CN114782418B - Detection method and device for ceramic tile surface defects and storage medium - Google Patents
Detection method and device for ceramic tile surface defects and storage medium Download PDFInfo
- Publication number
- CN114782418B CN114782418B CN202210680945.7A CN202210680945A CN114782418B CN 114782418 B CN114782418 B CN 114782418B CN 202210680945 A CN202210680945 A CN 202210680945A CN 114782418 B CN114782418 B CN 114782418B
- Authority
- CN
- China
- Prior art keywords
- picture
- picture set
- sample
- subset
- value
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
-
- 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
- G06T2207/20081—Training; Learning
-
- 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)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a method and a device for detecting surface defects of tiles and a storage medium, wherein the method comprises the following steps: collecting a first picture set of a ceramic tile, wherein the first picture set comprises a plurality of first sample pictures; processing the first picture set to obtain a second picture set meeting preset visual conditions, wherein the second picture set comprises a plurality of second sample pictures, and each second sample picture corresponds to one first sample picture; generating an image preprocessing model of the ceramic tile by adopting the first picture set and the second picture set; and detecting surface defect information of the ceramic tile by adopting the image preprocessing model. According to the invention, the technical problem of unstable detection result of the surface defect of the ceramic tile in the related technology is solved, the detection error of the surface defect of the ceramic tile is reduced, and the stability and robustness of the ceramic tile detection model are improved.
Description
Technical Field
The invention relates to the field of computers, in particular to a method and a device for detecting surface defects of tiles and a storage medium.
Background
In the related art, the manual sampling inspection has the risk of flowing out of defective products due to incomplete coverage. The existing ceramic tile defect detection method is characterized in that a camera is erected to carry out self-adaptive exposure shooting on a ceramic tile, a deep learning algorithm is used for training a ceramic tile defect recognition model, and AI defect recognition is carried out on the ceramic tile.
Due to the fact that the texture of the ceramic tile is changed greatly, the surface is smooth, the conditions of inconsistent photographing brightness and definition, multiple interference factors and the like exist even if self-adaptive exposure parameters are used, the deep learning training input picture is unstable and incomplete, and the robustness of a model detection algorithm is low.
In view of the above problems in the related art, no effective solution has been found at present.
Disclosure of Invention
The embodiment of the invention provides a method and a device for detecting surface defects of tiles and a storage medium.
According to an aspect of an embodiment of the present application, there is provided a method for detecting surface defects of a tile, including: collecting a first picture set of a ceramic tile, wherein the first picture set comprises a plurality of first sample pictures; processing the first picture set to obtain a second picture set meeting preset visual conditions, wherein the second picture set comprises a plurality of second sample pictures, and each second sample picture corresponds to one first sample picture; generating an image preprocessing model of the ceramic tile by adopting the first picture set and the second picture set; and detecting surface defect information of the ceramic tile by adopting the image preprocessing model.
Further, processing the first picture set to obtain a second picture set conforming to a preset view effect includes: for each first sample picture in the first picture set, performing denoising and filtering on the first sample picture to obtain an intermediate picture set; dividing the intermediate picture set according to the gray value and the contrast to obtain a plurality of sub-sets, wherein each sub-set corresponds to a gray value interval and a contrast interval; and respectively performing self-adaptive adjustment on the brightness and the contrast of the pictures in the sub-sets aiming at each sub-set in the plurality of sub-sets, and merging the adjusted pictures to generate the second picture set, wherein the brightness of each second picture in the second picture set is within a preset brightness interval, and the contrast is within a preset contrast interval.
Further, the denoising and filtering the first sample picture comprises: carrying out first denoising and filtering operation on the first sample picture, and filtering environmental dust noise points in the first sample picture to obtain a first picture; and carrying out second denoising and filtering operation on the first picture, and filtering light and shadow noise points in the first picture to obtain a second picture.
Further, performing a first denoising and filtering operation on the first sample picture, and filtering out environmental dust noise points in the first sample picture to obtain a first picture, including: performing track recognition and object recognition on the first sample picture, and extracting the tile texture of the first sample picture; decomposing the first sample picture into a texture area and a background area, wherein the texture area is an area where the tile texture of the tile is located, and the background area is other areas except the tile texture; and setting the same gray value or RGB value for all the pixel points in the background area.
Further, dividing the intermediate picture set according to the gray value and the contrast to obtain a plurality of sub-sets comprises: extracting the gray value and the contrast of each first intermediate picture in the intermediate picture set, and calculating the gray average value and the contrast average value of all pictures in the intermediate picture set; calculating a first difference value and a second difference value between the gray value and the contrast of each first intermediate picture and the gray average value and the contrast average value respectively; if a first intermediate picture with a first difference value larger than a first preset value and a second difference value larger than a second preset value exists in the intermediate picture set, dividing the first intermediate picture into a first subset; if a second intermediate picture with a first difference value smaller than a third preset value and a second difference value smaller than a fourth preset value exists in the intermediate picture set, dividing the second intermediate picture into a second subset; if a third intermediate picture with a first difference value larger than or equal to the third preset value and smaller than or equal to the first preset value exists in the intermediate picture set, and a second difference value larger than or equal to the fourth preset value and smaller than or equal to the second preset value exists in the intermediate picture set, dividing the third intermediate picture into a third subset, wherein the first subset is a light color plate picture, the second subset is a dark color plate picture, and the third subset is a neutral color plate picture.
Further, for each of the plurality of subsets, the adaptively adjusting the brightness and the contrast of the picture in the subset respectively comprises: for a first subset of light panel pictures, increasing a display gamma value of each first intermediate picture in the first subset; for a second subset of the darkroom slate pictures, reducing the display gamma value of each second intermediate picture in the second subset; for a third subset of neutral palette pictures, maintaining a display gamma value for each third intermediate picture in the third subset.
