CN116721058A - OPC drum surface defect detection method, system, electronic device and storage medium - Google Patents
OPC drum surface defect detection method, system, electronic device and storage medium Download PDFInfo
- Publication number
- CN116721058A CN116721058A CN202310504458.XA CN202310504458A CN116721058A CN 116721058 A CN116721058 A CN 116721058A CN 202310504458 A CN202310504458 A CN 202310504458A CN 116721058 A CN116721058 A CN 116721058A
- Authority
- CN
- China
- Prior art keywords
- image
- defect
- opc drum
- algorithm
- processed
- 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
Links
- 230000007547 defect Effects 0.000 title claims abstract description 150
- 238000001514 detection method Methods 0.000 title claims abstract description 38
- 238000003860 storage Methods 0.000 title claims abstract description 12
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 85
- 238000012545 processing Methods 0.000 claims abstract description 59
- 238000000034 method Methods 0.000 claims abstract description 46
- 230000004927 fusion Effects 0.000 claims abstract description 20
- 238000003062 neural network model Methods 0.000 claims abstract description 10
- 230000011218 segmentation Effects 0.000 claims description 40
- 238000003708 edge detection Methods 0.000 claims description 26
- 238000011049 filling Methods 0.000 claims description 20
- 238000001914 filtration Methods 0.000 claims description 19
- 230000006870 function Effects 0.000 claims description 17
- 238000000605 extraction Methods 0.000 claims description 14
- 230000000877 morphologic effect Effects 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 10
- 230000002950 deficient Effects 0.000 claims description 8
- 238000005260 corrosion Methods 0.000 claims description 6
- 230000003044 adaptive effect Effects 0.000 claims description 5
- 230000007797 corrosion Effects 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 4
- 230000004807 localization Effects 0.000 claims description 3
- 238000004891 communication Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 7
- BUGBHKTXTAQXES-UHFFFAOYSA-N Selenium Chemical compound [Se] BUGBHKTXTAQXES-UHFFFAOYSA-N 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 6
- 239000011669 selenium Substances 0.000 description 6
- 229910052711 selenium Inorganic materials 0.000 description 6
- 238000005530 etching Methods 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 5
- 239000000463 material Substances 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 238000003709 image segmentation Methods 0.000 description 3
- 238000002372 labelling Methods 0.000 description 3
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 description 2
- 229910052782 aluminium Inorganic materials 0.000 description 2
- 239000004020 conductor Substances 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000036039 immunity Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 235000002566 Capsicum Nutrition 0.000 description 1
- 239000006002 Pepper Substances 0.000 description 1
- 235000016761 Piper aduncum Nutrition 0.000 description 1
- 235000017804 Piper guineense Nutrition 0.000 description 1
- 244000203593 Piper nigrum Species 0.000 description 1
- 235000008184 Piper nigrum Nutrition 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- DBULDCSVZCUQIR-UHFFFAOYSA-N chromium(3+);trisulfide Chemical compound [S-2].[S-2].[S-2].[Cr+3].[Cr+3] DBULDCSVZCUQIR-UHFFFAOYSA-N 0.000 description 1
- 239000011248 coating agent Substances 0.000 description 1
- 238000000576 coating method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011109 contamination Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000005669 field effect Effects 0.000 description 1
- 238000005429 filling process Methods 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 239000012212 insulator Substances 0.000 description 1
- 238000007648 laser printing Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 235000012434 pretzels Nutrition 0.000 description 1
- 238000007639 printing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 150000003839 salts Chemical class 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 230000000007 visual effect Effects 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/34—Smoothing or thinning of the pattern; Morphological operations; Skeletonisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/54—Extraction of image or video features relating to texture
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
-
- 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
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Quality & Reliability (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The application provides a method, a system, electronic equipment and a storage medium for detecting surface defects of an OPC drum, and belongs to the field of detection of surface defects of photosensitive elements of printers; the method comprises the steps of collecting an outer surface image of an OPC drum to be inspected through an LED scanner; processing the outer surface image based on an image enhancement method to obtain an image to be processed; dividing an image to be processed by adopting a fusion dividing algorithm; processing the segmented image to be processed based on a defect positioning algorithm to obtain a defect area image; extracting and selecting characteristics of the defect area image to obtain corresponding defect classification characteristics; and identifying defect classification characteristics through the BP neural network model to obtain the defect type of the OPC drum to be inspected. By the application, the automation of OPC drum surface defect detection and the accurate identification of defect types can be realized.
Description
Technical Field
The application belongs to the technical field of detection of surface defects of photosensitive elements of printers, and particularly relates to a method, a system, electronic equipment and a storage medium for detecting the surface defects of an OPC drum.
Background
The photoconductor drum is the most central photosensitive element in CR-G. Its name is very various, and some computer professionals are familiar with it as a selenium drum, but its standard name is a photosensitive drum. These designations are due to the differences in the materials from which they are made. One type of organic photoconductor drum is in a tubular structure, and is called an OPC drum for short, and the full name of OPC is Organic Photo Conductor. Corresponding to the above, there are photosensitive drums produced by using an inorganic photosensitive material, such as a selenium drum and a chromium sulfide drum. However, since selenium is more expensive than gold, selenium drums are practically free of selenium components or contain only very small amounts of selenium. Because of the advantages of inexpensive and low contamination of OPC drums, most of the currently produced photoconductor drums are primarily OPC drums.
The OPC drum is a photoelectric conversion device formed by coating OPC material on the surface of a conductive aluminum cylinder, and is characterized in that the OPC drum is an insulator in the dark, can maintain a certain static charge, becomes a conductor after being irradiated by light with a certain wavelength, and releases the charge through aluminum base to form an electrostatic latent image. OPC drums are an important photosensitive component in printers and are a central component for laser printing and digital copying. The surface quality of an OPC drum is an important indicator for evaluating the grade of photosensitive materials, and the quality of the surface quality will also directly affect the performance and quality of the printer product. Because the OPC drum production process is inevitably free from surface defects of different types such as inclusion, scratches, roll marks, bubbles, chromatic aberration and the like, most of production enterprises at present do picture acquisition through cameras, and then arrange specific personnel to detect the surface defects on line, so that the production efficiency is affected, moreover, the probability of missing detection is increased due to easy fatigue, and the quality cannot be guaranteed. In addition, the defect type cannot be accurately analyzed by online detection, so that timely adjustment of the production process and the jig at the time is not facilitated, and the production cost is high.
