000 abstract description 5
- 230000009466 transformation Effects 0.000 abstract description 5
- 238000007689 inspection Methods 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 6
- 238000000605 extraction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- 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
- G06T2207/20048—Transform domain processing
- G06T2207/20056—Discrete and fast Fourier transform, [DFT, FFT]
-
- 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
- G06T2207/20048—Transform domain processing
- G06T2207/20061—Hough transform
-
- 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
- G06T2207/20076—Probabilistic image processing
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method for positioning a circular high-temperature area with frequency domain verification, which comprises the following steps: analyzing a binarized image of the image to be detected to obtain the center coordinates and the radius of each circular image; windowing each circular image to obtain windowed images; performing Fourier transform on the windowed image to obtain a window spectrum image corresponding to the circular image; and determining the deviation average amplitude value based on the window spectrum image, comparing the deviation average amplitude value with a verification average amplitude value, and judging the probability that the circular image is a circular high-temperature area. The method utilizes a large number of samples to obtain the characteristic standard of the circular high-temperature area, then utilizes the similarity between the characteristic of the detection object and the standard to obtain the probability value of the circular high-temperature area, effectively combines space domain analysis with frequency domain analysis, adopts Hough transformation to realize circular detection of the space domain, adopts window Fourier transformation and characteristic quantization calculation to realize frequency domain inspection, and improves the anti-noise capability of detection.
Description
Technical Field
The invention relates to the field of target object detection, in particular to a method for positioning a circular high-temperature area with frequency domain verification.
Background
The detection of the target object is widely applied to the realization of an automatic production line or hazard early warning. The identification positioning and geometric calculation of the circular area are an important item in the detection of the target object. And a two-dimensional image of the circular high-temperature area is obtained through detection or imaging, and the high-temperature area is identified and positioned on the basis.
At present, related researches propose a concentric ring pattern positioning method, a circular printing image defect detection method and the like, but all have the problem of lower detection accuracy.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a circular high-temperature area positioning method with frequency domain verification, which adopts a Hough transformation method to identify a circular shape and utilizes high temperature.
A method for locating a circular high temperature region with frequency domain verification, comprising:
analyzing a binarized image of the image to be detected to obtain the center coordinates and the radius of each circular image;
windowing each circular image to obtain windowed images;
performing Fourier transform on the windowed image to obtain a window spectrum image corresponding to the circular image;
and determining the deviation average amplitude value based on the window spectrum image, comparing the deviation average amplitude value with a verification average amplitude value, and judging the probability that the circular image is a circular high-temperature area.
Further, the analyzing the binarized image of the image to be detected to obtain the center coordinates and the radius of each circular image includes:
and identifying the ring shape in the binarized image by adopting a Hough transformation method, and calculating to obtain the center coordinates and the radius.
Further, the windowing of each circular image to obtain a windowed image includes: and windowing the circular image by adopting a rectangular frame to obtain the windowed image.
Further, before said determining said average magnitude of deviation based on said windowed spectral image, further comprises:
acquiring a feature-added reference one-dimensional matrix based on a non-circular spectrum image sample;
and determining a circular check average amplitude and a non-circular check average amplitude corresponding to the circular spectrum image sample and the non-circular spectrum image sample based on the characteristic reference one-dimensional matrix.
Further, the acquiring the one-dimensional matrix with the characteristic reference based on the non-circular spectrum image sample comprises the following steps:
selecting a plurality of non-circular spectrum image samples with M multiplied by N pixels, respectively extracting a 1 multiplied by N one-dimensional matrix on a straight line which takes the center of the image as the center in each non-circular spectrum image sample, and calculating by adopting a weighted average method to obtain the characteristic reference one-dimensional matrix, wherein N is a positive integer.