Further, generating an image preprocessing model of the tile using the first set of pictures and the second set of pictures comprises: configuring each first picture in the first picture set as input data, configuring each second picture in the second picture set as output data, and pairing the first pictures in the first picture set and the second pictures in the second picture set to obtain a plurality of sample pairs; and training the initial model of the ceramic tile by adopting the plurality of samples to obtain an image preprocessing model for generating the ceramic tile.
Further, the step of detecting the surface defect information of the ceramic tile by using the image preprocessing model comprises the following steps: acquiring an initial tile picture to be detected; inputting the initial tile picture into the image preprocessing model, and outputting a target tile picture meeting the preset visual condition; inputting the target tile picture into a preset defect detection model, and outputting the surface defect information of the initial tile picture, wherein the model parameters of the preset defect detection model are matched with the preset visual conditions.
According to another aspect of the embodiments of the present application, there is also provided an apparatus for detecting surface defects of ceramic tiles, including: the tile image acquisition device comprises an acquisition module, a processing module and a display module, wherein the acquisition module is used for acquiring a first image set of a tile, and the first image set comprises a plurality of first sample images; the processing module is used for processing the first picture set to obtain a second picture set meeting preset visual conditions, wherein the second picture set comprises a plurality of second sample pictures, and each second sample picture corresponds to one first sample picture; the generating module is used for generating an image preprocessing model of the ceramic tile by adopting the first picture set and the second picture set; and the detection module is used for detecting the surface defect information of the ceramic tile by adopting the image preprocessing model.
Further, the processing module includes: the filtering unit is used for carrying out denoising and filtering on each first sample picture in the first picture set to obtain an intermediate picture set; the dividing unit is used for dividing the intermediate image set according to the gray value and the contrast to obtain a plurality of sub-sets, wherein each sub-set corresponds to a gray value interval and a contrast interval; and the adjusting unit is used for respectively and adaptively adjusting the brightness and the contrast of the pictures in the sub-sets aiming at each sub-set in the plurality of sub-sets, merging the adjusted pictures to generate the second picture set, wherein the brightness of each second picture in the second picture set is within a preset brightness interval, and the contrast is within a preset contrast interval.
Further, the filtering unit includes: the first filtering unit is used for carrying out first denoising and filtering operation on the first sample picture, and filtering environmental dust noise points in the first sample picture to obtain a first picture; and the second filtering unit is used for carrying out second denoising and filtering operation on the first picture, and filtering the light and shadow noise points in the first picture to obtain a second picture.
Further, the first filtering unit includes: the identification subunit is used for carrying out track identification and object identification on the first sample picture and extracting the tile texture of the first sample picture; a decomposition subunit, configured to decompose the first sample picture into a texture area and a background area, where the texture area is an area where a tile texture of a tile is located, and the background area is an area other than the tile texture; and the setting subunit is used for setting the same gray value or RGB value for all the pixel points in the background area.
Further, the dividing unit includes: the first calculating subunit is used for extracting the gray value and the contrast of each first intermediate picture in the intermediate picture set and calculating the average gray value and the average contrast value of all pictures in the intermediate picture set; the second calculating subunit is used for calculating a first difference value and a second difference value between the gray value and the contrast of each first intermediate picture and the gray average value and the contrast average value respectively; a dividing subunit, configured to divide the first intermediate picture into a first subset if a first intermediate picture with a first difference value greater than a first preset value and a second difference value greater than a second preset value exists in the intermediate picture set; if a second intermediate picture with a first difference value smaller than a third preset value and a second difference value smaller than a fourth preset value exists in the intermediate picture set, dividing the second intermediate picture into a second subset; if a third intermediate picture with a first difference value larger than or equal to the third preset value and smaller than or equal to the first preset value exists in the intermediate picture set, and a second difference value larger than or equal to the fourth preset value and smaller than or equal to the second preset value exists in the intermediate picture set, dividing the third intermediate picture into a third subset, wherein the first subset is a light color plate picture, the second subset is a dark color plate picture, and the third subset is a neutral color plate picture.
Further, the adjusting unit includes: a lifting subunit, configured to, for a first subset of the light palette pictures, lift a display gamma value of each first intermediate picture in the first subset; a reduction subunit, configured to reduce, for a second subset of the deep-panel pictures, a display gamma value of each second intermediate picture in the second subset; a maintaining subunit, configured to maintain, for a third subset of the neutral-color-panel pictures, a display gamma value of each third intermediate picture in the third subset.
Further, the generating module includes: a pairing unit, configured to configure each first picture in the first picture set as input data, configure each second picture in the second picture set as output data, and pair the first picture in the first picture set and the second picture in the second picture set with each other to obtain a plurality of sample pairs; and the training unit is used for training the initial model of the ceramic tile by adopting the plurality of sample pairs to obtain an image preprocessing model for generating the ceramic tile.
Further, the detection module includes: the acquisition unit is used for acquiring an initial tile picture to be detected; the first output unit is used for inputting the initial tile picture into the image preprocessing model and outputting a target tile picture meeting the preset visual condition; and the second output unit is used for inputting the target tile picture into a preset defect detection model and outputting the surface defect information of the initial tile picture, wherein the model parameters of the preset defect detection model are matched with the preset visual conditions.
According to another aspect of the embodiments of the present application, there is also provided a storage medium including a stored program which performs the above steps when the program is executed.
According to another aspect of the embodiments of the present application, there is also provided an electronic device, including a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory complete communication with each other through the communication bus; wherein: a memory for storing a computer program; a processor for executing the steps of the method by running the program stored in the memory.
