CN117372365A - Method, computer program product and apparatus for detecting surface defects of compressor blades - Google Patents

Method, computer program product and apparatus for detecting surface defects of compressor blades Download PDF

Info

Publication number
CN117372365A
CN117372365A CN202311335341.XA CN202311335341A CN117372365A CN 117372365 A CN117372365 A CN 117372365A CN 202311335341 A CN202311335341 A CN 202311335341A CN 117372365 A CN117372365 A CN 117372365A
Authority
CN
China
Prior art keywords
compressor blade
gray value
surface defects
image
gradient
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.)
Pending
Application number
CN202311335341.XA
Other languages
Chinese (zh)
Inventor
齐鹏
王锡睿
张绣宇
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.)
Tongji University
Original Assignee
Tongji University
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 Tongji University filed Critical Tongji University
Priority to CN202311335341.XA priority Critical patent/CN117372365A/en
Publication of CN117372365A publication Critical patent/CN117372365A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/20—Image enhancement or restoration using local operators
    • G06T5/30—Erosion or dilatation, e.g. thinning
    • 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
    • G06T2207/10—Image acquisition modality
    • G06T2207/10004—Still image; Photographic image
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Landscapes

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

Abstract

The invention discloses a method, a computer program product and equipment for detecting surface defects of a compressor blade, and relates to the field of defect detection. The detection method comprises the following steps: performing binarization processing on the original image; performing morphological closing operation on the binarized image; and carrying out defect edge detection on the image subjected to morphological closing operation processing by using a Canny algorithm. According to the invention, binarization, closing operation and Canny algorithm are comprehensively applied to the specific problem of surface defect detection of the aero-engine compressor blade in the defect detection field, so that an accurate detection effect is realized; the calculation efficiency is high, and the acquisition time of the detection result is short; the parameter setting has the advantages of accuracy and flexibility, and can well meet the requirements of detection effect and detection time.