Further, the determining, based on the feature reference one-dimensional matrix, a circular check average amplitude and a non-circular check average amplitude corresponding to the circular spectrum image sample and the non-circular spectrum image sample includes: the circular spectrum image sample and the non-circular spectrum image sample are respectively subjected to the following amplitude calculation method to obtain amplitude matrix data, and the circular check average amplitude and the non-circular check average amplitude are respectively determined based on the corresponding amplitude matrix data:
taking the sample center as a rotation center, and rotationally scanning a preset angle range according to preset resolution to obtain a plurality of one-dimensional traversal matrixes, wherein the length of each one-dimensional traversal matrix is the length of the sample, and the width of each one-dimensional traversal matrix is 1; respectively calculating the deviation of the one-dimensional traversal matrix and the characteristic reference to obtain a deviation matrix; and carrying out Fourier transform on the deviation matrix, and taking a modulus to obtain amplitude matrix data.
Further, in the case where the sizes of the circular spectrum image sample and the non-circular spectrum image sample are 100×100, the one-dimensional traversal matrix of 1×100 is obtained by rotationally scanning from 0 ° to 179 ° with a resolution of 1 ° with the (50, 50) position in the sample as the rotation center.
Further, the fourier transforming the deviation matrix, and taking a modulus to obtain amplitude matrix data, includes: fourier transforming the bias matrix is shown in the following expression:
wherein f (n) is an element in the deviation matrix E; n is the number of the deviation matrix elements which is 180; f (mu) is a bias matrix frequency matrix;
and performing modular calculation on the frequency matrix f (mu) of the deviation matrix to obtain amplitude matrix data, wherein the amplitude matrix data are used for forming a deviation amplitude matrix, extracting the 5 th to 10 th elements in the deviation amplitude matrix and averaging to obtain the deviation average amplitude.
Further, the comparing the deviation average amplitude with the verification average amplitude to determine the probability that the circular image is a circular high temperature region includes:
and obtaining amplitude matrix data based on the amplitude calculation method, and determining the deviation average amplitude based on the corresponding amplitude matrix data.
Further, the comparing the deviation average amplitude with the verification average amplitude to determine the probability that the circular image is a circular high temperature region includes:
comparing the deviation average amplitude with the circular check average amplitude and the non-circular check average amplitude respectively, wherein when the deviation average amplitude is smaller than or equal to the circular check average amplitude, the probability that the window spectrum image is a circular high-temperature area is 100%; when the deviation average amplitude is smaller than or equal to the non-circular check average amplitude, the probability that the window spectrum image is a circular high-temperature area is 0; when the deviation average amplitude is larger than the circular check average amplitude and smaller than the non-circular check average amplitude, the probability that the window spectrum image is a circular high-temperature region is as follows:
wherein ,checking the average amplitude for said circle, +.>And checking the average amplitude value for the non-circular shape.
The invention has at least the following beneficial effects:
the method utilizes a large number of samples to obtain the characteristic standard of the circular high-temperature area, then utilizes the similarity between the characteristic of the detection object and the standard to obtain the probability value of the circular high-temperature area, effectively combines space domain analysis with frequency domain analysis, adopts Hough transformation to realize circular detection of the space domain, adopts window Fourier transformation and characteristic quantization calculation to realize frequency domain inspection, and improves the anti-noise capability of detection.
Other advantageous effects of the present invention will be described in detail in the detailed description section.
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 a method for locating a circular high temperature area with frequency domain verification as disclosed in the present invention.
Fig. 2 is a binarized image of an image to be detected in the method for locating a circular high-temperature region with frequency domain verification disclosed by the invention.
Fig. 3 is a graph of a hough circle detection result of a binarized image in the method for locating a circular high-temperature area with frequency domain verification disclosed by the invention.
Fig. 4 is an effect diagram of a windowed image in the method for locating a circular high temperature region with frequency domain verification disclosed by the invention.
Fig. 5 is a graph showing the effect of window fourier transform in the method for locating a circular high-temperature region with frequency domain verification disclosed by the invention.
Fig. 6 is a graph of a non-singular region window sample characteristic reference effect in the method for positioning a circular high temperature region with frequency domain verification disclosed by the invention.
FIG. 7 is a graph of average amplitude of sample errors in the disclosed method for locating circular high temperature regions with frequency domain verification.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be described in detail below. It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. All other embodiments, based on the examples herein, which are within the scope of the invention as defined by the claims, will be within the scope of the invention as defined by the claims.