Embodiments of the present application also provide a computer program product containing instructions, which when run on a computer, cause the computer to perform the steps of the above method.
By the method, a first picture set of the ceramic tile is collected, wherein the first picture set comprises a plurality of first sample pictures, the first picture set is processed to obtain a second picture set meeting the preset visual condition, the second picture set comprises a plurality of second sample pictures, each second sample picture corresponds to one first sample picture, an image preprocessing model of the ceramic tile is generated by adopting the first picture set and the second picture set, the surface defect information of the ceramic tile is detected by adopting the image preprocessing model, the first picture set with unstable visual condition is processed into the second picture set meeting the preset visual condition and the image preprocessing model is generated, the picture with higher quality is used in the ceramic tile defect detection, the technical problem that the detection result of the surface defect of the ceramic tile in the related technology is unstable is solved, and the detection error of the surface defect of the ceramic tile is reduced, the stability and the robustness of the tile detection model are improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
FIG. 1 is a block diagram of a hardware configuration of a computer according to an embodiment of the present invention;
FIG. 2 is a flow chart of a method of detecting surface defects of ceramic tiles according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of noise filtering according to an embodiment of the present invention;
fig. 4 is a block diagram showing a structure of an apparatus for detecting surface defects of ceramic tiles according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
The method provided by the first embodiment of the present application can be executed in a server, a computer, an industrial camera, a machine or a similar computing device. Taking an example of the present invention running on a computer, fig. 1 is a block diagram of a hardware structure of a computer according to an embodiment of the present invention. As shown in fig. 1, computer 10 may include one or more (only one shown in fig. 1) processors 102 (processor 102 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, and optionally may also include a transmission device 106 for communication functions and an input-output device 108. It will be appreciated by those of ordinary skill in the art that the configuration shown in FIG. 1 is illustrative only and is not intended to limit the configuration of the computer described above. For example, computer 10 may also include more or fewer components than shown in FIG. 1, or have a different configuration than shown in FIG. 1.
The memory 104 can be used for storing computer programs, for example, software programs and modules of application software, such as a computer program corresponding to a method for detecting surface defects of ceramic tiles in the embodiment of the present invention, and the processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, so as to implement the method. The memory 104 may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory located remotely from the processor 102, which may be connected to the computer 10 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission device 106 is used for receiving or transmitting data via a network. Specific examples of such networks may include wireless networks provided by the communications provider of computer 10. In one example, the transmission device 106 includes a Network adapter (NIC), which can be connected to other Network devices through a base station so as to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.
In this embodiment, a method for detecting surface defects of ceramic tiles is provided, and fig. 2 is a flowchart of a method for detecting surface defects of ceramic tiles according to an embodiment of the present invention, as shown in fig. 2, the flowchart includes the following steps:
step S202, collecting a first picture set of the ceramic tile, wherein the first picture set comprises a plurality of first sample pictures;
in this embodiment, the first picture set includes a plurality of sample pictures of tiles of multiple models (such as brands, patterns, categories, etc.), and each sample picture of the model includes one or more than one sample picture.
In some examples, a line scan camera is used to acquire a first sample picture, the line scan camera photographs the picture by splicing a plurality of columns of pixels, the preset width is 1000 pixels, and 5000 rows or 10000 rows of pictures can be photographed to obtain one picture; and processing w x (N) small-range pictures (N is cut according to the actual situation, and each small-range picture contains complete pattern texture of the ceramic tile) according to the single-line shooting characteristic of the camera, so as to complete the selection of the first picture set.
Step S204, processing the first picture set to obtain a second picture set meeting preset visual conditions, wherein the second picture set comprises a plurality of second sample pictures, and each second sample picture corresponds to one first sample picture;
in this embodiment, because each first sample picture in the first picture set has a difference, when the first picture set is processed, the processing manner and the processing degree of each first sample picture in the first picture set are different, but each second sample picture in the finally obtained second picture set meets the preset visual condition.
Step S206, generating an image preprocessing model of the ceramic tile by adopting the first picture set and the second picture set;
since the first picture set and the second picture set comprise sample pictures of multiple types of tiles, the image preprocessing model generated based on the first picture set and the second picture set can detect defects of various types of tiles to be detected.
And step S208, detecting the surface defect information of the ceramic tile by adopting an image preprocessing model.
Through the steps, a first picture set of the ceramic tile is collected, wherein the first picture set comprises a plurality of first sample pictures, the first picture set is processed to obtain a second picture set meeting the preset visual condition, the second picture set comprises a plurality of second sample pictures, each second sample picture corresponds to one first sample picture, an image preprocessing model of the ceramic tile is generated by adopting the first picture set and the second picture set, the surface defect information of the ceramic tile is detected by adopting the image preprocessing model, the first picture set with unstable visual condition is processed into the second picture set meeting the preset visual condition and the image preprocessing model is generated, the picture with higher quality is used in the ceramic tile defect detection, the technical problem that the detection result of the surface defect of the ceramic tile in the related technology is unstable is solved, and the detection error of the surface defect of the ceramic tile is reduced, the stability and the robustness of the tile detection model are improved.
In an implementation manner of this embodiment, processing the first picture set to obtain a second picture set conforming to a preset view effect includes:
s11, performing denoising and filtering on each first sample picture in the first picture set to obtain an intermediate picture set;
in some examples, denoising filtering the first sample picture comprises: carrying out first denoising and filtering operation on the first sample picture, and filtering environmental dust noise points in the first sample picture to obtain a first picture; and carrying out second denoising and filtering operation on the first picture, and filtering light and shadow noise points in the first picture to obtain a second picture.
