CN113516608B - Method and device for detecting defects of tire and tire detecting equipment - Google Patents
Method and device for detecting defects of tire and tire detecting equipment Download PDFInfo
- Publication number
- CN113516608B CN113516608B CN202010222164.4A CN202010222164A CN113516608B CN 113516608 B CN113516608 B CN 113516608B CN 202010222164 A CN202010222164 A CN 202010222164A CN 113516608 B CN113516608 B CN 113516608B
- Authority
- CN
- China
- Prior art keywords
- image
- tire
- belt
- gray
- binarized
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 66
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000001514 detection method Methods 0.000 claims abstract description 39
- 238000005260 corrosion Methods 0.000 claims description 32
- 230000007797 corrosion Effects 0.000 claims description 31
- 238000000605 extraction Methods 0.000 claims description 14
- 238000003708 edge detection Methods 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 13
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000003384 imaging method Methods 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 2
- 229910000831 Steel Inorganic materials 0.000 description 14
- 239000010959 steel Substances 0.000 description 14
- 230000002950 deficient Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 5
- 238000003491 array Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 230000000873 masking effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/73—Deblurring; Sharpening
- G06T5/75—Unsharp masking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- 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
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Image Analysis (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Processing (AREA)
Abstract
The invention provides a defect detection method and device for a tire and tire detection equipment, wherein the method comprises the following steps: acquiring an original tire image; extracting a belt layer area image according to the original tire image; extracting a left shoulder region image and a right shoulder region image according to the belt layer region image; and positioning a belt layer differential area according to the width of the left shoulder area image and the width of the right shoulder area image. According to the detection method, the edge image of the tire belt shoulder is detected, so that the belt differential level defect can be effectively detected.
Description
Technical Field
The present invention relates to the field of defect detection technologies, and in particular, to a method for detecting a defect of a tire, a device for detecting a defect of a tire, a tire detecting apparatus, and an electronic apparatus.
Background
At present, a semisteel tire defect recognition algorithm mainly focuses on recognizing defects of impurities, bubbles and steel wires of a crown part, and the recognition algorithm for a belt layer area is less, wherein the belt layer area comprises shoulder areas on two sides and a middle multi-layer steel wire area, the multi-layer steel wire area generates a phenomenon of steel wire intersection in an image due to different inclination directions of different layers of steel wires, and the shoulder areas have no steel wire intersection phenomenon.
Disclosure of Invention
The present invention aims to solve at least one of the technical problems in the related art to some extent.
Therefore, a first object of the present invention is to provide a method for detecting defects of a tire, which can effectively detect belt level defects by detecting edge images of shoulders of a belt of the tire.
A second object of the present invention is to provide a tire defect detecting device.
A third object of the present invention is to propose a tyre detection device.
A fourth object of the present invention is to propose an electronic device.
A fifth object of the present invention is to propose a computer readable storage medium.
To achieve the above object, an embodiment of a first aspect of the present invention provides a method for detecting a defect of a tire, including: acquiring an original tire image; extracting a belt layer area image according to the original tire image; extracting a left shoulder area image and a right shoulder area image according to the belt layer area image; and positioning a belt layer differential area according to the width of the left shoulder area image and the width of the right shoulder area image.
According to the defect detection method of the tire, an original tire image is obtained, a belt layer area image is extracted according to the original tire image, a left shoulder area image and a right shoulder area image are extracted according to the belt layer area image, and a belt layer differential area is positioned according to the width of the left shoulder area image and the width of the right shoulder area image. Therefore, the method can effectively detect the belt level defect by detecting the edge image of the tire belt shoulder.
In addition, the defect detection method for a tire according to the above embodiment of the present invention may further have the following additional technical features:
according to an embodiment of the present invention, the extracting a belt region image from the original tire image includes: performing image enhancement processing on the original tire image to obtain an enhanced tire image; and extracting the belt layer area image according to the reinforced tire image.
According to one embodiment of the present invention, the performing image enhancement processing on the raw tire image to obtain an enhanced tire image includes: and performing image enhancement processing on the original tire image by adopting a sharpening mask method to obtain the enhanced tire image.
According to an embodiment of the present invention, the extracting the belt region image from the reinforced tire image includes: performing relative binarization processing on the reinforced tire image to obtain a relative binarized tire image; positioning the belt layer outer edge according to the relative binarized tire image; and extracting the belt layer area image from the reinforced tire image according to the outer edge of the belt layer.
According to one embodiment of the present invention, the performing a relative binarization process on the reinforced tire image to obtain a relative binarized tire image includes: the relative binarized tire image is obtained by performing the following operation on each pixel in the enhanced tire image: setting a first window with a fixed size by taking the pixel as a center; if the gray value of the pixel in the first window meets the set condition, marking the gray value of the central pixel as 0; if the gray value of the pixel in the first window does not meet the set condition, marking the gray value of the central pixel as 255; the setting condition is that the gray value of the central pixel is smaller than a preset first gray threshold value, and the gray difference between the gray value of the central pixel and the maximum gray value of the pixels in the first window is larger than a preset second gray threshold value.