As shown in fig. 1, the invention discloses a method for positioning a circular high-temperature area with frequency domain verification, which comprises the following steps:
s1: calculating the center coordinates and the radius: and analyzing the binarized image of the image to be detected to obtain the center coordinates and the radius of each circular image.
S2: wrapping the circle with a window: and windowing each circular image to obtain a windowed image.
S3: fourier transforming the window: and carrying out Fourier transform on the windowed image to obtain a window spectrum image corresponding to the circular image.
S4: and (3) calculating characteristic quantification: and determining the deviation average amplitude value based on the window spectrum image, comparing the deviation average amplitude value with a verification average amplitude value, and judging the probability that the circular image is a circular high-temperature area.
In addition, feature reference matrix extraction is required before feature quantization calculation.
The technical scheme of the present invention will be described in detail with reference to a preferred embodiment.
The image to be detected is subjected to binarization processing to obtain a binarized image as shown in fig. 2, then a circle is identified by Hough transformation, and the center coordinates and the radius are calculated, and the result is shown in the following table 1.
| Round serial number | Center coordinates | Radius of radius | Round intensity value |
| 1 | (690，650) | 14 | 0.55 |
| 2 | (904，816) | 12 | 0.23 |
| 3 | (1054，424) | 13 | 0.21 |
| 4 | (699，1051) | 14 | 0.18 |
| 5 | (1028，572) | 11 | 0.16 |
TABLE 1
The hough transform is annotated in the figure for circular recognition, see fig. 3.
The circle is then wrapped with a window. Preferably, a rectangular frame is adopted, and the effect of the partial image after windowing is shown in fig. 4.
The window is then fourier transformed. The results are shown in FIG. 5. Circles corresponding to circle numbers 1-5 in FIGS. 4 a) through e), respectively.
Before the feature quantization calculation, feature reference matrix extraction is completed.
The reference matrix of 4 groups of non-singular area window image samples is extracted, the extracted matrix is added into a black background for display, and an effect diagram is shown in fig. 6, wherein the lower 4 straight lines are feature matrices manually extracted from 4 groups of samples, and the upper one is a non-singular area window image feature reference matrix B obtained by weighted average of 4 groups of sample feature matrices.
N non-singular area window spectrogram samples (non-circular spectrum image samples) are selected, and because the sample pixels are 100×100, a 1×100 one-dimensional matrix on a highlight straight line taking the center of the image as the end point in each sample is extracted and is marked as A i As shown in formula (1):
A i ＝[a i1 a i2 a i3 ... a i50 ](i＝1,2,3,...,n) (1)
wherein the elements in the array represent the gray value of each pixel point on the highlight straight line.
And calculating a characteristic reference one-dimensional matrix B by adopting a weighted average method, as shown in a formula (2).
Finally, after the feature reference matrix is obtained, feature quantization calculation is performed. Traversing 1 group of singular region window image samples and 4 groups of non-singular region window image samples, wherein the specific method comprises the following steps of:
extracting a 1×100 one-dimensional matrix with the length of 100 pixels, which is centered on the image center (50, 50), in a sample window spectrogram, wherein the expression is shown in the formula (3):
H θ ＝[h θ1 h θ2 h θ3 ... h θ100 ](θ＝0,1,2,3,…,179) (3)
one-dimensional matrix H θ The extraction range of (2) is from horizontal 0 DEG to 179 DEG, and scanning is carried out according to the resolution of 1 DEG, so as to obtain 180 one-dimensional traversal matrixes. The traversing sequence of the error calculation starts from a straight line with y=50, the straight line is rotated clockwise by an angle theta by taking coordinates (50, 50) as the center, a new straight line is obtained, and the coordinates of pixel points on the straight line are shown as formula (4):
one-dimensional matrix H obtained by each traversal in a window spectrogram θ Deviations from the reference matrix result in 180 deviation data per sample, which data are grouped into a 1 x 180 one-dimensional matrix, called the deviation matrix, denoted E.