By filtering the environmental dust noise in the first sample picture, the interference caused by the environmental dust can be eliminated, in one example, a first denoising filtering operation is performed on the first sample picture, and the filtering of the environmental dust noise in the first sample picture includes: performing track identification and object identification (the track identification is used for extracting patterns, and the object identification is used for extracting patterns) on the first sample picture, extracting the tile texture of the first sample picture, and decomposing the first sample picture into a texture region and a background region, wherein the texture region is a region where the tile texture of a tile is located, the background region is other regions except the tile texture, all pixel points in the background region are set with the same gray value or RGB value, if the pixel points are black images, the pixel points are set with the same gray value, and if the pixel points are color images, the pixel points are set with the same RGB value.
The interference caused by the light and shadow can be eliminated by filtering the light and shadow noise points in the first sample picture, in one example, the second denoising and filtering operation is performed on the first picture, the light and shadow noise points in the first picture are filtered, and the obtaining of the second picture comprises: and carrying out texture classification on the texture region, extracting line textures and block textures in the texture region, extracting the gray values of each group of pixels in the block textures line by line or column by column from the edge of the block textures, comparing the gray values of adjacent pixel groups (each pixel group is a plurality of lines of pixels or a plurality of columns of pixels are similar), determining that the block textures are light and shadow noise points if the gray values of the block textures are increased or decreased progressively in a direction exceeding a preset direction, and replacing the gray values or the RGB values of the block textures with the gray values or the RGB values of the background region. When comparing the gray values of the adjacent pixel groups, the gray average value of all the pixel points in each pixel group can be calculated first, and then the gray average values are used for comparison.
The tile is an object made of reflective materials, and when a back shadow of a certain background object is projected on the surface of the tile, due to the projection angle of light, a projection area can change colors in a certain trend, such as deepening or lightening.
Because first sample picture is at the shooting in-process, the scene thing at ceramic tile place probably because of person or scene thing cause the shadow on the ceramic tile under the condition of light, because the shadow region generally is grey or black, is similar with the base colour under the ceramic tile glaze, therefore the shadow probably can be discerned as the defect, like spot, damage, breach etc. need with the filtration of shadow noise point, reduce the interference that causes the defect detection.
Fig. 3 is a schematic diagram of noise filtering in the embodiment of the present invention, where light and shadow noise and dust noise exist in the first sample picture, and the light and shadow noise and dust noise are already removed in the second obtained picture through the noise removing and filtering.
By filtering out environmental dust noise and light shadow noise, various stains and residual shadows in the sample picture can be eliminated, the first sample picture obtained by shooting in the actual environment is converted into the second sample picture obtained by shooting in the ideal environment, and therefore when the picture to be detected is processed by adopting the image preprocessing model in the follow-up process, the initial tile picture can be processed into a target tile picture without noise, the interference of the noise on the defect detection is reduced, and the accuracy of the defect detection is improved.
S12, dividing the intermediate picture set according to the gray value and the contrast to obtain a plurality of sub-sets, wherein each sub-set corresponds to a gray value interval and a contrast interval;
in one example, dividing the intermediate picture set according to gray values and contrast to obtain a plurality of sub-sets includes: extracting the gray value and the contrast of each first intermediate picture in the intermediate picture set, and calculating the gray average value and the contrast average value of all pictures in the intermediate picture set; calculating a first difference value and a second difference value between the gray value and the contrast of each first intermediate picture and the gray average value and the contrast average value respectively; if a first intermediate picture with a first difference value larger than a first preset value and a second difference value larger than a second preset value exists in the intermediate picture set, dividing the first intermediate picture into a first subset; if a second intermediate picture with a first difference value smaller than a third preset value and a second difference value smaller than a fourth preset value exists in the intermediate picture set, dividing the second intermediate picture into a second sub-set; if a third intermediate picture with a first difference value larger than or equal to the third preset value and smaller than or equal to the first preset value exists in the intermediate picture set, and a second difference value larger than or equal to the fourth preset value and smaller than or equal to the second preset value exists in the intermediate picture set, dividing the third intermediate picture into a third subset, wherein the first subset is a light color plate picture, the second subset is a dark color plate picture, and the third subset is a neutral color plate picture.
In this example, three intervals, interval 1, interval 2 and interval 3 are set, wherein the first difference is greater than the first preset value and the second difference is greater than the second preset value, and is interval 1; the first difference is smaller than a third preset value and the second difference is smaller than a fourth preset value, and the interval is 2; the first difference is greater than or equal to the third preset value and less than or equal to the first preset value, and the second difference is greater than or equal to the fourth preset value and less than or equal to the second preset value, which is an interval 3.
For example, the intermediate picture set includes a picture 1, a picture 2, and a picture 3, where the grayscale value of the picture 1 is 20, the contrast is 50%, the grayscale value of the picture 2 is 200, the contrast is 20%, the grayscale value of the picture 3 is 50, and the contrast is 75%, and by calculation, the grayscale mean value is (20 +200+ 50)/3 =90, the contrast mean value is (50% +20% + 50%)/3 =40%, the first difference value of the picture 1 is-70, the second difference value is 10%, the first difference value of the picture 2 is 110, the second difference value is-20%, the first difference value of the picture 3 is-40, the second difference value is 35%, the first preset value is 10, the second preset value is 10%, the third preset value is-10, and the fourth preset value is-10%.
And S13, respectively performing adaptive adjustment on the brightness and the contrast of the pictures in the sub-sets aiming at each sub-set in the plurality of sub-sets, and merging the adjusted pictures to generate the second picture set, wherein the brightness of each second picture in the second picture set is within a preset brightness interval, and the contrast is within a preset contrast interval.