According to one embodiment of the present invention, the positioning of the belt outer edge from the relatively binarized tire image includes: performing inverse color transformation processing on the relative binarized tire image; sequentially performing expansion and corrosion treatment on the image subjected to the inverse color conversion treatment; performing vertical projection calculation on the image subjected to expansion and corrosion treatment to obtain a vertical projection gray value of each column of pixels; determining a left edge column and a right edge column which are closest to a vertical center line of the image after the expansion and corrosion treatment, wherein the vertical projection gray level value is smaller than a projection gray level threshold value, the projection gray level threshold value is a first set multiple of the maximum value in the vertical projection gray level values, and the first set multiple is smaller than 1; marking the gray value of the pixel positioned at the left side of the left edge column in the image after the expansion and corrosion treatment as 0, and marking the gray value of the pixel positioned at the right side of the edge column in the image after the expansion and corrosion treatment as 0 to obtain a marked image; in each row, a left edge point and a right edge point which are farthest from the vertical center line of the marked image and have a gradation value other than 0 are determined, and a left belt outer edge of the belt outer edges composed of the determined left edge points and a right belt outer edge of the belt outer edges composed of the determined right edge points are obtained.
According to one embodiment of the present invention, the positioning of the belt outer edge from the relatively binarized tire image includes: and performing edge detection on the relative binarized tire image according to the trained edge detection model to obtain the outer edge of the belt layer.
According to one embodiment of the present invention, the extracting a left shoulder region image and a right shoulder region image from the belt region image includes: carrying out local binarization processing on the belt layer area image to obtain a local binarized tire image; and extracting the left shoulder region image and the right shoulder region image according to the local binarized tire image.
According to one embodiment of the present invention, the performing local binarization processing on the belt layer area image to obtain a local binarized tire image includes: setting a second window with a fixed size; traversing the belt area image by utilizing the second window; if the gray value of the central pixel in the second window is larger than a local gray threshold, setting the gray value of the central pixel to 255, wherein the local gray threshold is a second set multiple of the average gray value of the pixels in the second window, and the second set multiple is larger than 1; and if the gray value of the central pixel in the second window is equal to or smaller than the local gray threshold value, setting the gray value of the central pixel to 0.
According to one embodiment of the invention, the extracting the left shoulder region image and the right shoulder region image from the partial binarized tire image includes: deleting the part of the local binarized tire image, the area of which is smaller than a set area threshold value, so as to obtain a tire shoulder area image; sequentially performing expansion and corrosion treatment on the tire shoulder area image; and carrying out median filtering treatment on the edges of the image subjected to the expansion corrosion treatment to obtain the left shoulder region image and the right shoulder region image.
To achieve the above object, a second aspect of the present invention provides a tire defect detecting device, comprising: the image acquisition module is used for acquiring an original tire image; the image extraction module is used for extracting a belt layer area image according to the original tire image, and extracting a left shoulder area image and a right shoulder area image according to the belt layer area image; and the region positioning module is used for positioning the belt ply differential region according to the width of the left shoulder region image and the width of the right shoulder region image.
According to the defect detection device for the tire, an original tire image is obtained through the image obtaining module, a belt layer area image is extracted through the image extracting module according to the original tire image, a left shoulder area image and a right shoulder area image are extracted according to the belt layer area image, and the area locating module locates a belt layer differential area according to the width of the left shoulder area image and the width of the right shoulder area image. Therefore, the device can effectively detect the belt level defect by detecting the edge image of the tire belt shoulder.
To achieve the above object, an embodiment of a third aspect of the present invention provides a tire detecting apparatus including the defect detecting device of a tire described above.
The tire detecting device provided by the embodiment of the invention can effectively detect the belt layer differential level defects through the tire defect detecting device.
To achieve the above object, an embodiment of a fourth aspect of the present invention provides an electronic device, including: the tire defect detection method is realized by the processor when the processor executes the program.
The electronic equipment provided by the embodiment of the invention can effectively detect the belt layer differential level defect by executing the defect detection method of the tire.
To achieve the above object, a fifth aspect of the present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the above-described tire defect detection method.
The computer readable storage medium of the embodiment of the invention can effectively detect the belt layer differential level defect by executing the defect detection method of the tire.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The foregoing and/or additional aspects and advantages of the invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:
FIG. 1 is a flowchart of a method of detecting a defect of a tire according to an embodiment of the present invention;
FIGS. 2a-2b are schematic representations of an original image and a tire image after enhancement of the original tire image, in accordance with one embodiment of the present invention;
FIG. 3 is a schematic representation of a tire image after a relative binarization process according to one embodiment of the present invention;
FIGS. 4 a-4 c are diagrams illustrating recognition results of an edge detection model according to one embodiment of the present invention;
FIGS. 5a and 5b are schematic views of an image after partial binarization of a belt region image according to an embodiment of the present invention;
FIGS. 6a and 6b are schematic illustrations of left and right shoulder region images according to one embodiment of the invention;
FIG. 7 is a schematic boundary view of left and right shoulder region images according to one embodiment of the invention;
FIG. 8 is a block schematic diagram of a tire defect detection apparatus according to an embodiment of the present invention;
FIG. 9 is a block schematic diagram of a tire testing apparatus according to an embodiment of the present invention;
fig. 10 is a block schematic diagram of an electronic device according to an embodiment of the invention.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative and intended to explain the present invention and should not be construed as limiting the invention.
A defect detection method of a tire, a defect detection apparatus of a tire, a tire detection device, and an electronic device according to embodiments of the present invention are described below with reference to the accompanying drawings.