The spectrogram of the singular area is in a ring shape with alternate brightness, the gray value change among 180 one-dimensional matrixes obtained after linear traversal is mild, and the spectrogram of the non-singular area has obvious gray value change among 180 one-dimensional matrixes after traversal due to the existence of other irregular edges besides circular edges. From the above law it can be derived that: the probability of occurrence of wave peaks and wave troughs of the deviation matrix obtained by calculating the singular region window image is smaller than that of the deviation matrix obtained by calculating the non-singular region window image, and the change is not obvious. I.e. the value of the high frequency band of the deviation matrix of the singular region window image is lower than the deviation matrix of the non-singular region window. It is necessary to fourier transform the deviation matrix E as shown in equation (5) and convert the data into the frequency domain for analysis.
Wherein f (n) is an element in the deviation matrix E; n is the number of the deviation matrix elements which is 180; f (mu) is the bias matrix frequency matrix.
And (5) performing modular calculation on the deviation matrix frequency matrix f (mu) to obtain amplitude matrix data. The amplitude data is formed into a deviation amplitude matrix, which is denoted as EF. In order to analyze the deviation amplitude high-frequency error data, the 5 th to 10 th elements in the EF matrix are extracted, the average value is calculated, and the deviation average amplitude is recorded as sigma.
Calculating error average amplitude values of 1 singular region sample (circular spectrum image sample) and 4 non-singular region samples (non-circular spectrum image sample), as shown in fig. 7, the lower curve is the sample error average amplitude value corresponding to the circular high temperature region, the upper curve is the sample error average amplitude value corresponding to the non-circular high temperature region), and the calculation result of the singular region samples is recorded as sigma Singular character The result of the calculation of the non-singular region is denoted as sigma Nonsingular . Respectively taking the average value of the two groups of data and recording asAs shown in formula (6):
finally, singular region probabilities are calculated. When (when)When the window is a singular region, the probability of the window being a singular region is 100%; when (when)When the window is a singular region, the probability of the window being a singular region is 0; when->When the singular region probability is calculated according to the expression shown in the formula (7):
the results obtained are shown in Table 2 below:
TABLE 2
It can be seen that only the circle with the circle number 1 is verified to be a circular high temperature region.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention.
Claims (4)
1. A method for locating a circular high temperature region with frequency domain verification, comprising:
analyzing a binarized image of the image to be detected to obtain the center coordinates and the radius of each circular image;
windowing each circular image to obtain windowed images;
performing Fourier transform on the windowed image to obtain a window spectrum image corresponding to the circular image;
determining the deviation average amplitude value based on the window spectrum image, comparing the deviation average amplitude value with a verification average amplitude value, and judging the probability that the circular image is a circular high-temperature area;
before said determining said average magnitude of deviation based on said windowed spectral image, further comprising:
acquiring a characteristic reference one-dimensional matrix based on a non-circular spectrum image sample;
determining a circular check average amplitude and a non-circular check average amplitude corresponding to the circular spectrum image sample and the non-circular spectrum image sample based on the characteristic reference one-dimensional matrix;
the obtaining the characteristic reference one-dimensional matrix based on the non-circular spectrum image sample comprises the following steps:
selecting a plurality of non-circular spectrum image samples with M multiplied by N pixels, respectively extracting a 1 multiplied by N one-dimensional matrix on a straight line which takes the center of the image as the center in each non-circular spectrum image sample, and calculating by adopting a weighted average method to obtain the characteristic reference one-dimensional matrix, wherein N is a positive integer;