Therefore, how to design a method for detecting the OPC drum product to realize the automation of OPC drum surface defect detection and the accurate identification of defect type is a problem to be solved by those skilled in the art.
Disclosure of Invention
In order to solve the technical problems, the invention provides an OPC drum surface defect detection method, an OPC drum surface defect detection system, an electronic device and a storage medium, which can realize the automation of OPC drum surface defect detection and the accurate identification of defect types.
In a first aspect, the invention provides a method of detecting a surface defect of an OPC drum, comprising:
acquiring an outer surface image of the OPC drum to be inspected through an LED scanner;
processing the outer surface image based on an image enhancement method to obtain an image to be processed;
dividing the image to be processed by adopting a fusion dividing algorithm; the fusion segmentation algorithm comprises an edge detection algorithm and a morphological segmentation algorithm;
processing the segmented image to be processed based on a defect positioning algorithm to obtain a defect area image;
extracting and selecting characteristics of the defect area image to obtain corresponding defect classification characteristics;
and identifying the defect classification characteristic through a BP neural network model to obtain the defect type of the OPC drum to be inspected.
In some preferred embodiments, the step of capturing an image of the exterior surface of the OPC drum to be inspected by the LED scanner comprises:
detecting brightness of an image of the outer surface of the OPC drum to be inspected in the scanning of the LED scanner through a circuit;
controlling the rotational speed of the OPC drum to be inspected according to the change of the brightness;
and adjusting the brightness of the scanning lamp of the LED scanner according to the brightness in the changing state.
In some preferred embodiments, the step of processing the outer surface image based on the image enhancement method to obtain the image to be processed specifically includes:
graying the outer surface image by a weighted average method to obtain a gray image;
reducing a plurality of noises in the gray level image through improved median filtering to obtain an image to be processed; the improved median filtering adopts different processing modes according to different characteristics of noise points and edge points, and can make a judgment according to the conditions in the neighborhood.
In some preferred embodiments, the step of segmenting the image to be processed using a fusion segmentation algorithm includes:
performing edge detection on the outer surface image subjected to gray scale processing by adopting a Canny edge detection algorithm to obtain a first processing result;
Calculating the morphological gradient of the image to be processed through a prefabricated formula to obtain a second processing result;
fusing the pixel value of each pixel point in the first processing result with the pixel value of the corresponding point in the second processing result to obtain the fused image of the image to be processed;
determining a first preset threshold based on an improved maximum inter-class variance algorithm principle;
and carrying out binary segmentation on the fused image according to the first preset threshold value so as to segment the image to be processed.
In some preferred embodiments, the step of obtaining the defect area image based on the segmented image to be processed by the defect localization algorithm specifically includes:
expanding the segmented image to be processed to connect the intermittent edges to form a closed contour;
carrying out region filling treatment on the image region of the closed contour by adopting a seed filling algorithm;
carrying out corrosion treatment on the filled image area;
denoising the corroded image area by adopting a denoising algorithm;
and traversing the image area after noise removal, and finding out the marks corresponding to all the closed outlines to locate an accurate defect area.
In some preferred embodiments, the seed points in the seed filling algorithm are obtained using a label connected component algorithm.
In some preferred embodiments, the step of extracting features of the defect area image and selecting to obtain corresponding defect classification features of the defect area image specifically includes:
extracting statistical features of the defect area image by adopting an adaptive feature extraction method; wherein the statistical features include gray scale features, shape features, and texture features;
calculating a corresponding criterion function value of each feature in the statistical features through a divisibility criterion function;
sorting the criterion function values from big to small;
and selecting the preset number of features which are ranked at the front as a selection result to obtain the defect classification features corresponding to the defect area images.
In a second aspect, the invention provides an OPC drum surface defect detection system comprising:
the acquisition module is used for acquiring an image of the outer surface of the OPC drum to be inspected through the LED scanner;
the enhancement module is used for processing the outer surface image based on an image enhancement method to obtain an image to be processed;
the segmentation module is used for segmenting the image to be processed by adopting a fusion segmentation algorithm; the fusion segmentation algorithm comprises an edge detection algorithm and a morphological segmentation algorithm;
the positioning module is used for processing the segmented image to be processed based on a defect positioning algorithm to obtain a defect area image;
The extraction module is used for extracting and selecting the characteristics of the defect area image to obtain the corresponding defect classification characteristics;
and the identification module is used for identifying the defect classification characteristic through the BP neural network model to obtain the defect type of the OPC drum to be inspected.
In some preferred embodiments, the acquisition module comprises:
an electrical inspection unit for detecting the brightness of the outer surface image of the OPC drum to be inspected in the scanning of the LED scanner through a circuit;
a control unit for controlling the rotational speed of the OPC drum to be inspected according to the brightness variation;
and the adjusting unit is used for adjusting the brightness of the scanning lamp of the LED scanner according to the brightness in the changing state.
In some preferred embodiments, the enhancement module comprises:
the gray level unit is used for carrying out graying treatment on the outer surface image by a weighted average method to obtain a gray level image;
the filtering unit is used for reducing a plurality of noises in the gray level image through improved median filtering to obtain an image to be processed; the improved median filtering adopts different processing modes according to different characteristics of noise points and edge points, and can make a judgment according to the conditions in the neighborhood.
In some preferred embodiments, the segmentation module comprises:
The edge detection unit is used for carrying out edge detection on the outer surface image subjected to gray scale processing by adopting a Canny edge detection algorithm to obtain a first processing result;
the first calculation unit is used for calculating the morphological gradient of the image to be processed through a prefabricated formula to obtain a second processing result;
the fusion unit is used for fusing the pixel value of each pixel point in the first processing result with the pixel value of the corresponding point in the second processing result to obtain an image after the image to be processed is fused;
a determining unit, configured to determine a first preset threshold based on an improved maximum inter-class variance algorithm principle;
and the segmentation unit is used for carrying out binary segmentation on the fused image according to the first preset threshold value so as to segment the image to be processed.