Based on the above example, for each of the plurality of subsets, the adaptive adjusting the brightness and the contrast of the picture in the subset respectively comprises: for a first subset of the light panel pictures, increasing a display gamma value of each first intermediate picture in the first subset; for a second subset of deep panel pictures, reducing a display gamma value of each second intermediate picture in the second subset; for a third subset of neutral palette pictures, maintaining a display gamma value for each third intermediate picture in the third subset.
In one example, the first picture set is set a, the second picture set is set B, each picture in set a is subjected to image processing to form picture set B, and then the following steps are performed:
a, respectively carrying out independent denoising and filtering on the pictures in the set A to eliminate the interference of environmental dust and the like;
b, performing manual review on the processed picture, and processing the picture modification parameters which are not obviously improved again;
c, calculating the gray average value and the contrast average value of the image processed in the last step, and dividing adjusting intervals according to the calculated values (the gray average value and the contrast average value) to be respectively a deep color plate, a neutral color plate and a light color plate;
d, respectively using self-adaptive parameters to correct the brightness and the contrast of the dark color plate, the neutral color plate and the light color plate;
d1, improving the brightness and contrast of the deep color plate, and reducing gamma;
d2, fine-tuning brightness and contrast of the neutral color plate, and fine-tuning gamma, wherein gamma can be kept unchanged or adjusted in a small amplitude within a preset range;
d3, reducing the brightness of the light color plate and improving the gamma;
and e, performing brightness contrast characteristic analysis on all the pictures again to enable all the pictures to fall into the target interval, and forming a sample B set.
In an embodiment of this embodiment, generating an image preprocessing model of a tile using the first picture set and the second picture set includes: configuring each first picture in the first picture set as input data, configuring each second picture in the second picture set as output data, and pairing the first pictures in the first picture set and the second pictures in the second picture set to obtain a plurality of sample pairs; and training the initial model of the ceramic tile by adopting the plurality of samples to obtain an image preprocessing model for generating the ceramic tile.
And training a relation model between the two picture sets by using a deep learning algorithm to obtain an image preprocessing model special for the ceramic tile.
In one embodiment of this embodiment, the detecting the surface defect information of the tile by using the image preprocessing model includes: acquiring an initial tile picture to be detected; inputting the initial tile picture into the image preprocessing model, and outputting a target tile picture meeting the preset visual condition; inputting the target tile picture into a preset defect detection model, and outputting the surface defect information of the initial tile picture, wherein the model parameters of the preset defect detection model are matched with the preset visual conditions. Under the preset visual condition, the preset defect detection model has the lowest false detection rate and the highest detection accuracy rate of the surface defects of the ceramic tiles.
The model is used for data processing before algorithm detection is carried out each time, so that the quality of the initial tile image can be improved, the initial tile image meets the detection condition of the preset defect detection model, and the robustness of the preset defect detection model algorithm is finally improved.
The embodiment provides an image processing method for improving the robustness of tile defect detection, so that the picture photographed by a camera can be close to the requirement of an algorithm.
Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but the former is a better implementation mode in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
Example 2
In this embodiment, a device for detecting surface defects of a tile is further provided, which is used to implement the above embodiments and preferred embodiments, and the description of the device is omitted. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.
Fig. 4 is a block diagram showing the structure of an apparatus for detecting surface defects of ceramic tiles according to an embodiment of the present invention, as shown in fig. 4, the apparatus comprising: an acquisition module 40, a processing module 42, a generation module 44, a detection module 46, wherein,
the system comprises an acquisition module 40, a storage module and a processing module, wherein the acquisition module is used for acquiring a first picture set of the ceramic tile, and the first picture set comprises a plurality of first sample pictures;
the processing module 42 is configured to process the first picture set to obtain a second picture set meeting a preset visual condition, where the second picture set includes a plurality of second sample pictures, and each second sample picture corresponds to one first sample picture;
a generating module 44, configured to generate an image preprocessing model of the tile by using the first picture set and the second picture set;
and a detection module 46 for detecting surface defect information of the ceramic tile using the image preprocessing model.
Optionally, the processing module includes: a filtering unit, configured to perform denoising and filtering on each first sample picture in the first picture set to obtain an intermediate picture set; the dividing unit is used for dividing the intermediate image set according to the gray value and the contrast to obtain a plurality of sub-sets, wherein each sub-set corresponds to a gray value interval and a contrast interval; and the adjusting unit is used for respectively and adaptively adjusting the brightness and the contrast of the pictures in the sub-sets aiming at each sub-set in the plurality of sub-sets, merging the adjusted pictures to generate the second picture set, wherein the brightness of each second picture in the second picture set is within a preset brightness interval, and the contrast is within a preset contrast interval.
Optionally, the filtering unit includes: the first filtering unit is used for carrying out first denoising and filtering operation on the first sample picture, and filtering environmental dust noise points in the first sample picture to obtain a first picture; and the second filtering unit is used for carrying out second denoising and filtering operation on the first picture, and filtering the light and shadow noise points in the first picture to obtain a second picture.
Optionally, the first filtering unit includes: the identification subunit is used for carrying out track identification and object identification on the first sample picture and extracting the tile texture of the first sample picture; a decomposition subunit, configured to decompose the first sample picture into a texture area and a background area, where the texture area is an area where a tile texture of a tile is located, and the background area is an area other than the tile texture; and the setting subunit is used for setting the same gray value or RGB value for all the pixel points in the background area.