Fig. 1 is a flowchart of a defect detection method of a tire according to an embodiment of the present invention.
As shown in fig. 1, the method for detecting a defect of a tire according to an embodiment of the present invention may include the steps of:
s1, acquiring an original tire image, wherein the original tire image can be obtained through a transmission imaging mode, and the internal structure of the tire can be displayed, for example, the original tire image can be a tire image shot through an X-ray imaging device.
S2, extracting a belt layer area image according to the original tire image.
In one embodiment of the present invention, extracting a belt region image from an original tire image includes:
s21, performing image enhancement processing on the original tire image to obtain an enhanced tire image.
In one embodiment of the present invention, an image enhancement process is performed on an original tire image to obtain an enhanced tire image, including: and performing image enhancement processing on the original tire image by adopting a sharpening mask method to obtain an enhanced tire image.
Specifically, the USM (Unsharp Masking) method is used to enhance the input original tire image, so as to remove some fine interference details and noise, and the main steps are as follows: the original tire image is firstly subjected to Gaussian blur, and then the original image is subtracted by a coefficient which is an empirical value and can be set according to the required enhancement effect, for example, the USM sharpening formula is as follows: (raw tire image-w x gaussian blur)/(1-w); where w represents a weight, i.e., an empirical value, and is typically in the range of: 0.1 to 0.9. Finally, scaling (normalizing) the image to a value between 0 and 255, for example, if the gray value of the subtraction result is smaller than 0, taking 0; if the gray value of the subtraction result is greater than 255, 255 is taken, wherein the original tire image and the tire image after the USM sharpening are shown in fig. 2a and 2b, respectively.
S22, extracting a belt layer area image according to the reinforced tire image.
In one embodiment of the present invention, extracting a belt region image from a reinforced tire image includes: performing relative binarization processing on the reinforced tire image to obtain a relative binarized tire image; positioning the belt layer outer edge according to the relative binarized tire image; and extracting a belt layer area image from the reinforced tire image according to the outer edge of the belt layer.
In one embodiment of the present invention, the method for performing a relative binarization process on a reinforced tire image to obtain a relative binarized tire image includes: each pixel in the enhanced tire image is subjected to the following operation to obtain a relatively binarized tire image: setting a first window with a fixed size by taking the pixel as a center; if the gray value of the pixel in the first window meets the set condition, marking the gray value of the central pixel as 0; if the gray value of the pixel in the first window does not meet the set condition, marking the gray value of the central pixel as 255; the setting condition is that the gray value of the central pixel is smaller than a preset first gray threshold value, and the gray difference between the gray value of the central pixel and the maximum gray value of the pixels in the first window is larger than a preset second gray threshold value, wherein the first gray threshold value can be set according to the gray value of the steel wire (the gray value of the steel wire can be determined according to an empirical value or a mode of counting the average gray value of the steel wire), and the second gray threshold value can be set according to the difference value of the gray value of the steel wire and the white area.
Specifically, the process of performing a relative binarization process on the tire image sharpened by the USM to extract a region with a relatively black color specifically includes: traversing each gray value on the image, setting a window (a first window) with a fixed size by taking the gray value of the pixel as the center, and performing the following operations on the image in the window: when the gray level of the central pixel is smaller than a preset first gray level threshold, the gray level difference between the gray level of the central pixel and the maximum gray level of the pixels in the window is obtained, when the gray level difference is larger than a preset second gray level threshold, the gray level of the central pixel is marked as 0, otherwise, the gray level of the central pixel is marked as 255. Thereby, a region (belt region) having a relatively black color can be extracted, wherein the image after the relatively binarization processing is as shown in fig. 3.
When the gray value of a pixel in the first window satisfies the set condition, the gray value of the pixel may be marked as 0, or when the gray value of the center pixel satisfies the set condition, the gray value of the pixel may be marked as 0.
Further, in one embodiment of the present invention, locating the belt outer edge from the relatively binarized tire image comprises: performing inverse color conversion processing on the relative binarized tire image; sequentially performing expansion and corrosion treatment on the image subjected to the inverse color conversion treatment; performing vertical projection calculation on the image subjected to expansion and corrosion treatment to obtain a vertical projection gray value of each column of pixels; determining a left edge column and a right edge column which are closest to a vertical center line of the image after the expansion and corrosion treatment, wherein the vertical projection gray level value is smaller than a projection gray level threshold value, the projection gray level threshold value is a first set multiple of the maximum value in the vertical projection gray level values, and the first set multiple is smaller than 1; marking the gray value of the pixel positioned at the left side of the left edge row in the image after the expansion and corrosion treatment as 0, and marking the gray value of the pixel positioned at the right side of the right edge row in the image after the expansion and corrosion treatment as 0 to obtain a marked image; in each row, a left edge point and a right edge point which are farthest from the vertical center line of the marked image and have a gradation value other than 0 are determined, resulting in a left belt layer outer edge of belt layer outer edges composed of the determined left edge points and a right belt layer outer edge of belt layer outer edges composed of the determined right edge points.
Wherein determining the left edge column and the right edge column closest to the vertical center line of the image after the expansion and corrosion processing and having the vertical projection gray value smaller than the projection gray threshold value may include: traversing from the middle to two sides of the image after the expansion and corrosion treatment according to the columns, determining a left edge column and a right edge column, traversing leftwards, taking the column as the left edge column when traversing to the first time that the vertical projection gray level value is smaller than the projection gray level threshold value, traversing rightwards, taking the column as the left edge column when traversing to the first time that the vertical projection gray level value is smaller than the projection gray level threshold value, wherein the projection gray level threshold value is a first set multiple of the maximum value in the vertical projection gray level values, and the first set multiple is smaller than 1.
In each row, determining left and right edge points that are farthest from the vertical center line of the marked image and that have gray values other than 0, resulting in a left belt outer edge of belt outer edges composed of the determined left edge points, and a right belt outer edge of belt outer edges composed of the determined right edge points, may include: traversing from the leftmost side to the middle of the marked image by rows, taking the position of the pixel with the gray value of not 0 traversed for the first time in each row as the left belt layer outer edge in the belt layer outer edges, traversing from the rightmost side to the middle of the marked image by rows, and taking the position of the pixel with the gray value of not 0 traversed for the first time in each row as the right belt layer outer edge in the belt layer outer edges. The first preset multiple may be calibrated according to practical situations, for example, the first preset multiple may be 0.03-0.06.
It should be noted that, the left edge row and the right edge row are each linear, and the left belt outer edge and the right belt outer edge of the belt outer edges may be linear or curved, and the latter is a relatively more realistic edge line.
Specifically, the relative binarized tire image is subjected to the inverse color conversion, that is, the original gradation value is 255 to 0, and the original gradation value 0 to 255. Then, the image after the inverse color conversion is subjected to an expansion-before-corrosion treatment. And (3) carrying out vertical projection gray value calculation on the image subjected to the expansion corrosion treatment (specifically, calculating the gray average value of each column of pixels, taking the average value as the vertical projection gray value of the pixels in the column), solving the maximum projection gray value, traversing the image from the middle of the column to the two sides, and when the projection value is smaller than the coefficient (the value can be a fixed value, such as 0.03-0.06, if the projection value is not an edge, the projection value is close to 0.), wherein the column is an edge column of the belt layer, thereby obtaining edge columns (a left edge column and a right edge column) of two belt layers, and marking the gray values of the pixels outside the left edge column and the right edge column as 0. Traversing according to lines, namely from the leftmost edge to the middle of the marked image, and if the projection gray value is not 0, determining the position as the outer edge of the left belt layer; and so on, from the rightmost edge to the middle of the image, if the projection gray value is not 0, the position is the outer edge of the right belt layer, so that the outer edge region of the belt layer can be obtained.
According to another embodiment of the invention, locating the belt outer edge from the relatively binarized tire image comprises: and performing edge detection on the relative binarized tire image according to the trained edge detection model to obtain the outer edge of the belt layer.
Specifically, in order to improve the versatility of the method and the detection accuracy, the edge detection method RCF (Richer Convolutional Features for Edge Detection) may be used to perform detection, and an edge detection model may be established in advance, for example, by labeling the outer edge of the belt layer, an edge detection model may be obtained, and then the outer edge of the belt layer may be directly detected using the detection model. For example, the model is trained using a plurality of tire samples (as shown in the labeled image) that are collected, so as to obtain a detection model capable of identifying the edges of the tire belt, wherein the result of the outer edges of the belt is shown in fig. 4, fig. 4a is an original tire image, fig. 4b is a tire labeling sample, and fig. 4c is a tire detection result.
S3, extracting a left shoulder area image and a right shoulder area image according to the belt layer area image.
In one embodiment of the invention, extracting left and right shoulder region images from a belt region image includes: carrying out local binarization processing on the belt layer area image to obtain a local binarized tire image; and extracting a left shoulder region image and a right shoulder region image according to the local binarized tire image.
In one embodiment of the present invention, the method for performing local binarization processing on a belt layer region image to obtain a local binarized tire image includes: setting a second window with a fixed size; traversing the belt layer area image by the second window; if the gray value of the central pixel in the second window is larger than the local gray threshold, setting the gray value of the pixel to 255, wherein the local gray threshold is a second set multiple of the average gray value of the pixels in the second window, and the second set multiple is larger than 1; if the gray value of the pixel in the second window is equal to or smaller than the local gray threshold, the gray value of the pixel is set to 0, wherein the second preset multiple can be 1.26-1.37.
Specifically, as shown in fig. 5a and 5b, where fig. 5a is a belt region in the extracted USM image, and fig. 5b is a locally binarized image, by which the outer edge of the belt can be obtained, the belt region in the USM image is extracted, and the region is locally binarized, that is, traversed with a window (second window) of a certain fixed size, and when the gray level value of the center pixel in the window is greater than the average gray level value of the window pixel by a second set multiple (the value is an empirical value, for example, may be 1.35), the gray level value of the pixel is set to 255, otherwise, the gray level value of the pixel is 0.
Further, according to an embodiment of the present invention, extracting left and right shoulder region images from a partial binarized tire image includes: deleting the part of the local binarized tire image, the area of which is smaller than the set area threshold value, so as to obtain a tire shoulder area image; sequentially performing expansion and corrosion treatment on the tire shoulder area image; and carrying out median filtering treatment on the edges of the image subjected to the expansion corrosion treatment to obtain a left shoulder region image and a right shoulder region image.
Specifically, the connected domain extraction is performed on the image after the local binarization treatment, the connected domain with small area is set to 0, so that the approximate area of the tire shoulder can be obtained, as shown in the gray area of fig. 6a, the connected domain area of the steel wire crossing part and the area of the steel wire area of the tire shoulder can be approximately counted, and the connected domain area of the steel wire crossing part below 15-25 pixels (namely, the connected domain area of the steel wire crossing part) is generally set and deleted. And performing expansion corrosion operation on the tire shoulder area image to obtain a tire shoulder area, such as a white area in fig. 6b, and then performing median filtering on the tire shoulder edges on the left and right sides to remove the interference of abnormal points, thereby obtaining a left tire shoulder area image and a right tire shoulder area image.
S4, positioning a belt layer differential area according to the width of the left shoulder area image and the width of the right shoulder area image.
Specifically, as shown in fig. 7, two boundary lines of the left shoulder region image and two boundary lines of the right shoulder region image are obtained, wherein the two boundary lines of the left shoulder region image are denoted as a and B, and the two boundary lines of the right shoulder region image are denoted as C and D.
The set positioning criteria may include determining whether the tire is defective based on the width of the left shoulder tire area image, and then considering that the tire is defective when the width between a and B is not within the first preset threshold range. The result of the final positioning may include one or more segments or all regions having a width between a and B that is not within the first preset threshold.
The set positioning criteria may include determining whether the tire is defective based on the width of the right shoulder tire area image, and then considering that the tire is defective when the width between C and D is not within the second preset threshold range. If such a defect is present, the result of the final positioning may include one or more segments or all regions having a width between C and D that is not within the second preset threshold.
The set positioning criterion may include determining whether the tire is defective based on a difference between the width of the left shoulder tire area image and the width of the right shoulder tire area image, and then considering that the tire is defective when the difference between the width between a and B and the width between C and D is not within a third preset threshold range. If such a defect is present, the final positioning result may include: one or more or all of the areas where the difference in width between a and B, C and D is not within the third preset threshold.
The set criteria may include any one of the above three criteria, or any combination of the three criteria, and if the defective area is not located according to all the set criteria, the tire may be considered to be normal.
It should be noted that the first preset threshold range, the second preset threshold range, and the third preset threshold range may be calibrated according to actual situations. In addition, in calculating the difference between the two boundary lines, the average value of each of all the differences between the two boundary lines may be employed as the final width difference between the two boundary lines.
In summary, according to the tire defect detection method of the embodiment of the present invention, an original tire image is obtained, a belt layer region image is extracted according to the original tire image, a left shoulder region image and a right shoulder region image are extracted according to the belt layer region image, and a belt layer differential region is located according to the width of the left shoulder region image and the width of the right shoulder region image. Therefore, the method can effectively detect the belt level defect by detecting the edge image of the tire belt shoulder.
Fig. 8 is a block schematic diagram of a defect detection apparatus for a tire according to an embodiment of the present invention.
As shown in fig. 8, the defect detecting device of the tire according to the embodiment of the present invention may include: an image acquisition module 10, an image extraction module 20, and a region localization module 30.
Wherein the image acquisition module 10 is used for acquiring an original tire image. The image extraction module 20 is used for extracting a belt layer area image according to an original tire image, and extracting a left shoulder area image and a right shoulder area image according to the belt layer area image. The region positioning module 30 is used for positioning the belt differential region according to the width of the left shoulder region image and the width of the right shoulder region image.
According to one embodiment of the present invention, the image extraction module 20 is specifically configured to perform image enhancement processing on the original tire image to obtain an enhanced tire image when extracting the belt area image from the original tire image; and extracting a belt layer area image according to the reinforced tire image.
In accordance with one embodiment of the present invention, the image extraction module 20 is specifically configured to perform image enhancement processing on the original tire image by using a sharpening mask method when performing image enhancement processing on the original tire image to obtain an enhanced tire image.
According to one embodiment of the present invention, the image extraction module 20 is specifically configured to perform a relative binarization process on the reinforced tire image to obtain a relative binarized tire image when extracting the belt area image from the reinforced tire image; positioning the belt layer outer edge according to the relative binarized tire image; and extracting a belt layer area image from the reinforced tire image according to the outer edge of the belt layer.
According to one embodiment of the present invention, the image extraction module 20 performs a relative binarization process on the enhanced tire image to obtain a relative binarized tire image, and is specifically configured to perform the following operation on each pixel in the enhanced tire image to obtain a relative binarized tire image: setting a first window with a fixed size by taking the pixel as a center; if the gray value of the pixel in the first window meets the set condition, marking the gray value of the central pixel as 0; if the gray value of the pixel in the first window does not meet the set condition, marking the gray value of the central pixel as 255; the setting condition is that the gray value of the pixel is smaller than a preset first gray threshold value, and the gray difference between the gray value of the central pixel and the maximum gray value of the pixels in the first window is larger than a preset second gray threshold value.