the determining the circular check average amplitude and the non-circular check average amplitude corresponding to the circular spectrum image sample and the non-circular spectrum image sample based on the characteristic reference one-dimensional matrix comprises the following steps: respectively adopting the following amplitude calculation method to the circular spectrum image sample and the non-circular spectrum image sample to obtain amplitude matrix data, and respectively determining the circular check average amplitude and the non-circular check average amplitude based on the corresponding amplitude matrix data;
taking the sample center as a rotation center, and rotationally scanning a preset angle range according to preset resolution to obtain a plurality of one-dimensional traversal matrixes, wherein the length of each one-dimensional traversal matrix is the length of the sample, and the width of each one-dimensional traversal matrix is 1; respectively calculating the deviation of the one-dimensional traversal matrix and the characteristic reference to obtain a deviation matrix; performing Fourier transform on the deviation matrix, and taking a mode to obtain amplitude matrix data;
in the case that the sizes of the circular spectrum image sample and the non-circular spectrum image sample are 100×100, rotationally scanning from 0 ° to 179 ° with a 1 ° resolution with the position (50, 50) in the sample as a rotation center, obtaining 180 one-dimensional traversal matrices with the sizes of 1×100;
performing fourier transform on the deviation matrix, and taking a modulus to obtain amplitude matrix data, including: fourier transforming the bias matrix is shown in the following expression:
wherein f (n) is an element in the deviation matrix E; n is the number of the deviation matrix elements which is 180; f (mu) is a bias matrix frequency matrix;
performing modular calculation on the frequency matrix f (mu) of the deviation matrix to obtain amplitude matrix data, wherein the amplitude matrix data are used for forming a deviation amplitude matrix, extracting the 5 th to 10 th elements in the deviation amplitude matrix and averaging to obtain the deviation average amplitude;
the comparing the deviation average amplitude with the verification average amplitude to judge the probability that the circular image is a circular high-temperature area comprises the following steps:
and obtaining amplitude matrix data based on the amplitude calculation method, and determining the deviation average amplitude based on the corresponding amplitude matrix data.
2. The method for locating a circular high-temperature area with frequency domain verification according to claim 1, wherein the analyzing the binarized image of the image to be detected to obtain the center coordinates and the radius of each circular image comprises:
and identifying the ring shape in the binarized image by adopting a Hough transformation method, and calculating to obtain the center coordinates and the radius.
3. The method for locating a circular high temperature region with frequency domain verification according to claim 1, wherein the windowing each circular image to obtain a windowed image comprises: and windowing the circular image by adopting a rectangular frame to obtain the windowed image.
4. The method for locating a circular high temperature region with frequency domain verification according to claim 1, wherein comparing the deviation average amplitude with the verification average amplitude, determining the probability that the circular image is a circular high temperature region comprises:
comparing the deviation average amplitude with the circular check average amplitude and the non-circular check average amplitude respectively, wherein when the deviation average amplitude is smaller than or equal to the circular check average amplitude, the probability that the window spectrum image is a circular high-temperature area is 100%; when the deviation average amplitude is smaller than or equal to the non-circular check average amplitude, the probability that the window spectrum image is a circular high-temperature area is 0; when the deviation average amplitude is larger than the circular check average amplitude and smaller than the non-circular check average amplitude, the probability that the window spectrum image is a circular high-temperature region is as follows:
wherein ,checking the average amplitude for said circle, +.>And checking the average amplitude value for the non-circular shape.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110846675.8A CN113838122B (en) | 2021-07-26 | 2021-07-26 | Circular high-temperature area positioning method with frequency domain verification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110846675.8A CN113838122B (en) | 2021-07-26 | 2021-07-26 | Circular high-temperature area positioning method with frequency domain verification |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113838122A CN113838122A (en) | 2021-12-24 |
| CN113838122B true CN113838122B (en) | 2023-10-17 |
Family
ID=78962963