Optionally, the dividing unit includes: the first calculating subunit is used for extracting the gray value and the contrast of each first intermediate picture in the intermediate picture set and calculating the average gray value and the average contrast value of all pictures in the intermediate picture set; the second calculating subunit is used for calculating a first difference value and a second difference value between the gray value and the contrast of each first intermediate picture and the gray average value and the contrast average value respectively; a dividing subunit, configured to divide the first intermediate picture into a first subset if a first intermediate picture with a first difference value greater than a first preset value and a second difference value greater than a second preset value exists in the intermediate picture set; if a second intermediate picture with a first difference value smaller than a third preset value and a second difference value smaller than a fourth preset value exists in the intermediate picture set, dividing the second intermediate picture into a second subset; if a third intermediate picture with a first difference value larger than or equal to the third preset value and smaller than or equal to the first preset value exists in the intermediate picture set, and a second difference value larger than or equal to the fourth preset value and smaller than or equal to the second preset value exists in the intermediate picture set, dividing the third intermediate picture into a third subset, wherein the first subset is a light color plate picture, the second subset is a dark color plate picture, and the third subset is a neutral color plate picture.
Optionally, the adjusting unit includes: a lifting subunit, configured to, for a first subset of the light palette pictures, lift a display gamma value of each first intermediate picture in the first subset; a reduction subunit, configured to reduce, for a second subset of the deep-panel pictures, a display gamma value of each second intermediate picture in the second subset; a maintaining subunit, configured to maintain, for a third subset of the neutral-color-panel pictures, a display gamma value of each third intermediate picture in the third subset.
Optionally, the generating module includes: a pairing unit, configured to configure each first picture in the first picture set as input data, configure each second picture in the second picture set as output data, and pair the first picture in the first picture set and the second picture in the second picture set with each other to obtain a plurality of sample pairs; and the training unit is used for training the initial model of the ceramic tile by adopting the plurality of samples to obtain an image preprocessing model for generating the ceramic tile.
Optionally, the detection module includes: the acquisition unit is used for acquiring an initial tile picture to be detected; the first output unit is used for inputting the initial tile picture into the image preprocessing model and outputting a target tile picture meeting the preset visual condition; and the second output unit is used for inputting the target tile picture into a preset defect detection model and outputting the surface defect information of the initial tile picture, wherein the model parameters of the preset defect detection model are matched with the preset visual conditions.
It should be noted that, the above modules may be implemented by software or hardware, and for the latter, the following may be implemented, but not limited to: the modules are all positioned in the same processor; alternatively, the modules are respectively located in different processors in any combination.
Example 3
Embodiments of the present invention also provide a storage medium having a computer program stored therein, wherein the computer program is arranged to perform the steps of any of the above method embodiments when executed.
Alternatively, in the present embodiment, the storage medium may be configured to store a computer program for executing the steps of:
s1, collecting a first picture set of the ceramic tile, wherein the first picture set comprises a plurality of first sample pictures;
s2, processing the first picture set to obtain a second picture set meeting preset visual conditions, wherein the second picture set comprises a plurality of second sample pictures, and each second sample picture corresponds to one first sample picture;
s3, generating an image preprocessing model of the ceramic tile by adopting the first picture set and the second picture set;
and S4, detecting the surface defect information of the ceramic tile by using the image preprocessing model.
Optionally, in this embodiment, the storage medium may include, but is not limited to: various media capable of storing computer programs, such as a usb disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk.
Embodiments of the present invention also provide an electronic device comprising a memory having a computer program stored therein and a processor arranged to run the computer program to perform the steps of any of the above method embodiments.
Optionally, the electronic device may further include a transmission device and an input/output device, where the transmission device is connected to the processor, and the input/output device is connected to the processor.
Optionally, in this embodiment, the processor may be configured to execute the following steps by a computer program:
s1, collecting a first picture set of the ceramic tile, wherein the first picture set comprises a plurality of first sample pictures;
s2, processing the first picture set to obtain a second picture set meeting preset visual conditions, wherein the second picture set comprises a plurality of second sample pictures, and each second sample picture corresponds to one first sample picture;
s3, generating an image preprocessing model of the ceramic tile by adopting the first picture set and the second picture set;
and S4, detecting the surface defect information of the ceramic tile by using the image preprocessing model.
Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation manners, and this embodiment is not described herein again.
The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments.
In the above embodiments of the present application, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one type of division of logical functions, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk, and various media capable of storing program codes.
The foregoing is only a preferred embodiment of the present application and it should be noted that those skilled in the art can make several improvements and modifications without departing from the principle of the present application, and these improvements and modifications should also be considered as the protection scope of the present application.
Claims (7)
1. A method for detecting surface defects of ceramic tiles, comprising:
collecting a first picture set of a ceramic tile, wherein the first picture set comprises a plurality of first sample pictures;
processing the first picture set to obtain a second picture set meeting a preset visual condition, wherein the second picture set comprises a plurality of second sample pictures, and each second sample picture corresponds to one first sample picture;
generating an image preprocessing model of the ceramic tile by adopting the first picture set and the second picture set;
detecting surface defect information of the ceramic tile by adopting the image preprocessing model;
wherein, processing the first picture set to obtain a second picture set conforming to a preset view effect comprises: for each first sample picture in the first picture set, performing denoising and filtering on the first sample picture to obtain an intermediate picture set; dividing the intermediate image set according to the gray value and the contrast to obtain a plurality of subsets, wherein each subset corresponds to a gray value interval and a contrast interval, the first subset is a light color plate image, the second subset is a dark color plate image, and the third subset is a neutral color plate image; for a first subset of light panel pictures, increasing a display gamma value of each first intermediate picture in the first subset; for a second subset of the darkroom slate pictures, reducing the display gamma value of each second intermediate picture in the second subset; aiming at a third subset of the neutral color plate pictures, maintaining the display gamma value of each third intermediate picture in the third subset, and combining the adjusted pictures to generate a second picture set, wherein the brightness of each second picture in the second picture set is within a preset brightness interval, and the contrast is within a preset contrast interval;
generating an image preprocessing model of the tile by using the first picture set and the second picture set comprises the following steps: configuring each first picture in the first picture set as input data, configuring each second picture in the second picture set as output data, and pairing the first pictures in the first picture set and the second pictures in the second picture set to obtain a plurality of sample pairs; and training the initial model of the ceramic tile by adopting the plurality of samples to obtain an image preprocessing model for generating the ceramic tile.