According to one embodiment of the invention, the image extraction module 20 is specifically configured to perform a color inversion process on the relative binarized tire image when the belt outer edge is located according to the relative binarized tire image; sequentially performing expansion and corrosion treatment on the image subjected to the inverse color conversion treatment; determining a left edge column and a right edge column which are closest to a vertical center line of the image after the expansion and corrosion treatment, wherein the vertical projection gray level value is smaller than a projection gray level threshold value, the projection gray level threshold value is a first set multiple of the maximum value in the vertical projection gray level values, and the first set multiple is smaller than 1; marking the gray value of the pixel positioned at the left side of the left edge row in the image after the expansion and corrosion treatment as 0, and marking the gray value of the pixel positioned at the right side of the right edge row in the image after the expansion and corrosion treatment as 0 to obtain a marked image; in each row, a left edge point and a right edge point which are farthest from the vertical center line of the marked image and have a gradation value other than 0 are determined, resulting in a left belt layer outer edge of belt layer outer edges composed of the determined left edge points and a right belt layer outer edge of belt layer outer edges composed of the determined right edge points.
According to one embodiment of the present invention, the image extraction module 20 is specifically configured to perform edge detection on the relatively binarized tire image according to the trained edge detection model to obtain the belt outer edge when the belt outer edge is located according to the relatively binarized tire image.
According to one embodiment of the present invention, the image extraction module 20 extracts a left shoulder region image and a right shoulder region image according to the belt region image, and is specifically configured to perform local binarization processing on the belt region image to obtain a local binarized tire image; and extracting a left shoulder region image and a right shoulder region image according to the local binarized tire image.
According to one embodiment of the present invention, the image extraction module 20 performs a local binarization process on the belt area image to obtain a local binarized tire image, and is specifically configured to set a second window with a fixed size; traversing the belt layer area image by using a second window; if the gray value of the central pixel in the second window is larger than the local gray threshold, setting the gray value of the central pixel to 255, wherein the local gray threshold is a second set multiple of the average gray value of the pixels in the second window, and the second set multiple is larger than 1; if the gray value of the center pixel in the second window is equal to or smaller than the local gray threshold, the gray value of the center pixel is set to 0.
According to one embodiment of the present invention, the image extraction module 20 extracts a left shoulder region image and a right shoulder region image according to the local binarized tire image, and is specifically configured to delete a portion of the local binarized tire image where the area of the connected region is smaller than a set area threshold value, so as to obtain a shoulder region image; sequentially performing expansion and corrosion treatment on the tire shoulder area image; and carrying out median filtering treatment on the edges of the image subjected to the expansion corrosion treatment to obtain a left shoulder region image and a right shoulder region image.
It should be noted that, for details not disclosed in the defect detection device of the tire according to the embodiment of the present invention, please refer to details disclosed in the defect detection method of the tire according to the embodiment of the present invention, and detailed descriptions thereof are omitted herein.
According to the defect detection device for the tire, an original tire image is obtained through the image obtaining module, a belt layer area image is extracted through the image extracting module according to the original tire image, a left shoulder area image and a right shoulder area image are extracted according to the belt layer area image, and the area locating module locates a belt layer differential area according to the width of the left shoulder area image and the width of the right shoulder area image. Therefore, the device can effectively detect the belt level defect by detecting the edge image of the tire belt shoulder.
Fig. 9 is a block schematic diagram of a tire detecting apparatus according to an embodiment of the present invention.
As shown in fig. 9, the tire detecting apparatus 100 of the embodiment of the present invention may include: the defect detecting device 110 for a tire described above.
The tire detecting device provided by the embodiment of the invention can effectively detect the belt layer differential level defects through the tire defect detecting device.
Fig. 10 is a block schematic diagram of an electronic device according to an embodiment of the invention.
As shown in fig. 10, the electronic device 200 of the embodiment of the present invention may include: the above-described tire defect detection method is implemented by the memory 210, the processor 220, and a computer program stored in the memory 210 and executable on the processor 220, when the processor 220 executes the program.
The electronic equipment provided by the embodiment of the invention can effectively detect the belt layer differential level defect by executing the defect detection method of the tire.
Further, an embodiment of the present invention also proposes a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the above-described tire defect detection method.
The computer readable storage medium of the embodiment of the invention can effectively detect the belt layer differential level defect by executing the defect detection method of the tire.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present invention, the meaning of "plurality" means at least two, for example, two, three, etc., unless specifically defined otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and additional implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order from that shown or discussed, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present invention.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. As with the other embodiments, if implemented in hardware, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, and where the program, when executed, includes one or a combination of the steps of the method embodiments.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules may also be stored in a computer readable storage medium if implemented in the form of software functional modules and sold or used as a stand-alone product.
The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, or the like. While embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the invention.
Claims (14)
1. A method of detecting a defect in a tire, comprising:
acquiring an original tire image, wherein the original tire image is acquired in a transmission imaging mode so as to display the internal structure of the tire;
extracting a belt layer area image according to the original tire image;
extracting a left shoulder area image and a right shoulder area image according to the belt layer area image;
and positioning a belt layer differential area according to the width of the left shoulder area image and the width of the right shoulder area image.
2. The defect detection method according to claim 1, wherein the extracting a belt region image from the original tire image includes:
performing image enhancement processing on the original tire image to obtain an enhanced tire image;
And extracting the belt layer area image according to the reinforced tire image.
3. The defect detection method of claim 2, wherein performing image enhancement processing on the raw tire image to obtain an enhanced tire image comprises:
and performing image enhancement processing on the original tire image by adopting a sharpening mask method to obtain the enhanced tire image.
4. The defect detection method of claim 2, wherein the extracting the belt region image from the enhanced tire image comprises:
performing relative binarization processing on the reinforced tire image to obtain a relative binarized tire image;
positioning the belt layer outer edge according to the relative binarized tire image;
and extracting the belt layer area image from the reinforced tire image according to the outer edge of the belt layer.
5. The method of claim 4, wherein the subjecting the enhanced tire image to a relative binarization process to obtain a relative binarized tire image comprises:
the relative binarized tire image is obtained by performing the following operation on each pixel in the enhanced tire image:
Setting a first window with a fixed size by taking the pixel as a center; if the gray value of the pixel in the first window meets the set condition, marking the gray value of the central pixel as 0; if the gray value of the pixel in the first window does not meet the set condition, marking the gray value of the central pixel as 255; the setting condition is that the gray value of the central pixel is smaller than a preset first gray threshold value, and the gray difference between the gray value of the central pixel and the maximum gray value of the pixels in the first window is larger than a preset second gray threshold value.
6. The defect detection method of claim 4, wherein said locating the belt outer edge from the relatively binarized tire image comprises:
performing inverse color transformation processing on the relative binarized tire image;
sequentially performing expansion and corrosion treatment on the image subjected to the inverse color conversion treatment;
performing vertical projection calculation on the image subjected to expansion and corrosion treatment to obtain a vertical projection gray value of each column of pixels;
determining a left edge column and a right edge column which are closest to a vertical center line of the image after the expansion and corrosion treatment, wherein the vertical projection gray level value is smaller than a projection gray level threshold value, the projection gray level threshold value is a first set multiple of the maximum value in the vertical projection gray level values, and the first set multiple is smaller than 1;
Marking the gray value of the pixel positioned at the left side of the left edge row in the image after the expansion and corrosion treatment as 0, and marking the gray value of the pixel positioned at the right side of the right edge row in the image after the expansion and corrosion treatment as 0 to obtain a marked image;
in each row, a left edge point and a right edge point which are farthest from the vertical center line of the marked image and have a gradation value other than 0 are determined, and a left belt outer edge of the belt outer edges composed of the determined left edge points and a right belt outer edge of the belt outer edges composed of the determined right edge points are obtained.
7. The defect detection method of claim 4, wherein said locating the belt outer edge from the relatively binarized tire image comprises:
and performing edge detection on the relative binarized tire image according to the trained edge detection model to obtain the outer edge of the belt layer.
8. The defect detection method according to claim 1, wherein the extracting left and right shoulder region images from the belt region image includes:
Carrying out local binarization processing on the belt layer area image to obtain a local binarized tire image;
and extracting the left shoulder region image and the right shoulder region image according to the local binarized tire image.
9. The defect detection method according to claim 8, wherein the performing the local binarization processing on the belt layer region image to obtain a local binarized tire image comprises:
setting a second window with a fixed size;
traversing the belt area image by utilizing the second window;
if the gray value of the central pixel in the second window is larger than a local gray threshold, setting the gray value of the central pixel to 255, wherein the local gray threshold is a second set multiple of the average gray value of the pixels in the second window, and the second set multiple is larger than 1;
and if the gray value of the central pixel in the second window is equal to or smaller than the local gray threshold value, setting the gray value of the central pixel to 0.
10. The defect detection method of claim 8, wherein the extracting the left shoulder region image and the right shoulder region image from the partial binarized tire image comprises:
Deleting the part of the local binarized tire image, the area of which is smaller than a set area threshold value, so as to obtain a tire shoulder area image;
sequentially performing expansion and corrosion treatment on the tire shoulder area image;
and carrying out median filtering treatment on the edges of the image subjected to the expansion corrosion treatment to obtain the left shoulder region image and the right shoulder region image.
11. A defect detecting device for a tire, comprising:
the image acquisition module is used for acquiring an original tire image, wherein the original tire image is acquired in a transmission imaging mode so as to display the internal structure of the tire;
the image extraction module is used for extracting a belt layer area image according to the original tire image, and extracting a left shoulder area image and a right shoulder area image according to the belt layer area image;
and the region positioning module is used for positioning the belt ply differential region according to the width of the left shoulder region image and the width of the right shoulder region image.
12. A tire testing apparatus, comprising: the defect detecting apparatus for a tire according to claim 11.
13. An electronic device, comprising: memory, a processor and a computer program stored on the memory and executable on the processor, which processor, when executing the program, implements the method for detecting defects of a tyre according to any one of claims 1 to 10.
14. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, implements a method for detecting defects of a tyre according to any one of claims 1 to 10.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010222164.4A CN113516608B (en) | 2020-03-26 | 2020-03-26 | Method and device for detecting defects of tire and tire detecting equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010222164.4A CN113516608B (en) | 2020-03-26 | 2020-03-26 | Method and device for detecting defects of tire and tire detecting equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113516608A CN113516608A (en) | 2021-10-19 |
CN113516608B true CN113516608B (en) | 2024-03-26 |
Family
ID=78060203
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010222164.4A Active CN113516608B (en) | 2020-03-26 | 2020-03-26 | Method and device for detecting defects of tire and tire detecting equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113516608B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118010738B (en) * | 2024-04-09 | 2024-06-11 | 钛玛科(北京)工业科技有限公司 | Contour-based tire cotton thread extraction method, device, equipment and storage medium |
CN118010739B (en) * | 2024-04-09 | 2024-07-09 | 钛玛科(北京)工业科技有限公司 | Method, device and equipment for detecting metal leakage based on cotton thread distance |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0823623A1 (en) * | 1996-08-06 | 1998-02-11 | Nova C.O.R.D. Ag | Procedure for detecting tyre defects |
JP2008309649A (en) * | 2007-06-14 | 2008-12-25 | Yokohama Rubber Co Ltd:The | Method and device for inspecting tire |
CN104024792A (en) * | 2011-11-07 | 2014-09-03 | 株式会社神户制钢所 | Tire shape inspection method and tire shape inspection device |
CN107230207A (en) * | 2017-06-23 | 2017-10-03 | 合肥美亚光电技术股份有限公司 | The detection method and system of tire |
CN107345921A (en) * | 2017-08-03 | 2017-11-14 | 集美大学 | A kind of tire belt fitting quality determining method and system |
CN108230321A (en) * | 2018-01-19 | 2018-06-29 | 深圳市亿图视觉自动化技术有限公司 | Defect inspection method and device |
CN109154576A (en) * | 2016-05-31 | 2019-01-04 | 倍耐力轮胎股份公司 | Method for checking tire |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP5562278B2 (en) * | 2011-03-15 | 2014-07-30 | 株式会社神戸製鋼所 | Tire shape inspection device and tire shape inspection method |
CN109716095B (en) * | 2016-07-26 | 2022-04-15 | 倍耐力轮胎股份公司 | Method and inspection station for inspecting tyres for vehicle wheels |
-
2020
- 2020-03-26 CN CN202010222164.4A patent/CN113516608B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0823623A1 (en) * | 1996-08-06 | 1998-02-11 | Nova C.O.R.D. Ag | Procedure for detecting tyre defects |
JP2008309649A (en) * | 2007-06-14 | 2008-12-25 | Yokohama Rubber Co Ltd:The | Method and device for inspecting tire |
CN104024792A (en) * | 2011-11-07 | 2014-09-03 | 株式会社神户制钢所 | Tire shape inspection method and tire shape inspection device |
CN109154576A (en) * | 2016-05-31 | 2019-01-04 | 倍耐力轮胎股份公司 | Method for checking tire |
CN107230207A (en) * | 2017-06-23 | 2017-10-03 | 合肥美亚光电技术股份有限公司 | The detection method and system of tire |
CN107345921A (en) * | 2017-08-03 | 2017-11-14 | 集美大学 | A kind of tire belt fitting quality determining method and system |
CN108230321A (en) * | 2018-01-19 | 2018-06-29 | 深圳市亿图视觉自动化技术有限公司 | Defect inspection method and device |
Non-Patent Citations (2)
Title |
---|
全钢载重子午线轮胎零度带束层偏出的原因分析和解决措施;雍占福;杨朔;洪剑;郑涛;;橡胶科技;20140115(第01期);51-53 * |
轮胎X射线0号带束层接头检测定位量化算法的研究;林佳佳;吴则举;刘中冬;;科学技术与工程(第25期);126-130+141 * |
Also Published As
Publication number | Publication date |
---|---|
CN113516608A (en) | 2021-10-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111310558B (en) | Intelligent pavement disease extraction method based on deep learning and image processing method | |
CN111145161B (en) | Pavement crack digital image processing and identifying method | |
CN107808378B (en) | Method for detecting potential defects of complex-structure casting based on vertical longitudinal and transverse line profile features | |
CN110766736B (en) | Defect detection method, defect detection device, electronic equipment and storage medium | |
CN106780486B (en) | Steel plate surface defect image extraction method | |
CN109872303B (en) | Surface defect visual detection method and device and electronic equipment | |
CN101901342B (en) | Method and device for extracting image target region | |
CN108921813B (en) | Unmanned aerial vehicle detection bridge structure crack identification method based on machine vision | |
CN101499164B (en) | Image interpolation reconstruction method based on single low-resolution image | |
CN111080650B (en) | Method for detecting looseness and loss faults of small part bearing blocking key nut of railway wagon | |
CN113516608B (en) | Method and device for detecting defects of tire and tire detecting equipment | |
CN103455994A (en) | Method and equipment for determining image blurriness | |
CN101682767B (en) | Systems and methods for measuring loss of detail in a video codec block | |
CN117094975A (en) | Method and device for detecting surface defects of steel and electronic equipment | |
Ramya et al. | A robust segmentation algorithm using morphological operators for detection of tumor in MRI | |
CN113780110A (en) | Method and device for detecting weak and small targets in image sequence in real time | |
CN114037691A (en) | Carbon fiber plate crack detection method based on image processing | |
CN102509265B (en) | Digital image denoising method based on gray value difference and local energy | |
CN117388256A (en) | Pipeline weld defect detection method based on Swin transducer | |
CN116542963A (en) | Float glass defect detection system and detection method based on machine learning | |
CN112330633B (en) | Jumper wire adhesive tape damage fault image segmentation method based on self-adaptive band-pass filtering | |
CN115797327A (en) | Defect detection method and device, terminal device and storage medium | |
CN115082819A (en) | Food foreign matter detection method and device, computer equipment and storage medium | |
Sengupta et al. | Edge detection in dermascopic images by linear structuring element | |
CN112950665B (en) | Semi-automatic curve-shaped target extraction method and system |
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 |