In some preferred embodiments, the positioning module comprises:
the expansion unit is used for expanding the segmented image to be processed to connect the intermittent edges to form a closed contour;
the filling unit is used for carrying out region filling treatment on the image region with the closed contour by adopting a seed filling algorithm;
the etching unit is used for etching the filled image area;
The denoising unit is used for denoising the corroded image area by adopting a denoising algorithm;
the traversing unit is used for traversing the image area after noise removal and finding out the marks corresponding to all the closed outlines so as to locate the accurate defect area.
In some preferred embodiments, the extraction module comprises:
the extraction unit is used for extracting the statistical characteristics of the defect area image by adopting an adaptive characteristic extraction method; wherein the statistical features include gray scale features, shape features, and texture features;
the second calculation unit is used for calculating the corresponding criterion function value of each feature in the statistical features through the divisibility criterion function;
the sorting unit is used for sorting the criterion function values from big to small;
and the selecting unit is used for selecting the preset number of features which are ranked at the front as a selecting result to obtain the defect classification features corresponding to the defect area images.
In a third aspect, the present application provides an electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the OPC drum surface defect detection method of the first aspect when executing the computer program.
In a fourth aspect, the present application provides a storage medium having stored thereon a computer program which when executed by a processor implements the OPC drum surface defect detection method of the first aspect.
Compared with the prior art, the OPC drum surface defect detection method, the OPC drum surface defect detection system, the electronic equipment and the storage medium have the following beneficial effects:
1. the LED scanner is used for collecting images in a scanning mode, so that the images of the actual surface collected by the OPC drum can be directly attached to the images collected by the OPC drum in a scanning mode, the collected image pixels are higher, and the cost is lower. In addition, the rotating speed of the OPC drum can be automatically adjusted for the area with the defects by a circuit detection mode, and the brightness of the scanning lamp can be automatically adjusted according to the brightness returned by the scanning lamp scanned on the surface of the defective area, so that the definition and the accuracy of the acquired image can be improved.
2. By adopting the image enhancement method, the acquired image can be clearer or some concerned features can be enhanced, and non-concerned features can be simulated, so that the quality of the acquired image can be improved, the information quantity of the image can be enriched, and the interpretation and recognition effects of the image can be enhanced.
3. By adopting a segmentation algorithm fused with edge detection and morphological gradient, the defect detection and accurate positioning can be not affected, and the requirements of online real-time processing are basically met; the threshold value is not required to be determined manually, so that the related advantages of edge detection are maintained, the noise immunity is high, and the segmentation effect is superior to that of the existing image segmentation algorithm.
4. The defect positioning algorithm is adopted to solve the problem of partial lost edges of the segmented image, and a small amount of noise and pseudo defects, so that the main contour of the defects is not influenced while the intermittent edges and the noise are removed, and the positioning accuracy of the defect area is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a method for detecting a surface defect of an OPC drum in accordance with embodiment 1 of the present invention;
FIG. 2 is a block diagram of an OPC drum surface defect detection system in accordance with the method of embodiment 1 provided in accordance with embodiment 2 of the present invention;
fig. 3 is a schematic hardware structure of an electronic device according to embodiment 3 of the present invention.
Reference numerals illustrate:
the system comprises a 10-acquisition module, an 11-electric detection unit, a 12-control unit and a 13-adjustment unit;
a 20-enhancement module, a 21-gray unit and a 22-filtering unit;
30-segmentation module, 31-side detection unit, 32-first calculation unit, 33-fusion unit, 34-determination unit, 35-segmentation unit;
a 40-positioning module, a 41-expansion unit, a 42-filling unit, a 43-corrosion unit, a 44-denoising unit and a 45-traversing unit;
50-extraction module, 51-extraction unit, 52-second calculation unit, 53-sorting unit, 54-selection unit;
60-an identification module;
70-bus, 71-processor, 72-memory, 73-communication interface.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments may be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art.
Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the disclosed aspects may be practiced without one or more of the specific details, or with other methods, components, devices, steps, etc. In other instances, well-known methods, devices, implementations, or operations are not shown or described in detail to avoid obscuring aspects of the disclosure.
The block diagrams depicted in the figures are merely functional entities and do not necessarily correspond to physically separate entities. That is, the functional entities may be implemented in software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.
The flow diagrams depicted in the figures are exemplary only, and do not necessarily include all of the elements and operations/steps, nor must they be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the order of actual execution may be changed according to actual situations.
Example 1
Specifically, FIG. 1 is a flow chart of a method for detecting a surface defect of an OPC drum according to an embodiment.
As shown in FIG. 1, the OPC drum surface defect detection method of the present embodiment comprises the steps of:
s101, acquiring an image of the outer surface of the OPC drum to be inspected through an LED scanner.
Specifically, OPC drum surface defect detection is an essential process in the printing industry today, and OPC drums, which are an important photosensitive component in printers, can affect the print quality of the printer if the OPC drum surface is defective. Currently, the adopted device generally uses a camera to collect images, the images collected by the camera are panoramic images, and mechanical cutting processing is needed in the image processing process, so that the detection rate of the surface defects of the OPC drum is slower. According to the embodiment, the LED scanner is used for replacing a traditional camera to collect images, the images of the actual surface of the OPC drum can be directly attached to the images collected by scanning, the collected image pixels are higher, and the cost is lower.
Further, the specific steps of step S101 include:
s1011, detecting the brightness of the outer surface image of the OPC drum to be detected in the scanning of the LED scanner through the circuit.
Specifically, the luminance automatic measurement circuit employed in this embodiment has a photocurrent signal output when the light to be measured is projected onto the OPC drum, and a current-voltage converter composed of a pair of field effect transistors is converted into a voltage signal, which is then linearly amplified by 5623. In order to make the measuring circuit have good linearity and high stability, a deep negative feedback network consisting of R4 (or R5) and C2 is adopted.