2. The method of claim 1, wherein denoising filtering the first sample picture comprises:
carrying out first denoising and filtering operation on the first sample picture, and filtering environmental dust noise points in the first sample picture to obtain a first picture;
and carrying out second denoising and filtering operation on the first picture, and filtering light and shadow noise points in the first picture to obtain a second picture.
3. The method according to claim 2, wherein performing a first denoising and filtering operation on the first sample picture to filter the environmental dust noise in the first sample picture to obtain a first picture comprises:
carrying out track identification and object identification on the first sample picture, and extracting the tile texture of the first sample picture;
decomposing the first sample picture into a texture area and a background area, wherein the texture area is an area where the tile texture of the tile is located, and the background area is other areas except the tile texture;
and setting the same gray value or RGB value for all the pixel points in the background area.
4. The method of claim 1, wherein dividing the set of intermediate pictures by gray value and contrast to obtain a plurality of subsets comprises:
extracting the gray value and the contrast of each first intermediate picture in the intermediate picture set, and calculating the gray average value and the contrast average value of all pictures in the intermediate picture set;
calculating a first difference value and a second difference value between the gray value and the contrast of each first intermediate picture and the gray average value and the contrast average value respectively;
if a first intermediate picture with a first difference value larger than a first preset value and a second difference value larger than a second preset value exists in the intermediate picture set, dividing the first intermediate picture into a first subset; if a second intermediate picture with a first difference value smaller than a third preset value and a second difference value smaller than a fourth preset value exists in the intermediate picture set, dividing the second intermediate picture into a second subset; and if a third intermediate picture with a first difference value larger than or equal to the third preset value and smaller than or equal to the first preset value exists in the intermediate picture set, and a second difference value larger than or equal to the fourth preset value and smaller than or equal to the second preset value exists in the intermediate picture set, dividing the third intermediate picture into a third subset.
5. The method of claim 1, wherein detecting surface defect information of the tile using the image pre-processing model comprises:
acquiring an initial tile picture to be detected;
inputting the initial tile picture into the image preprocessing model, and outputting a target tile picture meeting the preset visual condition;
inputting the target tile picture into a preset defect detection model, and outputting the surface defect information of the initial tile picture, wherein the model parameters of the preset defect detection model are matched with the preset visual conditions.
6. A device for detecting defects on the surface of ceramic tiles, comprising:
the tile image acquisition device comprises an acquisition module, a processing module and a display module, wherein the acquisition module is used for acquiring a first image set of a tile, and the first image set comprises a plurality of first sample images;
the processing module is used for processing the first picture set to obtain a second picture set meeting preset visual conditions, wherein the second picture set comprises a plurality of second sample pictures, and each second sample picture corresponds to one first sample picture;
the generating module is used for generating an image preprocessing model of the ceramic tile by adopting the first picture set and the second picture set;
the detection module is used for detecting the surface defect information of the ceramic tile by adopting the image preprocessing model;
wherein the apparatus is further configured to: processing the first picture set to obtain a second picture set conforming to a preset view angle effect, wherein the step of processing the first picture set comprises the following steps: for each first sample picture in the first picture set, performing denoising and filtering on the first sample picture to obtain an intermediate picture set; dividing the intermediate image set according to the gray value and the contrast to obtain a plurality of subsets, wherein each subset corresponds to a gray value interval and a contrast interval, the first subset is a light color plate image, the second subset is a dark color plate image, and the third subset is a neutral color plate image; for a first subset of the light panel pictures, increasing a display gamma value of each first intermediate picture in the first subset; for a second subset of the darkroom slate pictures, reducing the display gamma value of each second intermediate picture in the second subset; aiming at a third subset of the neutral color plate pictures, maintaining the display gamma value of each third intermediate picture in the third subset, and combining the adjusted pictures to generate a second picture set, wherein the brightness of each second picture in the second picture set is within a preset brightness interval, and the contrast is within a preset contrast interval;
the generation module comprises: the matching unit is used for configuring each first picture in the first picture set as input data, configuring each second picture in the second picture set as output data, and matching the first pictures in the first picture set and the second pictures in the second picture set to obtain a plurality of sample pairs; and the training unit is used for training the initial model of the ceramic tile by adopting the plurality of samples to obtain an image preprocessing model for generating the ceramic tile.