Description

Method, computer program product and apparatus for detecting surface defects of compressor blades
Technical Field
The present invention relates to the field of defect detection technology, and more particularly, to a method, a computer program product, and an apparatus for detecting a surface defect of a compressor blade.
Background
The problem of compressor blade wear often occurs in aeroengines during use. The abrasion of the compressor blade needs to be maintained in time, otherwise, great potential safety hazards are caused to the navigation of the aircraft.
At present, the maintenance of the conventional aero-engine compressor blade is mainly realized by disassembling the engine compressor blade by a skilled maintenance worker and then checking and repairing the blade. However, the process of disassembling the compression blades of the engine is complicated, and requires a plurality of workers to complete the process together, and the process of assembling the compression blades after the disassembly is easy to cause additional damage to the compression blades.
The snake-shaped robot with the camera can be applied to the defect detection field, can accurately and conveniently capture and transmit images of the observed surface, see fig. 1, and can judge the state of the image observed surface under the condition that the detection personnel do not perform disassembly operation, so as to further determine a further maintenance strategy.
The computer-aided surface defect detection method can help detection personnel to find surface defects, improves detection speed and accuracy, but has less research in related aspects.
Chinese patent publication No. CN115471738A discloses a method for extracting a photovoltaic developable roof based on high resolution effect, which extracts the photovoltaic developable roof by steps of clipping rectangular areas, principal component analysis, binarization, decision tree classification and threshold classification, masking, canny operator edge detection, and closing operation. The Canny operator edge detection before the closing operation is performed may lead to some edge breaks. Canny operator edge detection typically results in a more continuous edge, but the erosion operation of the closed-loop operation may break the edge into multiple segments. Thus, this method does not meet the need for aircraft engine compressor blade surface defects to be fully detected.
The Chinese patent with publication number CN105260693A discloses a laser two-dimension code positioning method, which performs two-dimension code edge extraction by the steps of brightness equalization, conversion into a gray level diagram, bilateral filtering, binarization, median filtering, closing operation and Canny operator edge detection. Median filtering uses the median value of the pixels in the neighborhood to replace the value of the center pixel. This operation can effectively remove salt and pepper noise or impulse noise in the image, but it can also cause blurring of the edges. Because the pixel values vary significantly near the edge, median filtering replaces the edge pixels with median values in the neighborhood, resulting in blurring of the edge and morphological changes to the edge. Therefore, the median filtering is not suitable for preprocessing the defect detection image, and the method of the patent cannot meet the requirement that the surface defects of the aero-engine compressor blade need to be accurately detected.
The Chinese patent with publication number of CN1 16309780A discloses a water gauge water level identification method based on target detection, which carries out water level line detection by the steps of median filtering, canny operator edge detection, hough transformation, binarization and closing operation. The method uses median filtering operation which can lead the edge to generate morphological change in preprocessing, and places the Canny operator edge detection at a position relatively before. Canny operator edge detection is a computationally intensive operation, and placing the operation in front increases the overall computational complexity, affects the real-time performance of detection, and is not beneficial to surface defect positioning. And the final closing operation also breaks the detected edge into multiple segments. Therefore, this method does not meet the need for an aircraft engine compressor blade surface defect that needs to be detected entirely and accurately.
Disclosure of Invention
In order to conveniently and accurately detect and repair the surface defects of the compressor blade of the aeroengine, the invention provides a method, a computer program product and equipment for detecting the surface defects of the compressor blade.
In order to achieve the above object, in one aspect, the present invention provides a method for detecting a surface defect of a compressor blade, which is characterized by comprising the following steps:
s101, performing binarization processing on an original image of a picture of a compressor blade;
step S102, performing morphological closing operation on the binarized image, namely performing expansion and corrosion on the image;
and step S103, performing defect edge detection on the image subjected to morphological closing operation processing by using a Canny algorithm.
Preferably, in the step S102, the expanding process is that the structuring element traverses all pixels except the edge of the image, and the gray value of each pixel takes the maximum gray value of the pixel in the corresponding structuring element window.
Preferably, in the step S102, the processing of the erosion is that the structuring element traverses all pixels except the image edge, and each pixel gray value takes a gray value minimum value of the pixels in the corresponding structuring element window.
Further, the structuring elements are all of the 5*5 matrix.
Preferably, the Canny algorithm performs defect edge detection including four basic steps:
step S131, smoothing the image by using a Gaussian filter;
step S132, calculating the gradient amplitude and the gradient direction of the pixel point by finite difference;
s133, performing non-maximum suppression on the gradient amplitude;
step S134, detecting and connecting edges by using a double-threshold algorithm.
Further, in the step S131, the gaussian filter width is set to 7; in the step S132, the standard deviation is set to 1.
Further, in the step S133, for a pixel, the gradient direction of the pixel has an included angle θ with the horizontal direction, and the gradient direction is divided into the following four parts according to the magnitude of θ:
horizontal gradient direction: (0, 22.5 ]. Mu. 22.5,0 ]. Mu. (157.5, 180 ]. Mu.180, 157.5)
45 ° gradient direction: (22.5, 67.5) U.S. (157.5, -112.5)
Vertical gradient direction: (67.5, 112.5) U (-112.5, -67.5)
135 ° gradient direction: (112.5, 157.5) U (-67.5, -22.5)
The gray value gradient magnitudes of different adjacent pixels in different gradient directions are compared: if the gray value gradient amplitude of the pixel point is larger than the gray value of the adjacent pixel point in a certain gradient direction, the gray value gradient amplitude of the pixel point is reserved, otherwise, the gray value gradient amplitude of the pixel point is restrained.
Further, in the step S134, the double threshold is set to 0.3 and 0.5.
In another aspect, the present invention provides a computer program product for detecting surface defects of a compressor blade, wherein the computer program, when executed by a processor, implements a method for detecting surface defects of a compressor blade as described above.
In yet another aspect, the present invention provides an apparatus for detecting a surface defect of a compressor blade, comprising an image acquisition device, a memory, and a processor, wherein the apparatus stores executable instructions that, when executed by one or more processors, cause the one or more processors to perform the method for detecting a surface defect of a compressor blade.
Compared with the prior art, the invention has the following advantages or beneficial effects:
(1) According to the invention, binarization, closing operation and Canny algorithm are comprehensively applied to the specific problem of surface defect detection of the aero-engine compressor blade in the defect detection field, so that an accurate detection effect is realized;
(2) The invention has higher calculation efficiency, and shorter acquisition time of the detection result, which can reach 3.61ms;
(3) The parameter setting method has the advantages of accuracy and flexibility, and can well meet the requirements of detection effect and detection time.
Drawings
The invention and its features and advantages will become more apparent from reading of the detailed description of non-limiting embodiments, given with reference to the following drawings.
Fig. 1 is an exemplary diagram of an application scenario of the present invention.
FIG. 2 is a flow chart of a detection method according to an embodiment of the invention.
FIG. 3 is a gray scale view of an aircraft engine compressor blade surface in an embodiment of the invention.
FIG. 4 is a binary image of an aircraft engine compressor blade surface in an embodiment of the invention.
FIG. 5 is a graph of the results of a closed operation of a surface of an aircraft engine compressor blade in accordance with an embodiment of the present invention.
FIG. 6 is a smoothed image of a Gaussian filter of an aircraft engine compressor blade surface in an embodiment of the invention.
FIG. 7 is a graph showing the gradient magnitude calculations for an aircraft engine compressor blade surface in accordance with one embodiment of the present invention.
FIG. 8 is a schematic diagram of a method for non-maximum suppression of gradient magnitude in an embodiment of the invention.
FIG. 9 is an image of an aircraft engine compressor blade surface with non-maximum suppression of gradient magnitude in an embodiment of the invention.
FIG. 10 is a graph of a Canny algorithm defect edge detection of an aircraft engine compressor blade surface in accordance with an embodiment of the present invention.
Detailed Description
The invention will now be further described with reference to the accompanying drawings and specific examples, which are not intended to limit the invention.
In the following detailed description, numerous specific details are set forth in order to provide a more thorough understanding of the invention. However, it will be apparent to those skilled in the art that well-known algorithms and models are not shown in detail in order to avoid obscuring the principles of the present invention.
The order of execution of the operations, steps, and the like in the apparatus and methods shown in the claims, the specification, and the drawings may be in any order as long as the order is not particularly limited, and the output of the preceding process is not used in the subsequent process.
Example 1
Referring to fig. 2, the present embodiment provides a method for detecting a surface defect of a compressor blade, which is based on image processing of a photograph of the compressor blade, and specifically includes the following steps:
step S101, binarizing the original image of the compressor blade photo. Specifically, the original image is a black and white photograph of the surface of an aircraft engine compressor blade. The binarization is to set the gray value of each pixel point on the original image to 0 or 255, that is, the gray value of the pixel point is converted to 255 when the gray value of the pixel point is greater than or equal to a threshold value, and the gray value of the pixel point is converted to 0 when the gray value of the pixel point is less than a threshold value. The binarized image is only black and white.
Step S102, performing morphological closing operation on the binarized image, namely performing expansion and corrosion on the image. The closed operation is a mathematical morphology processing tool with a certain noise reduction effect, and the specific meaning is that the image is firstly expanded and then corroded. As shown in the following formula, a is a two-dimensional matrix of pixel points of the processed image, and B is a structuring element.
Preferably, the expanding process is that the structuring element traverses all pixels except the image edge, and each pixel gray value takes the gray value maximum value of the pixel in the corresponding structuring element window. The processing of the corrosion is that the structuring element traverses all pixel points except the image edge, and the gray value of each pixel point takes the minimum gray value of the pixel point in the corresponding structuring element window.
Step S101 and step S102 are steps of preprocessing an image.
And step S103, performing defect edge detection on the image subjected to morphological closing operation processing by using a Canny algorithm. As a preferred technical solution, the Canny algorithm for defect edge detection includes four basic steps:
step S131, smoothing the image by using a Gaussian filter. Specifically, the gaussian filter is capable of both anti-noise interference and accurate edge detection. The gaussian filter processes the image specifically as shown in the following equation. h (x, y, sigma) is a Gaussian filter function, and Gaussian filter smoothing is carried out on the gray value f (x, y) of the pixel point of the image to obtain the gray value g (x, y) of the pixel point after processing.
g(x，y)＝h(x，y，σ)*f(x，y)
Step S132, calculating the gradient amplitude and the gradient direction of the pixel point by finite difference. Specifically, the gray value of the pixel point of the image processed by the Gaussian filter is g (x, y), and the partial derivatives of x and y are calculated by using the finite difference of the first-order partial derivatives:
g (x, y) is the magnitude of the gray value gradient, representing the edge intensity of the image. θ (x, y) is the azimuth angle of the gray value gradient. When G (x, y) is locally maximum, θ (x, y) reflects the edge direction of the image. And replacing the gray value with the gray value gradient amplitude as a numerical value in the two-dimensional matrix of the image.
And S133, performing non-maximum suppression on the gradient amplitude to reserve the point with the maximum local gradient so as to refine the edge and eliminate stray response caused by edge detection.
Step S134, detecting and connecting edges by using a double-threshold algorithm. Specifically, a dual threshold value uses a high threshold value and a low threshold value to distinguish edge pixels. Comparing the gray value gradient amplitude of the pixel point with a high threshold value and a low threshold value, and if the gradient amplitude is larger than the high threshold value, the pixel point is an edge pixel; if the gradient magnitude is less than the low threshold, the gradient magnitude of the pixel is removed. After the process, the obtained graph is the surface defect profile of the aero-engine compressor blade.
The technical scheme of the invention is described in more detail below through specific implementation examples.
The raw image to be processed in this example is shown in fig. 3 as a gray scale image of the surface of an aircraft engine compressor blade.
Step one, binarizing. The binarization process was performed on fig. 3 using MATLAB R2021a programming. And taking the binarization threshold value as 127, converting into 255 when the gray value of the pixel point is more than or equal to 127, and converting into 0 when the gray value of the pixel point is less than 127. The resulting binarized image is shown in fig. 4.
And step two, closing operation. The closed operation is performed on fig. 4 by using MATLAB R2021a programming, that is, expansion is performed before corrosion, the structural elements are all of the 5*5 matrix, each gray value of a pixel point firstly takes the maximum value of the gray value of the pixel point in the corresponding 5*5 matrix, and then takes the minimum value of the gray value of the pixel point in the corresponding 5*5 matrix. The result of the closing operation is shown in fig. 5.
And thirdly, detecting the defect edge by using a Canny algorithm. The edge detection by MATLAB R2021a programming using the Canny algorithm includes the four basic steps:
(1) The image is smoothed using a gaussian filter. The gaussian filter width is set to 7 and the standard deviation is set to 1. The image after the gaussian filter smoothing is shown in fig. 6.
(2) And calculating the gradient amplitude and direction of the pixel point by finite difference. The gradient magnitude calculation is shown in fig. 7.
(3) Non-maximum suppression of gradient magnitude is performed. As shown in fig. 8, a pixel point is P, the included angle between the gradient direction and the horizontal direction is θ, and the gradient direction is divided into the following four parts according to the magnitude of θ.
Horizontal gradient direction: (0, 22.5 ]. Mu. 22.5,0 ]. Mu. (157.5, 180 ]. Mu.180, 157.5)
45 ° gradient direction: (22.5, 67.5) U.S. (157.5, -112.5)
Vertical gradient direction: (67.5, 112.5) U (-112.5, -67.5)
135 ° gradient direction: (112.5, 157.5) U (-67.5, -22.5)
Comparing the gray value gradient magnitudes of different adjacent pixels in different gradient directions; if the gray value gradient amplitude of the pixel point is larger than the gray value of the adjacent pixel point in a certain gradient direction, the gray value gradient amplitude of the pixel point is reserved, otherwise, the gray value gradient amplitude of the pixel point is restrained. As shown in FIG. 8, when the P-point gray scale value has a horizontal gradient direction, P and D are determined 1 、D 2 Comparing the gray value gradient amplitude, if the gray value gradient amplitude of P is larger than D 1 、D 2 The pixel gray value gradient magnitude is preserved, otherwise suppressed. 45 degree gradient direction corresponds to C 1 、C 2 Comparing the vertical gradient direction with B 1 、B 2 Comparing the 135 degree gradient direction corresponding to A 1 、A 2 A comparison is made. An image of the gradient magnitude with non-maximum suppression is shown in fig. 9.
(4) Edges are detected and connected using a double threshold algorithm. The double threshold is set to 0.3 and 0.5. The detection and connection of edges using the double threshold algorithm is shown in fig. 10.
From the results of the examples, it can be clearly seen that the method comprehensively applies the binarization, the closing operation and the Canny algorithm to the specific problem of the surface defect detection of the aero-engine compressor blade in the defect detection field, and realizes the accurate detection effect. The program of the embodiment has higher calculation efficiency, and the acquisition time of the detection result is shorter and can reach 3.61ms; the parameter setting method has the advantages of accuracy and flexibility, and can well meet the requirements of detection effect and detection time.
Example 2
The present embodiment provides a computer program product for detecting surface defects of a compressor blade, which when being executed by a processor implements a method for detecting surface defects of a compressor blade as described above. The above functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Example 3
The embodiment provides an apparatus for detecting surface defects of a compressor blade, which comprises an image acquisition device, a memory and a processor, wherein executable instructions are stored in the processor, and when the executable instructions are executed by the processor or the processors, the processor or the processors can be caused to execute the method for detecting the surface defects of the compressor blade.
In summary, the invention provides a method, a computer program product and equipment for detecting surface defects of a compressor blade, and relates to the field of defect detection. The detection method comprises the following steps: performing binarization processing on the original image; performing morphological closing operation on the binarized image; and carrying out defect edge detection on the image subjected to morphological closing operation processing by using a Canny algorithm. According to the invention, binarization, closing operation and Canny algorithm are comprehensively applied to the specific problem of surface defect detection of the aero-engine compressor blade in the defect detection field, so that an accurate detection effect is realized; the calculation efficiency is high, and the acquisition time of the detection result is short; the parameter setting has the advantages of accuracy and flexibility, and can well meet the requirements of detection effect and detection time.
Those skilled in the art will understand that the skilled person can implement the modification in combination with the prior art and the above embodiments, and this will not be repeated here. Such modifications do not affect the essence of the present invention, and are not described herein.
The preferred embodiments of the present invention have been described above. It is to be understood that the invention is not limited to the specific embodiments described above, wherein devices and structures not described in detail are to be understood as being implemented in a manner common in the art; any person skilled in the art can make many possible variations and modifications to the technical solution of the present invention or modifications to equivalent embodiments without departing from the scope of the technical solution of the present invention, using the methods and technical contents disclosed above, without affecting the essential content of the present invention. Therefore, any simple modification, equivalent variation and modification of the above embodiments according to the technical substance of the present invention still fall within the scope of the technical solution of the present invention.
Those of ordinary skill in the art will appreciate that the elements of the various examples described in connection with the present embodiments, i.e., the algorithm steps, can be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

Claims (10)

1. The method for detecting the surface defects of the compressor blade is characterized by comprising the following steps of:
s101, performing binarization processing on an original image of a picture of a compressor blade;
step S102, performing morphological closing operation on the binarized image, namely performing expansion and corrosion on the image;
and step S103, performing defect edge detection on the image subjected to morphological closing operation processing by using a Canny algorithm.
2. The method according to claim 1, wherein in the step S102, the expanding process is that the structuring element traverses all pixels except the image edge, and each pixel gray value takes the gray value maximum value of the pixel in the corresponding structuring element window.
3. The method according to claim 2, wherein in the step S102, the erosion is performed by traversing all pixels except the image edge by the structuring element, and each pixel gray value takes a gray value minimum value of the pixels in the corresponding structuring element window.
4. A method of detecting surface defects of a compressor blade according to claim 2 or claim 3, wherein the structuring elements are all of the 5*5 matrix.
5. A method for detecting surface defects of a compressor blade according to claim 1 or 3, wherein the Canny algorithm comprises four basic steps:
step S131, smoothing the image by using a Gaussian filter;
step S132, calculating the gradient amplitude and the gradient direction of the pixel point by finite difference;
s133, performing non-maximum suppression on the gradient amplitude;
step S134, detecting and connecting edges by using a double-threshold algorithm.
6. The method for detecting surface defects of a compressor blade according to claim 5, wherein in said step S131, the gaussian filter width is set to 7; in the step S132, the standard deviation is set to 1.
7. The method for detecting surface defects of a compressor blade according to claim 5, wherein in the step S133, for a pixel, an included angle between a gradient direction and a horizontal direction is θ, and the gradient direction is divided into four parts according to the magnitude of θ:
the horizontal gradient direction is (0, 22.5) U (-22.5,0) U (157.5, 180) U (-180, 157.5)
45 DEG gradient direction (22.5, 67.5]
Perpendicular gradient direction (67.5, 112.5U (-112.5, -67.5)
135 DEG gradient direction (112.5, 157.5]
The gray value gradient magnitudes of different adjacent pixels in different gradient directions are compared: if the gray value gradient amplitude of the pixel point is larger than the gray value of the adjacent pixel point in a certain gradient direction, the gray value gradient amplitude of the pixel point is reserved, otherwise, the gray value gradient amplitude of the pixel point is restrained.
8. The method for detecting surface defects of a compressor blade according to claim 6, wherein in the step S134, the double threshold is set to 0.3 and 0.5.
9. A computer program product for detecting surface defects of a compressor blade, characterized in that the computer program, when executed by a processor, implements a method for detecting surface defects of a compressor blade according to any one of claims 1 to 8.
10. An apparatus for detecting surface defects of a compressor blade, comprising image acquisition means, a memory, a processor, characterized in that it stores executable instructions that, when executed by one or more processors, cause the one or more processors to perform the method for detecting surface defects of a compressor blade according to any one of claims 1 to 8.
CN202311335341.XA 2023-10-16 2023-10-16 Method, computer program product and apparatus for detecting surface defects of compressor blades Pending CN117372365A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311335341.XA CN117372365A (en) 2023-10-16 2023-10-16 Method, computer program product and apparatus for detecting surface defects of compressor blades