S1012, controlling the rotating speed of the OPC drum to be inspected according to the brightness change.
Specifically, in this embodiment, the brightness automatic measurement circuit and the driving motor for driving the OPC drum are both electrically connected to the control center, and when the brightness fed back by the brightness automatic measurement circuit changes obviously, it is indicated that the scanning area may have defects, and the control center controls the driving motor to reduce the output power, so that the rotation speed of the OPC drum is slowed down, and therefore, the corresponding area can be scanned by the LED scanner, and the acquisition accuracy of the images of the suspected defective area is improved.
S1013, adjusting the brightness of the scanning lamp of the LED scanner according to the brightness in the changing state.
Specifically, in this embodiment, the power controller of the scanning lamp is electrically connected to the control center, and when the brightness fed back by the brightness automatic measurement circuit changes obviously, it is indicated that there may be a defect in the scanning area; in order to be able to increase the sharpness of the defective area in the acquired image, the brightness of the scanning lamp can be increased by controlling the power controller through the control hub, thereby increasing the scanning brightness in this period.
S102, processing the outer surface image based on an image enhancement method to obtain an image to be processed.
Specifically, the image enhancement method adopted by the embodiment can make the acquired image clearer or enhance some concerned features, and simulate non-concerned features, so that the quality of the acquired image can be improved, the information content of the image can be enriched, and the subsequent interpretation and recognition effects of the image can be enhanced.
Further, the specific steps of step S102 include:
and S1021, carrying out graying treatment on the outer surface image by a weighted average method to obtain a gray image.
Specifically, in this embodiment, the ratio of the three components to the total component is divided according to the actual requirement in consideration of the visual effect difference caused by the different specific gravity of R, G, B, and the graying processing is implemented by the weighted addition method, so that the data of the three channels of RGB is changed into the data image of the single channel, and the data storage amount is obviously reduced.
And S1022, reducing a plurality of noises in the gray level image through improved median filtering, and obtaining the image to be processed.
The improved median filtering adopts different processing modes according to different characteristics of noise points and edge points, and can make a judgment according to the conditions in the neighborhood.
Specifically, the acquired environmental temperature and humidity, the electronic devices and the structure of the acquisition equipment and other factors can influence the shot image, so that the image generates noise, such as thermal noise caused by resistance, optical response non-uniformity noise and the like. There are basically four types of common noise in images: gaussian noise, poisson noise, multiplicative noise, and pretzel noise. Gaussian noise refers to a type of noise whose probability density function follows a gaussian distribution; poisson noise is a noise model conforming to poisson distribution, which is mainly used to describe the number of times a random event occurs in a fixed time and the magnitude of its probability; multiplicative noise is typically caused by channel imperfections, which are multiplied by the signal in which it is present and in which it is not present; salt and pepper noise, also called impulse noise, is a bright and dark spot between black and white generated by a sensor and a transmission channel, and the size of some pixel values is randomly changed in the decoding process. In specific practice, the self-adaptive filtering method adopts an improved median filtering method, adopts different processing modes according to different characteristics of noise points and edge points, can automatically make judgment according to conditions in the neighborhood, has good adaptability, and can reduce the influence of the selection of the size of a filtering window on the noise reduction effect.
S103, segmenting the image to be processed by adopting a fusion segmentation algorithm; the fusion segmentation algorithm comprises an edge detection algorithm and a morphological segmentation algorithm.
Specifically, the embodiment adopts a segmentation algorithm fused with edge detection and morphological gradient, can realize that defect detection and accurate positioning are not affected, and basically meets the requirement of online real-time processing; the threshold value is not required to be determined manually, so that the related advantages of edge detection are maintained, the noise immunity is high, and the segmentation effect is superior to that of the existing image segmentation algorithm.
Further, the specific steps of step S103 include:
s1031, performing edge detection on the outer surface image subjected to gray scale processing by adopting a Canny edge detection algorithm to obtain a first processing result.
Specifically, the gray-scale processed image is processed by adopting the traditional Canny edge detection, the Canny edge detection adopts a specific Gaussian filter to smooth the image, then the finite difference of first-order partial derivatives is adopted to calculate the amplitude and the direction of the gradient, the calculated amplitude in each direction is subjected to non-maximum suppression, and finally the hysteresis threshold method is adopted to remove the pseudo edge and the connecting edge. However, in this embodiment, the hysteresis threshold is not performed on the conventional Canny edge detection, but two thresholds are set to 0 directly, so that all edges in the image can be preserved, including false edges.
S1032, calculating the morphological gradient of the image to be processed through a prefabricated formula to obtain a second processing result.
Specifically, the morphological gradient is the difference between the expansion and corrosion maps. The mathematical expression used in this embodiment is as follows:
dst＝dilatg(src，element)-erode(src，element)。
s1033, fusing the pixel value of each pixel point in the first processing result with the pixel value of the corresponding point in the second processing result to obtain the image after the fusion of the image to be processed.
Specifically, in this embodiment, the pixel value of each pixel point in the first processing result is fused with the pixel value of the corresponding point in the second processing result, and this process can remove some false edges, such as edges of noise response, but the obtained edges are darker, and many false weak contour edges exist.
S1034, determining a first preset threshold based on the improved maximum inter-class variance algorithm principle.
Specifically, in order to remove false edges and weak edges in the fusion process, a relatively ideal segmentation result is obtained, and the key point is to determine a first preset threshold value. In this embodiment, an improved maximum inter-class variance algorithm is used, which is a slight modification of the maximum inter-class approach. The principle of the improved maximum inter-class variance algorithm is as follows: firstly, traversing all pixels of an image to be processed after image fusion, and storing all non-zero pixel values; secondly, dividing the non-zero pixel values into two groups of areas according to a certain gray level as a threshold value, and calculating the probability corresponding to each group of areas; again, the total variance of the two sets of regions is calculated; and finally, determining an optimal segmentation threshold according to the total variance, setting the gradient larger than the segmentation threshold as white, and setting the gradient smaller than the segmentation threshold as black, wherein the obtained result is used as a result image of edge detection.
S1035, performing binary segmentation on the fused image according to the first preset threshold value so as to segment the image to be processed.
Specifically, thresholding is simply to perform a binarizing operation on a gray-scale image, and the fundamental principle is to determine whether an image pixel is 0 or 255 by using a set threshold value, so that the setting of the threshold value is important in image binarization. The binarization of images is divided into global binarization and local binarization, and the difference is whether the threshold value is unified in one image. The present embodiment uses global binarization, i.e. pixels in the image below a certain threshold are set to black and others to white. A common algorithm is to select the middle of all possible values, so 128 will be selected for an 8 bit deep image (ranging from 0 to 255). This method works well when the image black pixels are truly below 128, and white is also above 128.
S104, processing the segmented image to be processed based on a defect positioning algorithm to obtain a defect area image.
Specifically, the defect positioning algorithm is adopted to solve the problem of partial edges lost by the segmented image and a small amount of noise and pseudo defects, so that the main contour of the defects is not influenced while the intermittent edges and the noise are removed, and the positioning precision of the defect area is improved.
Further, the specific steps of step S104 include:
s1041, expanding the segmented image to be processed to connect the intermittent edges to form a closed contour.
Specifically, although the above image segmentation well separates the defective image area from the background, a part of the edges is lost and a small amount of noise exists. How to connect the intermittent edges and remove noise without affecting the main profile of the defect is critical for defect localization.
S1042, carrying out region filling processing on the image region with the closed contour by adopting a seed filling algorithm.
The seed points in the seed filling algorithm are obtained by adopting a labeling connected component algorithm. The connected component algorithm comprises a four-connected algorithm and an eight-connected algorithm, and if any two pixel points in the image contour are connected up and down or left and right, the four-connected algorithm is called four-connected; if two pixels in an image are connected up and down or left and right, or connected diagonally, then the connected component is called eight-connected.
Specifically, for the seed filling algorithm, how to obtain the filled seed points is the key of the seed filling algorithm, in this embodiment, the seed points of each contour are obtained by adopting an algorithm of labeling connected components, so as to fill each contour of the image, and the expanded image is subjected to regional filling by adopting the seed filling algorithm.
And S1043, performing corrosion treatment on the filled image area.
Specifically, the present embodiment can eliminate the boundary points of the connected domain by the etching treatment, and the treatment process of shrinking the boundary inward. In addition, the corrosion treatment can remove adhesion between objects and also can remove small particle noise.
S1044, denoising the corroded image area by adopting a denoising algorithm.
Specifically, the filled image is eroded, but a small amount of noise interference still exists in the image. Conventional denoising algorithms such as median filtering, mean filtering or gaussian filtering are adopted, and are not applicable in this case, and the embodiment adopts a denoising algorithm with small size and large size to eliminate interference and noise.
S1045, traversing the image area after noise removal, and finding out the marks corresponding to all the closed outlines to locate the accurate defect area.
Specifically, in this embodiment, the labels corresponding to all the contours are found by traversing the image from which noise is removed; traversing the image to determine the minimum abscissa X of the coordinates of the corresponding contour point min Minimum ordinate Y min Maximum abscissa X max Maximum ordinate Y max Thereby forming two points (X min ，Y min )，(X max ，Y max ) Accurate defect areas can be located.
S105, extracting and selecting the characteristics of the defect area image to obtain the corresponding defect classification characteristics.
In particular, the acquired image of the defective area is a high-dimensional pattern space, which greatly increases the complexity of the classifier and seriously affects the efficiency of the classifier. Therefore, it is necessary to convert the high-dimensional pattern space into the low-dimensional feature space, that is, to perform feature extraction and selection of the image.
Further, the specific steps of step S105 include:
s1051, extracting statistical features of the defect area image by adopting an adaptive feature extraction method; wherein the statistical features include gray scale features, shape features, and texture features.
In particular, the gray scale characteristics of the defect area refer to the defect outline area rather than the defect rectangular area, so that accurate description of the gray scale characteristics of different types of defects can be more represented. Shape features mainly include area, perimeter, compactness, slenderness, rectangularity, invariance, etc. Texture features mainly adopt first order statistics and second order statistics to describe texture characteristics of defects.
S1052, each of the statistical features is calculated to be the corresponding criterion function value by the divisibility criterion function.
Specifically, the present embodiment implements feature selection by a simple individual selection method, which is to calculate the value of the separability criterion function for each of the D features individually.
S1053, sorting the criterion function values from big to small.
S1054, selecting the preset number of features which are ranked at the front as a selection result to obtain the defect classification features corresponding to the defect area images.
Specifically, the feature selection is essentially to select D (D < D) most efficient (most efficient feature to classify) features from D-dimensional features as input to the classifier in the subsequent stage.
S106, identifying the defect classification characteristic through the BP neural network model to obtain the defect type of the OPC drum to be inspected.
Specifically, through the construction of a BP neural network model, the steps of acquisition of a data set, data normalization, design of input and hidden and output layers, setting of other parameters of a network and the like are adopted; the data set of the network training is composed of gray level, shape and texture features extracted from each defect sample picture, and after feature selection, the most effective 20 features are selected from 33 features extracted from each defect sample. Inputting the defect classification characteristics into a constructed BP neural network model, wherein the specific identification process comprises the following steps: initializing BP network training parameters, executing a program, terminating a network training condition, a network training result and a defect identification result.
In summary, firstly, the LED scanner is used for collecting the outer surface image of the OPC drum to be detected, so that the definition and accuracy of the collected image can be improved; secondly, the image to be processed is obtained by processing the outer surface image by adopting an image enhancement method, so that the quality of the acquired image can be improved, the information quantity of the image can be enriched, and the interpretation and recognition effects of the image can be enhanced; secondly, the fusion segmentation algorithm is adopted to segment the image to be processed, so that the defect detection and accurate positioning are not affected, and the requirement of online real-time processing is basically met; secondly, processing the segmented image to be processed based on a defect positioning algorithm to obtain a defect area image, so that the main contour of the defect is not influenced while the intermittent edge and noise are removed; thirdly, extracting and selecting the characteristics of the defect area image to obtain the corresponding defect classification characteristics; finally, identifying defect classification characteristics through a BP neural network model to obtain defect types; with the above steps, the automation of the OPC drum surface defect detection and the accurate identification of the defect type can be realized.
Example 2
This embodiment provides a block diagram of a system corresponding to the method described in embodiment 1. FIG. 2 is a block diagram of a configuration of an OPC drum surface defect detection system in accordance with the present embodiment, as shown in FIG. 2, the system comprising:
An acquisition module 10 for acquiring an image of the outer surface of the OPC drum to be inspected by the LED scanner;
an enhancement module 20, configured to process the outer surface image based on an image enhancement method to obtain an image to be processed;
a segmentation module 30, configured to segment the image to be processed by using a fusion segmentation algorithm; the fusion segmentation algorithm comprises an edge detection algorithm and a morphological segmentation algorithm;
a positioning module 40, configured to obtain a defect area image based on the image to be processed after the segmentation processed by the defect positioning algorithm;
the extracting module 50 is configured to perform feature extraction and selection on the defect area image to obtain a corresponding defect classification feature;
the identification module 60 is configured to identify the defect classification feature through a BP neural network model to obtain a defect type of the OPC drum to be inspected.
Specifically, the acquisition module 10 includes:
an electrical inspection unit 11 for detecting the brightness of the outer surface image of the OPC drum to be inspected in the scanning of the LED scanner by a circuit;
a control unit 12 for controlling the rotational speed of the OPC drum to be inspected according to the change of the brightness;
and an adjusting unit 13 for adjusting the brightness of the scanning lamp of the LED scanner according to the brightness in the changing state.
Specifically, the enhancement module 20 includes:
a gray level unit 21 for graying the outer surface image by a weighted average method to obtain a gray level image;
a filtering unit 22, configured to reduce a number of noises in the gray-scale image through improved median filtering, so as to obtain an image to be processed; the improved median filtering adopts different processing modes according to different characteristics of noise points and edge points, and can make a judgment according to the conditions in the neighborhood.
Specifically, the segmentation module 30 includes:
an edge detection unit 31, configured to perform edge detection on the outer surface image processed by gray scale by using a Canny edge detection algorithm to obtain a first processing result;
a first calculation unit 32, configured to calculate a morphological gradient of the image to be processed through a prefabricated formula to obtain a second processing result;
a fusion unit 33, configured to fuse a pixel value of each pixel point in the first processing result with a pixel value of a corresponding point in the second processing result, so as to obtain a fused image of the image to be processed;
a determining unit 34, configured to determine a first preset threshold based on the improved principle of the maximum inter-class variance algorithm;
and a segmentation unit 35, configured to perform binary segmentation on the fused image according to the first preset threshold, so as to segment the image to be processed.
Specifically, the positioning module 40 includes:
an expansion unit 41 for expanding the segmented image to be processed to connect intermittent edges to form a closed contour;
a filling unit 42, configured to perform a region filling process on the image region with the closed contour by using a seed filling algorithm; the seed points in the seed filling algorithm are obtained by adopting a labeling connected component algorithm;
an etching unit 43 for etching the filled image region;
a denoising unit 44, configured to denoise the corroded image area by using a denoising algorithm;
the traversing unit 45 is configured to traverse the image area after removing the noise, and find the labels corresponding to all the closed contours to locate the accurate defect area.
Specifically, the extraction module 50 includes:
an extracting unit 51, configured to extract statistical features of the defect area image by using an adaptive feature extraction method; wherein the statistical features include gray scale features, shape features, and texture features;
a second calculation unit 52, configured to calculate, by using a divisibility criterion function, a criterion function value corresponding to each of the statistical features;
A sorting unit 53, configured to sort the criterion function values from large to small;
and the selecting unit 54 is configured to select a preset number of features ranked forward as a selection result, so as to obtain a defect classification feature corresponding to the defect area image.
The above-described respective modules may be functional modules or program modules, and may be implemented by software or hardware. For modules implemented in hardware, the various modules described above may be located in the same processor; or the above modules may be located in different processors in any combination.
Example 3
The OPC drum surface defect detection method described in connection with FIG. 1 may be implemented by an electronic device. Fig. 3 is a schematic diagram of the hardware structure of the electronic device according to the present embodiment.
The electronic device may include a processor 71 and a memory 72 storing computer program instructions.
In particular, the processor 71 may comprise a Central Processing Unit (CPU), or an application specific integrated circuit (Application Specific Integrated Circuit, abbreviated as ASIC), or may be configured as one or more integrated circuits embodying the present application.
Memory 72 may include, among other things, mass storage for data or instructions. By way of example, and not limitation, memory 72 may comprise a Hard Disk Drive (HDD), floppy Disk Drive, solid state Drive (Solid State Drive, SSD), flash memory, optical Disk, magneto-optical Disk, tape, or universal serial bus (Universal Serial Bus, USB) Drive, or a combination of two or more of the foregoing. The memory 72 may include removable or non-removable (or fixed) media, where appropriate. The memory 72 may be internal or external to the data processing apparatus, where appropriate. In a particular embodiment, the memory 72 is a Non-Volatile memory. In particular embodiments, memory 72 includes Read-Only Memory (ROM) and random access Memory (Random Access Memory, RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (Programmable Read-Only Memory, abbreviated PROM), an erasable PROM (Erasable Programmable Read-Only Memory, abbreviated EPROM), an electrically erasable PROM (Electrically Erasable Programmable Read-Only Memory, abbreviated EEPROM), an electrically rewritable ROM (Electrically Alterable Read-Only Memory, abbreviated EAROM), or a FLASH Memory (FLASH), or a combination of two or more of these. The RAM may be Static Random-Access Memory (SRAM) or dynamic Random-Access Memory (Dynamic Random Access Memory DRAM), where the DRAM may be a fast page mode dynamic Random-Access Memory (Fast Page Mode Dynamic Random Access Memory FPMDRAM), extended data output dynamic Random-Access Memory (Extended Date Out Dynamic Random Access Memory EDODRAM), synchronous dynamic Random-Access Memory (Synchronous Dynamic Random-Access Memory SDRAM), or the like, as appropriate.
Memory 72 may be used to store or cache various data files that need to be processed and/or communicated, as well as possible computer program instructions for execution by processor 71.
The processor 71 implements the OPC drum surface defect detection method of embodiment 1 described above by reading and executing computer program instructions stored in the memory 72.
In some of these embodiments, the electronic device may also include a communication interface 73 and a bus 70. As shown in fig. 3, the processor 71, the memory 72, and the communication interface 73 are connected to each other through the bus 70 and perform communication with each other.
The communication interface 73 is used to enable communication between modules, devices, units and/or units in the present application. Communication interface 73 may also enable communication with other components such as: and the external equipment, the image/data acquisition equipment, the database, the external storage, the image/data processing workstation and the like are used for data communication.
Bus 70 includes hardware, software, or both, coupling the components of the device to one another. Bus 70 includes, but is not limited to, at least one of: data Bus (Data Bus), address Bus (Address Bus), control Bus (Control Bus), expansion Bus (Expansion Bus), local Bus (Local Bus). By way of example, and not limitation, bus 70 may include a graphics acceleration interface (Accelerated Graphics Port), abbreviated AGP, or other graphics Bus, an enhanced industry standard architecture (Extended Industry Standard Architecture, abbreviated EISA) Bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an industry standard architecture (Industry Standard Architecture, ISA) Bus, a wireless bandwidth (InfiniBand) interconnect, a Low Pin Count (LPC) Bus, a memory Bus, a micro channel architecture (Micro Channel Architecture, abbreviated MCa) Bus, a peripheral component interconnect (Peripheral Component Interconnect, abbreviated PCI) Bus, a PCI-Express (PCI-X) Bus, a serial advanced technology attachment (Serial Advanced Technology Attachment, abbreviated SATA) Bus, a video electronics standards association local (Video Electronics Standards Association Local Bus, abbreviated VLB) Bus, or other suitable Bus, or a combination of two or more of these. Bus 70 may include one or more buses, where appropriate. Although a particular bus is described and illustrated, the present application contemplates any suitable bus or interconnect.
The electronic device may acquire an OPC drum surface defect detection system and perform the OPC drum surface defect detection method of embodiment 1.
In addition, in combination with the OPC drum surface defect detection method of embodiment 1 described above, the present application may be implemented by providing a storage medium. The storage medium having stored thereon computer program instructions; which when executed by a processor, performs the OPC drum surface defect detection method of embodiment 1 described above.
The technical features of the above-described embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above-described embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing description of the preferred embodiments of the application is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the application.
Claims (10)
1. A method of detecting a surface defect of an OPC drum, comprising:
acquiring an outer surface image of the OPC drum to be inspected through an LED scanner;
Processing the outer surface image based on an image enhancement method to obtain an image to be processed;
dividing the image to be processed by adopting a fusion dividing algorithm; the fusion segmentation algorithm comprises an edge detection algorithm and a morphological segmentation algorithm;
processing the segmented image to be processed based on a defect positioning algorithm to obtain a defect area image;
extracting and selecting characteristics of the defect area image to obtain corresponding defect classification characteristics;
and identifying the defect classification characteristic through a BP neural network model to obtain the defect type of the OPC drum to be inspected.
2. The method of detecting surface defects of an OPC drum of claim 1 wherein the step of capturing images of the outer surface of the OPC drum to be inspected by the LED scanner comprises:
detecting brightness of an image of the outer surface of the OPC drum to be inspected in the scanning of the LED scanner through a circuit;
controlling the rotational speed of the OPC drum to be inspected according to the change of the brightness;
and adjusting the brightness of the scanning lamp of the LED scanner according to the brightness in the changing state.
3. The method of detecting a surface defect of an OPC drum of claim 1 wherein the step of processing the outer surface image based on the image enhancement method to obtain a processed image comprises:
Graying the outer surface image by a weighted average method to obtain a gray image;
reducing a plurality of noises in the gray level image through improved median filtering to obtain an image to be processed; the improved median filtering adopts different processing modes according to different characteristics of noise points and edge points, and can make a judgment according to the conditions in the neighborhood.
4. The OPC drum surface defect detection method of claim 1 wherein the step of segmenting the image to be processed using a fusion segmentation algorithm comprises:
performing edge detection on the outer surface image subjected to gray scale processing by adopting a Canny edge detection algorithm to obtain a first processing result;
calculating the morphological gradient of the image to be processed through a prefabricated formula to obtain a second processing result;
fusing the pixel value of each pixel point in the first processing result with the pixel value of the corresponding point in the second processing result to obtain the fused image of the image to be processed;
determining a first preset threshold based on an improved maximum inter-class variance algorithm principle;
and carrying out binary segmentation on the fused image according to the first preset threshold value so as to segment the image to be processed.
5. The method of detecting a surface defect of an OPC drum as set forth in claim 1 wherein the step of processing the segmented image to be processed based on the defect localization algorithm to obtain an image of a defective area comprises:
expanding the segmented image to be processed to connect the intermittent edges to form a closed contour;
carrying out region filling treatment on the image region of the closed contour by adopting a seed filling algorithm;
carrying out corrosion treatment on the filled image area;
denoising the corroded image area by adopting a denoising algorithm;
and traversing the image area after noise removal, and finding out the marks corresponding to all the closed outlines to locate an accurate defect area.
6. The OPC drum surface defect detection method of claim 5 wherein the seed points in the seed filling algorithm are obtained using a label connected component algorithm.
7. The method of detecting a surface defect of an OPC drum as set forth in claim 1 wherein the step of extracting features from the image of the defective area and selecting corresponding defect classification features thereof comprises:
extracting statistical features of the defect area image by adopting an adaptive feature extraction method; wherein the statistical features include gray scale features, shape features, and texture features;
Calculating a corresponding criterion function value of each feature in the statistical features through a divisibility criterion function;
sorting the criterion function values from big to small;
and selecting the preset number of features which are ranked at the front as a selection result to obtain the defect classification features corresponding to the defect area images.
8. A method of detecting a surface defect of an OPC drum, comprising:
the acquisition module is used for acquiring an image of the outer surface of the OPC drum to be inspected through the LED scanner;
the enhancement module is used for processing the outer surface image based on an image enhancement method to obtain an image to be processed;
the segmentation module is used for segmenting the image to be processed by adopting a fusion segmentation algorithm; the fusion segmentation algorithm comprises an edge detection algorithm and a morphological segmentation algorithm;
the positioning module is used for processing the segmented image to be processed based on a defect positioning algorithm to obtain a defect area image;
the extraction module is used for extracting and selecting the characteristics of the defect area image to obtain the corresponding defect classification characteristics;
and the identification module is used for identifying the defect classification characteristic through the BP neural network model to obtain the defect type of the OPC drum to be inspected.
9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the OPC drum surface defect detection method of any one of claims 1 to 7 when executing the computer program.
10. A storage medium having a computer program stored thereon, wherein the program when executed by a processor implements the OPC drum surface defect detection method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310504458.XA CN116721058A (en) | 2023-05-06 | 2023-05-06 | OPC drum surface defect detection method, system, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310504458.XA CN116721058A (en) | 2023-05-06 | 2023-05-06 | OPC drum surface defect detection method, system, electronic device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116721058A true CN116721058A (en) | 2023-09-08 |
Family
ID=87870484
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310504458.XA Pending CN116721058A (en) | 2023-05-06 | 2023-05-06 | OPC drum surface defect detection method, system, electronic device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116721058A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117011290A (en) * | 2023-09-27 | 2023-11-07 | 南昌理工学院 | Defect diagnosis method, system and computer equipment |
| CN117058141A (en) * | 2023-10-11 | 2023-11-14 | 福建钜鸿百纳科技有限公司 | Glass edging defect detection method and terminal |
| CN117218097A (en) * | 2023-09-23 | 2023-12-12 | 宁波江北骏欣密封件有限公司 | Method and device for detecting surface defects of shaft sleeve type silk screen gasket part |
| CN117392066A (en) * | 2023-09-26 | 2024-01-12 | 钛玛科（北京）工业科技有限公司 | Defect detection method, device, equipment and storage medium |
| CN117392066B (en) * | 2023-09-26 | 2024-07-09 | 钛玛科（北京）工业科技有限公司 | Defect detection method, device, equipment and storage medium |
-
2023
- 2023-05-06 CN CN202310504458.XA patent/CN116721058A/en active Pending
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117218097A (en) * | 2023-09-23 | 2023-12-12 | 宁波江北骏欣密封件有限公司 | Method and device for detecting surface defects of shaft sleeve type silk screen gasket part |
| CN117218097B (en) * | 2023-09-23 | 2024-04-12 | 宁波江北骏欣密封件有限公司 | Method and device for detecting surface defects of shaft sleeve type silk screen gasket part |
| CN117392066A (en) * | 2023-09-26 | 2024-01-12 | 钛玛科（北京）工业科技有限公司 | Defect detection method, device, equipment and storage medium |
| CN117392066B (en) * | 2023-09-26 | 2024-07-09 | 钛玛科（北京）工业科技有限公司 | Defect detection method, device, equipment and storage medium |
| CN117011290A (en) * | 2023-09-27 | 2023-11-07 | 南昌理工学院 | Defect diagnosis method, system and computer equipment |
| CN117011290B (en) * | 2023-09-27 | 2023-12-15 | 南昌理工学院 | Defect diagnosis method, system and computer equipment |
| CN117058141A (en) * | 2023-10-11 | 2023-11-14 | 福建钜鸿百纳科技有限公司 | Glass edging defect detection method and terminal |
| CN117058141B (en) * | 2023-10-11 | 2024-03-01 | 福建钜鸿百纳科技有限公司 | Glass edging defect detection method and terminal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115170576B (en) | Aluminum pipe surface defect detection method based on machine vision | |
| CN116721058A (en) | OPC drum surface defect detection method, system, electronic device and storage medium | |
| CN109377485B (en) | Machine vision detection method for instant noodle packaging defects | |
| CN114494259B (en) | Cloth defect detection method based on artificial intelligence | |
| CN115351598A (en) | Numerical control machine tool bearing detection method | |
| US9239281B2 (en) | Method and device for dividing area of image of particle in urine | |
| WO2017161598A1 (en) | Fast density estimation method for defect inspection application | |
| CN116433666B (en) | Board card line defect online identification method, system, electronic equipment and storage medium | |
| CN114782329A (en) | Bearing defect damage degree evaluation method and system based on image processing | |
| CN116228780B (en) | Silicon wafer defect detection method and system based on computer vision | |
| CN114926407A (en) | Steel surface defect detection system based on deep learning | |
| CN116664565A (en) | Hidden crack detection method and system for photovoltaic solar cell | |
| CN109886931A (en) | Gear ring of wheel speed sensor detection method of surface flaw based on BP neural network | |
| CN111986195A (en) | Appearance defect detection method and system | |
| CN116228741A (en) | PCBA (printed circuit board assembly) component defect detection method and device | |
| CN115294377A (en) | System and method for identifying road cracks | |
| CN113888536A (en) | Printed matter double image detection method and system based on computer vision | |
| CN112561875A (en) | Photovoltaic cell panel coarse grid detection method based on artificial intelligence | |
| Haoran et al. | Egg crack detection based on support vector machine | |
| CN117333467B (en) | Image processing-based glass bottle body flaw identification and detection method and system | |
| Li et al. | Wafer crack detection based on yolov4 target detection method | |
| CN111428752B (en) | Visibility detection method based on infrared image | |
| US20060126136A1 (en) | Image inspecting apparatus, image inspecting method, control program and computer-readable storage medium | |
| Li et al. | Surface Defect Detection of Seals Based on K‐Means Clustering Algorithm and Particle Swarm Optimization | |
| CN113989481A (en) | Contract text image seal detection and removal method |
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 |