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110846675.8A Active CN113838122B (en) | 2021-07-26 | 2021-07-26 | Circular high-temperature area positioning method with frequency domain verification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113838122B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103925878A (en) * | 2014-04-11 | 2014-07-16 | 南京信息工程大学 | Hole set detection method and system based on Hough round convolution transformation algorithm |
| CN108038854A (en) * | 2017-12-18 | 2018-05-15 | 天津普达软件技术有限公司 | A kind of method for detecting bucket bottom foreign matter |
| CN108121983A (en) * | 2016-11-29 | 2018-06-05 | 蓝盾信息安全技术有限公司 | A kind of text image method for correcting error based on Fourier transformation |
| CN111291706A (en) * | 2020-02-24 | 2020-06-16 | 齐鲁工业大学 | Retina image optic disc positioning method |
| CN111914680A (en) * | 2020-07-13 | 2020-11-10 | 苏州亚朴智能科技有限公司 | Component identification and positioning method based on frequency domain characteristics |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8114306B2 (en) * | 2009-05-22 | 2012-02-14 | International Business Machines Corporation | Method of forming sub-lithographic features using directed self-assembly of polymers |
| CN103196362B (en) * | 2012-01-09 | 2016-05-11 | 西安智意能电子科技有限公司 | A kind of system of the three-dimensional position for definite relative checkout gear of emitter |
-
2021
- 2021-07-26 CN CN202110846675.8A patent/CN113838122B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103925878A (en) * | 2014-04-11 | 2014-07-16 | 南京信息工程大学 | Hole set detection method and system based on Hough round convolution transformation algorithm |
| CN108121983A (en) * | 2016-11-29 | 2018-06-05 | 蓝盾信息安全技术有限公司 | A kind of text image method for correcting error based on Fourier transformation |
| CN108038854A (en) * | 2017-12-18 | 2018-05-15 | 天津普达软件技术有限公司 | A kind of method for detecting bucket bottom foreign matter |
| CN111291706A (en) * | 2020-02-24 | 2020-06-16 | 齐鲁工业大学 | Retina image optic disc positioning method |
| CN111914680A (en) * | 2020-07-13 | 2020-11-10 | 苏州亚朴智能科技有限公司 | Component identification and positioning method based on frequency domain characteristics |
Non-Patent Citations (2)
| Title |
|---|
| Christopher Hollitt."A convolution approach to the circle Hough transform for arbitrary radius".《Springer》.2013,第683-694页. * |
| 杨春岩."一种基于霍夫变换的圆检测方法".《白城师范学院学报》.2016,第30卷(第2期),第65-68页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113838122A (en) | 2021-12-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6598162B2 (en) | Visual identification method of multi-type BGA chip based on linear clustering | |
| CN107798672B (en) | Method and system for measuring width of cut tobacco or cut stem and server with system | |
| CN104123542B (en) | Device and method for positioning hub workpiece | |
| EP3556576B1 (en) | Process and system for the detection of defects in a tyre | |
| CN107301637B (en) | Surface defect detection method for nearly rectangular planar industrial products | |
| CN112699876B (en) | Automatic reading method for various meters of gas collecting station | |
| CN105675626B (en) | A kind of character defect inspection method of tire-mold | |
| CN101256156B (en) | Precision measurement method for flat crack and antenna crack | |
| CN112686920A (en) | Visual measurement method and system for geometric dimension parameters of circular part | |
| CN111311576A (en) | Point cloud information-based defect detection method | |
| US20230230229A1 (en) | Method and apparatus for analyzing biochip image, computer device, and storage medium | |
| CN113269758A (en) | Cigarette appearance detection method and test device based on machine vision | |
| CN115294527A (en) | Subway tunnel damage detection method based on computer vision | |
| US6813377B1 (en) | Methods and apparatuses for generating a model of an object from an image of the object | |
| US6898333B1 (en) | Methods and apparatus for determining the orientation of an object in an image | |
| CN117078679A (en) | Automatic assembly line production detection method for cooling fan based on machine vision | |
| CN114972453B (en) | Improved SAR image region registration method based on LSD and template matching | |
| CN113838122B (en) | Circular high-temperature area positioning method with frequency domain verification | |
| CN110321890B (en) | A digital meter identification method for an electric power inspection robot | |
| CN109948629B (en) | GIS equipment X-ray image fault detection method based on SIFT features | |
| CN115980095A (en) | Chip appearance detection method and system based on machine vision | |
| CN117593300B (en) | PE pipe crack defect detection method and system | |
| CN117314901A (en) | Scale-adaptive chip detection neural network system | |
| CN112330635B (en) | Corn seed internal crack detection method based on correlation filtering | |
| CN114677428B (en) | Transmission line ice thickness detection method based on UAV image processing |
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 |