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311335341.XA CN117372365A (en) 2023-10-16 2023-10-16 Method, computer program product and apparatus for detecting surface defects of compressor blades

Publications (1)

Publication Number Publication Date
CN117372365A true CN117372365A (en) 2024-01-09

Family

ID=89407153

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311335341.XA Pending CN117372365A (en) 2023-10-16 2023-10-16 Method, computer program product and apparatus for detecting surface defects of compressor blades

Country Status (1)

Country Link
CN (1) CN117372365A (en)

Similar Documents

Publication Publication Date Title
US8413493B1 (en) Method for detecting a defect on an operating turbine rotor blade
CN107808161B (en) Underwater target identification method based on optical vision
Sun et al. Automated pavement distress detection using advanced image processing techniques
Nayyeri et al. Foreground–background separation technique for crack detection
WO2021118463A1 (en) Defect detection in image space
CN117593294B (en) Centrifugal fan blade crack visual detection method based on image feature analysis
CN107993219A (en) A kind of deck of boat detection method of surface flaw based on machine vision
CN111652825A (en) Edge tracking straight line segment rapid detection device and method based on gradient direction constraint
Peng et al. Non-uniform illumination image enhancement for surface damage detection of wind turbine blades
CN113516619A (en) Product surface flaw identification method based on image processing technology
CN115564710A (en) Fire smoke detection method and device based on LK optical flow method and storage medium
CN117237330B (en) Automatic bridge defect detection method based on machine vision
CN112950594A (en) Method and device for detecting surface defects of product and storage medium
CN111127450B (en) Bridge crack detection method and system based on image
CN117372365A (en) Method, computer program product and apparatus for detecting surface defects of compressor blades
Lin et al. Detection of surface variations on curved mirrors of vehicles using slight deviation control techniques
Nguyen et al. A novel automatic concrete surface crack identification using isotropic undecimated wavelet transform
Yasmin et al. Performance Study of Soft Local Binary Pattern over Local Binary Pattern under Noisy Images
CN112785594B (en) Automatic bridge structure crack identification method based on image two-dimensional amplitude estimation
CN105678704B (en) A kind of non local intermediate value blind landing method for de-noising of view-based access control model perception
CN115049641A (en) Electric data processing method and system for anomaly detection of mechanical parts
CN111105408B (en) Building surface crack detection method and system based on image processing
Mustapha et al. Crack Detection on Surfaces Using Digital Image Processing
CN116818778B (en) Rapid and intelligent detection method and system for automobile parts
CN115526867B (en) Method and device for extracting crack defects of X-ray image of carbon fiber composite gas cylinder

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