7. A storage medium, comprising a stored computer program, wherein the computer program is operative to perform the steps of the method of any of the preceding claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210680945.7A CN114782418B (en) | 2022-06-16 | 2022-06-16 | Detection method and device for ceramic tile surface defects and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210680945.7A CN114782418B (en) | 2022-06-16 | 2022-06-16 | Detection method and device for ceramic tile surface defects and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114782418A CN114782418A (en) | 2022-07-22 |
| CN114782418B true CN114782418B (en) | 2022-09-16 |
Family
ID=82421431
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210680945.7A Active CN114782418B (en) | 2022-06-16 | 2022-06-16 | Detection method and device for ceramic tile surface defects and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114782418B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105723209A (en) * | 2013-10-11 | 2016-06-29 | 普罗杰塔工程有限责任公司 | Decoration line |
| CN109410129A (en) * | 2018-09-28 | 2019-03-01 | 大连理工大学 | A kind of method of low light image scene understanding |
| CN109540925A (en) * | 2019-01-23 | 2019-03-29 | 南昌航空大学 | Complicated ceramic tile surface defect inspection method based on difference shadow method and local variance measurement operator |
| CN112308803A (en) * | 2020-11-25 | 2021-02-02 | 哈尔滨工业大学 | Self-supervision low-illumination image enhancement and denoising method based on deep learning |
| CN112419179A (en) * | 2020-11-18 | 2021-02-26 | 北京字跳网络技术有限公司 | Method, device, equipment and computer readable medium for repairing image |
| CN113627435A (en) * | 2021-07-13 | 2021-11-09 | 南京大学 | Method and system for detecting and identifying flaws of ceramic tiles |
| CN114154552A (en) * | 2021-10-22 | 2022-03-08 | 佛山科学技术学院 | Method, device, medium and equipment for detecting grading and color separation of ceramic tiles |
| CN114202508A (en) * | 2021-11-04 | 2022-03-18 | 广东工业大学 | Detection method and system suitable for highlighting surface defects of various ceramic tiles |
| CN114332004A (en) * | 2021-12-27 | 2022-04-12 | 华南师范大学 | Method and device for detecting surface defects of ceramic tiles, electronic equipment and storage medium |
| CN114419038A (en) * | 2022-03-28 | 2022-04-29 | 深圳市信润富联数字科技有限公司 | Method and device for identifying surface defects of hub, storage medium and electronic equipment |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| ITRM20130068A1 (en) * | 2013-02-08 | 2014-08-09 | Marmoelettromeccanica S R L | REINFORCEMENT SYSTEM FOR GRES, PORCELAIN OR CERAMIC SHEETS, MARBLE OR TRAVERTINE OF THIN THICKNESS, IN PARTICULAR FOR VENTILATED WALLS |
-
2022
- 2022-06-16 CN CN202210680945.7A patent/CN114782418B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105723209A (en) * | 2013-10-11 | 2016-06-29 | 普罗杰塔工程有限责任公司 | Decoration line |
| CN109410129A (en) * | 2018-09-28 | 2019-03-01 | 大连理工大学 | A kind of method of low light image scene understanding |
| CN109540925A (en) * | 2019-01-23 | 2019-03-29 | 南昌航空大学 | Complicated ceramic tile surface defect inspection method based on difference shadow method and local variance measurement operator |
| CN112419179A (en) * | 2020-11-18 | 2021-02-26 | 北京字跳网络技术有限公司 | Method, device, equipment and computer readable medium for repairing image |
| CN112308803A (en) * | 2020-11-25 | 2021-02-02 | 哈尔滨工业大学 | Self-supervision low-illumination image enhancement and denoising method based on deep learning |
| CN113627435A (en) * | 2021-07-13 | 2021-11-09 | 南京大学 | Method and system for detecting and identifying flaws of ceramic tiles |
| CN114154552A (en) * | 2021-10-22 | 2022-03-08 | 佛山科学技术学院 | Method, device, medium and equipment for detecting grading and color separation of ceramic tiles |
| CN114202508A (en) * | 2021-11-04 | 2022-03-18 | 广东工业大学 | Detection method and system suitable for highlighting surface defects of various ceramic tiles |
| CN114332004A (en) * | 2021-12-27 | 2022-04-12 | 华南师范大学 | Method and device for detecting surface defects of ceramic tiles, electronic equipment and storage medium |
| CN114419038A (en) * | 2022-03-28 | 2022-04-29 | 深圳市信润富联数字科技有限公司 | Method and device for identifying surface defects of hub, storage medium and electronic equipment |
Non-Patent Citations (1)
| Title |
|---|
| 瓷砖表面质量视觉检测技术研究;高倩倩;《中国优秀硕士学位论文全文数据库》;20190115(第01期);第I138-2893 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114782418A (en) | 2022-07-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110766679B (en) | Lens contamination detection method and device and terminal equipment | |
| CN110473242B (en) | Texture feature extraction method, texture feature extraction device and terminal equipment | |
| CN111527539A (en) | Correction method, correction device and correction system for arbitrary splicing of full screens | |
| CN109214996B (en) | Image processing method and device | |
| CN111383186A (en) | Image processing method and device and terminal equipment | |
| CN113781396B (en) | Screen defect detection method, device, equipment and storage medium | |
| CN113168669A (en) | Image processing method and device, electronic equipment and readable storage medium | |
| CN110855876B (en) | Image processing method, terminal and computer storage medium | |
| CN110458789B (en) | Image definition evaluating method and device and electronic equipment | |
| CN107909554B (en) | Image noise reduction method and device, terminal equipment and medium | |
| CN116883336A (en) | Image processing method, device, computer equipment and medium | |
| CN108107611B (en) | Self-adaptive defect detection method and device and electronic equipment | |
| CN115587966A (en) | Method and system for detecting whether parts are missing or not under condition of uneven illumination | |
| CN110838088B (en) | Multi-frame noise reduction method and device based on deep learning and terminal equipment | |
| CN114782418B (en) | Detection method and device for ceramic tile surface defects and storage medium | |
| CN105809677B (en) | Image edge detection method and system based on bilateral filter | |
| CN115375689B (en) | Tobacco shred barrel detection method, device, equipment and medium based on machine vision | |
| CN111598794A (en) | Image imaging method and device for removing underwater overlapping condition | |
| CN111311610A (en) | Image segmentation method and terminal equipment | |
| JP2006226837A (en) | Method and apparatus for inspecting stain | |
| CN115829848A (en) | Method, apparatus and computer-readable storage medium for processing graphic symbols | |
| CN115619796A (en) | Method and device for obtaining photovoltaic module template and nonvolatile storage medium | |
| CN110147765A (en) | A kind of image processing method and device | |
| CN111445431B (en) | Image segmentation method, terminal equipment and computer readable storage medium | |
| CN113111921B (en) | Object identification method, device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |