CN117115197B - Intelligent processing method and system for design data of LED lamp bead circuit board - Google Patents
Intelligent processing method and system for design data of LED lamp bead circuit board Download PDFInfo
- Publication number
- CN117115197B CN117115197B CN202310999665.7A CN202310999665A CN117115197B CN 117115197 B CN117115197 B CN 117115197B CN 202310999665 A CN202310999665 A CN 202310999665A CN 117115197 B CN117115197 B CN 117115197B
- Authority
- CN
- China
- Prior art keywords
- connected domain
- lamp bead
- circuit board
- led lamp
- segmentation result
- 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
- 239000011324 bead Substances 0.000 title claims abstract description 375
- 238000013461 design Methods 0.000 title claims abstract description 34
- 238000003672 processing method Methods 0.000 title claims abstract description 14
- 230000011218 segmentation Effects 0.000 claims abstract description 103
- 238000010586 diagram Methods 0.000 claims abstract description 101
- 230000008859 change Effects 0.000 claims abstract description 20
- 238000012545 processing Methods 0.000 claims abstract description 17
- 238000004891 communication Methods 0.000 claims abstract description 7
- 238000000034 method Methods 0.000 claims description 38
- 238000004364 calculation method Methods 0.000 claims description 15
- 102100035971 Molybdopterin molybdenumtransferase Human genes 0.000 claims description 7
- 101710119577 Molybdopterin molybdenumtransferase Proteins 0.000 claims description 7
- 230000002708 enhancing effect Effects 0.000 claims description 6
- 238000003064 k means clustering Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 4
- 238000009826 distribution Methods 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 238000000605 extraction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012795 verification Methods 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
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- 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
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- 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
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- 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
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
- G06V10/763—Non-hierarchical techniques, e.g. based on statistics of modelling distributions
-
- 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
- G06T2207/30141—Printed circuit board [PCB]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Multimedia (AREA)
- Probability & Statistics with Applications (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of image processing, in particular to an intelligent processing method and system for design data of an LED lamp bead circuit board, comprising the following steps: acquiring a gray level image of an LED lamp bead circuit board; obtaining the similarity degree of the lamp beads of the connected domain in the segmentation result diagram under each threshold; obtaining the reliability degree of the connected domain as the lamp bead in the segmentation result diagram under each threshold according to the association degree of the adjacent connected domains of the connected domain in the segmentation result diagram under each threshold; the change of the number of the lamp beads under different thresholds is obtained according to the reliability degree that the communication domain is the lamp beads, the lamp bead gray scale interval is obtained according to the change of the number of the lamp beads, the enhanced LED lamp bead circuit board image is obtained according to the lamp bead gray scale interval, and intelligent processing of the design data of the LED lamp bead circuit board is realized. The invention realizes the linear enhancement of the self-adaptive parameters, can effectively reduce the influence of factors such as noise and the like on the image characteristic recognition, and improves the intelligent degree of the system.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to an intelligent processing method and system for design data of an LED lamp bead circuit board.
Background
The LED lamp bead circuit board design data processing method mainly relates to the aspects of data acquisition and cleaning, feature extraction, data analysis and modeling, design optimization, visual display, verification test and data management, wherein the feature extraction is to extract useful features from original design data, including component types, positions, connection modes and the like, and the circuit board shape and layout information can be extracted through an image processing technology for analysis.
When designing the LED lamp bead circuit board, the information such as the circuit board shape and the layout of components of the existing circuit board needs to be analyzed and extracted, the circuit board image needs to be segmented, and different components are segmented from the circuit board image, but the segmentation result of the image may be inaccurate due to noise influence, so that the image needs to be enhanced in advance, and the influence of noise and the like is eliminated.
Disclosure of Invention
The invention provides an intelligent processing method and system for design data of an LED lamp bead circuit board, which are used for solving the existing problems.
The invention discloses an intelligent processing method and system for design data of an LED lamp bead circuit board, and the intelligent processing method and system adopt the following technical scheme:
The embodiment of the invention provides an intelligent processing method for design data of an LED lamp bead circuit board, which comprises the following steps:
Acquiring a gray level image of an LED lamp bead circuit board;
dividing the gray level images of the LED lamp bead circuit board by different thresholds to obtain LED lamp bead circuit board division result diagrams under different thresholds;
The segmentation result diagram of the LED lamp bead circuit board under any threshold is recorded as a segmentation result diagram; obtaining the similarity degree of the lamp beads of each connected domain in the segmentation result diagram; acquiring adjacent connected domains of each connected domain; acquiring the distance average value from each connected domain to the adjacent connected domain according to the adjacent connected domain of each connected domain, and recording the distance average value as a first distance average value of each connected domain; acquiring the distance average value from each connected domain to other connected domains, and recording the distance average value as a second distance average value of each connected domain; obtaining a lamp bead constraint coefficient of each connected domain; obtaining the association degree of adjacent connected domains of each connected domain according to the first distance average value of each connected domain, the second distance average value of each connected domain and the lamp bead constraint coefficient of each connected domain; obtaining the reliability degree of each connected domain of the segmentation result diagram under different thresholds according to the association degree of adjacent connected domains of each connected domain and the similarity degree of the lamp beads;
Obtaining the change of the number of the lamp beads according to the reliability degree that all the connected domains of the segmentation result diagram under all the threshold values are the lamp beads; obtaining a lamp bead gray scale interval according to the change of the number of the lamp beads; and linearly enhancing the LED lamp bead circuit board image according to the lamp bead gray scale interval to obtain the enhanced LED lamp bead circuit board image, extracting information of the enhanced LED lamp bead circuit board image, and analyzing the information to realize intelligent processing of the design data of the LED lamp bead circuit board.
Preferably, the method for obtaining the similarity degree of the lamp beads of each connected domain in the segmentation result graph includes the following specific steps:
K-Means clustering is carried out on all gradient directions of the G connected domain in the segmentation result diagram to obtain clusters C 1,C2,C3,C4 of four gradient directions; acquiring the average value of adjacent gradient directions in each cluster, and respectively marking the included angles of the average values of the adjacent gradient directions in each cluster as Acquisition/>The average value of (2) is denoted as/>
The calculation expression of the similarity degree of the lamp beads of the G-th connected domain is as follows:
Wherein D G represents the degree of similarity of the lamp beads of the G-th connected domain; k represents the number of clusters; Representing the included angle of the average value of the first adjacent gradient directions in each cluster of the G connected domain; /(I) And the average value of the included angles of the average values of all adjacent gradient directions in each cluster of the G connected domain is represented.
Preferably, the method for obtaining the adjacent connected domain of each connected domain includes the following specific steps:
Presetting a parameter n, for the G-th connected domain in the segmentation result diagram, acquiring the mass centers of all connected domains in the segmentation result diagram, taking the distance between the mass center of the G-th connected domain and the mass centers of all other connected domains as the distance between the G-th connected domain and all connected domains in the segmentation result diagram, and taking the average value of the distances between the G-th connected domain and all connected domains as And defining n connected domains corresponding to n minimum values in the distances from the centroid of the G connected domain to the centroids of other connected domains as adjacent connected domains of the G connected domain.
Preferably, the method for obtaining the average value of the distance from each connected domain to its adjacent connected domain according to the adjacent connected domain of each connected domain includes the following specific steps:
The calculation expression of the distance average value between the G-th connected domain and the adjacent connected domain is as follows:
In the method, in the process of the invention, Representing the average value of the distance between the G-th connected domain and the adjacent connected domain; l G,i represents a distance between the G-th communicating region and the i-th communicating region in the adjacent communicating region of the G-th communicating region; n is a preset parameter.
Preferably, the method for obtaining the constraint coefficients of the lamp beads of each connected domain includes the following specific steps:
For the G-th connected domain in the segmentation result diagram, setting the barycenter coordinate of the connected domain G as (x G,yG), taking the center point of the segmentation result diagram as a point O, and taking the point O as the circle center to obtain the same-direction boundary of the G-th connected domain; wherein the communicating domain A, B is a homodromous adjacent communicating domain on the homodromous boundary of the communicating domain G, and the centroid coordinate of the communicating domain B is (x B,yB); the lamp bead constraint coefficient of the G-th connected domain
Preferably, the obtaining the association degree of adjacent connected domains of each connected domain according to the first distance average value of each connected domain, the second distance average value of each connected domain and the lamp bead constraint coefficient of each connected domain includes the following specific methods:
The calculation expression of the association degree of the adjacent connected domains of the G-th connected domain is as follows:
wherein C G represents the degree of association between adjacent connected domains of the G-th connected domain; Representing the average value of the distance between the G-th connected domain and the adjacent connected domain; /(I) Representing the average value of the distances from the G-th connected domain to all other connected domains; AC G represents the lamp bead constraint coefficient of the G-th connected domain; exp () represents an exponential function based on a natural constant.
Preferably, the method for obtaining the reliability degree of the lamp beads for each connected domain of the segmentation result diagram under different thresholds according to the association degree of adjacent connected domains and the similarity degree of the lamp beads of each connected domain includes the following specific steps:
And for the G-th connected domain in the segmentation result diagram under different thresholds, obtaining the reliability degree of the G-th connected domain as the lamp bead according to the similarity degree of the lamp bead of the G-th connected domain and the association degree of the adjacent connected domains of the G-th connected domain, wherein the calculation expression formula is as follows:
RG＝DG×CG
Wherein R G represents the reliability of the G-th communication domain as a lamp bead; d G represents the degree of similarity of the lamp beads of the G-th connected domain; c G represents the degree of association between adjacent connected domains of the G-th connected domain.
Preferably, the reliability degree of the lamp beads according to all the connected domains of the segmentation result diagram under all the threshold values is changed to obtain the number of the lamp beads; the method for obtaining the light bead gray scale interval according to the change of the number of the light beads comprises the following specific steps:
presetting a threshold t1, for an LED lamp bead circuit board segmentation result diagram under any threshold, acquiring the reliability degree of all connected domains of the LED lamp bead circuit board segmentation result diagram under the threshold as lamp beads, and marking the connected domains corresponding to the reliability degree of the connected domains as the lamp beads being greater than or equal to the threshold t1 as the LED lamp beads, thereby acquiring the quantity of all the LED lamp beads in the LED lamp bead circuit board segmentation result diagram under the threshold; similarly, the number of the lamp beads in the LED lamp bead circuit board segmentation result diagram under each threshold value is obtained;
Taking a threshold value corresponding to the maximum value of the number of the LED lamp beads in the LED lamp bead circuit board segmentation result diagram as the initial gray level of a lamp bead gray level interval, and marking as I min; and marking a threshold value corresponding to the number of the LED lamp beads in the LED lamp bead circuit board segmentation result diagram as the ending gray level of the lamp bead gray level interval, and marking the ending gray level as I max, wherein the lamp bead gray level interval is [ I min,Imax ].
Preferably, the linear enhancement is performed on the LED lamp bead circuit board image according to the lamp bead gray scale interval, and the enhanced LED lamp bead circuit board image is obtained, which comprises the following specific steps:
Presetting a threshold t2, acquiring the gray value of each pixel point in the gray image of the LED lamp bead circuit board, marking any pixel point in the gray image of the LED lamp bead circuit board as a target pixel point, marking the threshold t2 as an enhancement coefficient of the target pixel point if the gray value of the target pixel point is not in a lamp bead gray interval, and taking the product of the gray value of the target pixel point and the enhancement coefficient of the target pixel point as a new gray value of the target pixel point; if the gray value of the target pixel point is in the bead gray interval, marking a connected domain in an LED bead circuit board segmentation result diagram corresponding to the target pixel point under the threshold value of I min as a target connected domain, marking the sum of the reliability of the target connected domain as a bead and the threshold value t2 as an enhancement coefficient of the pixel point, and taking the product of the gray value of the target pixel point and the enhancement coefficient of the target pixel point as a new gray value of the target pixel point; and similarly, linearly enhancing all pixel points in the gray level image of the LED lamp bead circuit board to obtain the enhanced image of the LED lamp bead circuit board.
The embodiment of the invention provides an intelligent processing system for LED lamp bead circuit board design data, which comprises an image acquisition module, a lamp bead reliability acquisition module and an image enhancement module, wherein:
The image acquisition module is used for acquiring a gray image of the LED lamp bead circuit board;
The lamp bead similarity obtaining module is used for obtaining the lamp bead similarity of each connected domain in the LED lamp bead circuit board segmentation result diagram under each threshold;
The lamp bead reliability obtaining module is used for obtaining the reliability of each connected domain as a lamp bead in the LED lamp bead circuit board segmentation result diagram under each threshold according to the association degree of the adjacent connected domains of each connected domain in the LED lamp bead circuit board segmentation result diagram under each threshold;
The image enhancement module is used for obtaining the change of the number of the lamp beads under different thresholds according to the reliability degree that the connected domain is the lamp beads, obtaining a lamp bead gray scale interval according to the change of the number of the lamp beads, obtaining an enhanced LED lamp bead circuit board image according to the lamp bead gray scale interval, and realizing intelligent processing of design data of the LED lamp bead circuit board.
The technical scheme of the invention has the beneficial effects that: when the gray level image of the LED lamp bead circuit board is linearly enhanced, the gray level of a background area and the gray level of a target area are likely to be relatively close, the gray level image of the whole LED lamp bead circuit board is linearly enhanced, the background area is also enhanced, and the problem that the enhancement effect of the target area is not obvious is solved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of steps of an intelligent processing method for design data of an LED lamp bead circuit board;
FIG. 2 is a block diagram of an intelligent processing system for LED lamp bead circuit board design data;
FIG. 3 is a gray scale image of an LED bead circuit board of the present invention;
fig. 4 is a graph showing the annular distribution of the LED lamp beads according to the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following is a detailed description of specific implementation, structure, characteristics and effects of the method and system for intelligently processing design data of the LED lamp bead circuit board according to the invention in combination with the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The invention provides a method and a system for intelligently processing design data of an LED lamp bead circuit board, which are specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of steps of an intelligent processing method for design data of an LED lamp bead circuit board according to an embodiment of the present invention is shown, where the method includes the following steps:
step S001: and acquiring a gray level image of the LED lamp bead circuit board.
It should be noted that, when the shape and layout information of the LED lamp bead circuit board are extracted, the shell of the LED lamp bead is usually made of transparent or semitransparent material, so that the characteristics of the collected LED lamp bead circuit board image are not obvious, and each part of the whole LED lamp bead circuit board image cannot be accurately identified. The LED lamp bead circuit board image is required to be grayed, threshold segmentation of different thresholds is carried out on the LED lamp bead circuit board gray level image, the change of the number of lamp bead areas in a threshold segmentation result diagram of different thresholds is analyzed, a lamp bead gray level interval is obtained, and the LED lamp bead circuit board image is enhanced by combining linear enhancement.
Specifically, an image of the LED lamp bead circuit board is collected by the camera and is subjected to a graying operation, so as to obtain a gray image of the LED lamp bead circuit board, as shown in fig. 3, wherein the graying operation is an existing operation, and the description is omitted here.
And obtaining the gray level image of the LED lamp bead circuit board.
Step S002: and obtaining the similarity degree of the lamp beads of each connected domain in the LED lamp bead circuit board segmentation result diagram under each threshold.
It should be noted that, according to fig. 3, the important information in the gray level image of the LED lamp bead circuit board is LED lamp beads and round holes, wherein the LED lamp beads are generally rectangular in shape, the LED lamp beads are uniformly distributed on the circuit board, and the shell combined with the LED lamp beads is generally made of transparent or semitransparent material, so that the gray level value of the LED lamp beads is higher. And (3) carrying out threshold segmentation on the gray level image of the LED lamp bead circuit board with different thresholds, and obtaining the similarity degree of the lamp beads of each connected domain according to the shape of the connected domain under each threshold.
A parameter d is preset, where the embodiment is described by d=1, and the embodiment is not specifically limited, where d depends on the specific implementation.
Specifically, a gray level histogram of a gray level image of the LED lamp bead circuit board is obtained, the maximum value of gray level values in the gray level histogram is recorded as H max, the minimum value is recorded as H min, and threshold segmentation is carried out once every step length d; the gray level image of the LED lamp bead circuit board is divided by using H min as a threshold value, and then divided by using H min+d,Hmin+2d,…,Hmax as a threshold value, so that a (max-min+1) LED lamp bead circuit board division result diagram is obtained.
It should be noted that, the gradient directions of the rectangular connected domain or the circular connected domain can be clustered into four types, and the gradient direction mean value of each cluster and the gradient direction mean value difference of the adjacent clusters are pi/2, so that the LED lamp bead connected domain also meets the condition; for any one connected domain, if the difference of the included angles of the average values of the four clustering adjacent gradient directions of the connected domain is smaller, the probability that the connected domain is a rectangular connected domain or a circular connected domain is larger, and the similarity degree of the lamp beads of the connected domain is larger.
Specifically, for a G-th connected domain in the LED lamp bead circuit board segmentation result diagram under any threshold, carrying out K-Means clustering on all gradient directions of the connected domain, wherein the clustering number of K=4, so as to obtain clusters C 1,C2,C3,C4 of four gradient directions; acquiring the average value of adjacent gradient directions in each cluster, and respectively marking the included angles of the average values of the adjacent gradient directions in each cluster asAcquisition/>The average value of (2) is denoted as/>
The calculation expression of the similarity degree of the lamp beads of the G-th connected domain is as follows:
Wherein D G represents the degree of similarity of the lamp beads of the G-th connected domain; k represents the number of clusters; Representing the included angle of the average value of the first adjacent gradient directions in each cluster of the G connected domain; /(I) And the average value of the included angles of the average values of all adjacent gradient directions in each cluster of the G connected domain is represented.
And similarly, obtaining the similarity degree of the lamp beads of each connected domain in the LED lamp bead circuit board segmentation result diagram under each threshold.
So far, the similarity degree of the lamp beads of each connected domain in the LED lamp bead circuit board segmentation result diagram under each threshold value is obtained.
Step S003: and obtaining the reliability degree of each connected domain in the LED lamp bead circuit board segmentation result diagram under each threshold according to the association degree of the adjacent connected domains of each connected domain in the LED lamp bead circuit board segmentation result diagram under each threshold.
The LED lamp beads on the LED lamp bead circuit board are uniformly distributed, and the distance between adjacent LED lamp bead communicating domains is regular; for any one connected domain, if the distance average value between the connected domain and the adjacent connected domain and the distance average value difference between all connected domains in the LED lamp bead circuit board segmentation result diagram are smaller, the association degree of the adjacent connected domain of the connected domain is larger, and the possibility that the connected domain is an LED lamp bead is larger.
A parameter n is preset, where the present embodiment is described with n=4 cases, and the present embodiment is not specifically limited, where n depends on the specific implementation.
Specifically, for the G-th connected domain in the LED lamp bead circuit board segmentation result diagram under any threshold value, the centroid of all connected domains in the LED lamp bead circuit board segmentation result diagram under the threshold value is obtained, the distances between the centroid of the G-th connected domain and the centroids of all other connected domains are calculated, the distances between the centroid of the G-th connected domain and the centroids of all other connected domains are used as the distances between the G-th connected domain and all connected domains in the LED lamp bead circuit board segmentation result diagram, and the average value of the distances between the G-th connected domain and all connected domains is recorded asAnd defining n connected domains corresponding to n minimum values in the distances from the centroid of the G connected domain to the centroids of other connected domains as adjacent connected domains of the G connected domain.
The calculation expression of the distance average value between the G-th connected domain and the adjacent connected domain is:
In the method, in the process of the invention, Representing the average value of the distance between the G-th connected domain and the adjacent connected domain; l G,i represents a distance between the G-th communicating region and the i-th communicating region in the adjacent communicating region of the G-th communicating region; n is a preset parameter.
It should be noted that, there are two general types of distributions of the lamp beads on the LED lamp bead circuit board: the array distribution and the annular distribution, in this embodiment, the beads on the LED bead circuit board are distributed and arranged in an annular manner, so that the distances from any LED bead in the LED bead circuit board image to the centers of the LED bead circuit board images and two co-adjacent LED beads thereof should be identical or nearly identical.
Specifically, for the G-th connected domain in the LED lamp bead circuit board segmentation result diagram under any threshold, setting the barycenter coordinate of the connected domain G as (x G,yG), and acquiring the same-direction boundary of the G-th connected domain by taking the point O as the circle center if the central point of the LED lamp bead circuit board segmentation result diagram under the threshold is the point O; the annular distribution diagram of the LED lamp beads is shown in fig. 4, wherein the communicating region A, B is a homodromous adjacent communicating region on the homodromous boundary of the communicating region G, the centroid coordinate of the communicating region A is (x A,yA), and the centroid coordinate of the communicating region B is (x B,yB); the lamp bead constraint coefficient of the G-th connected domain
In summary, the calculation expression of the association degree of the adjacent connected domain of the G-th connected domain is:
wherein C G represents the degree of association between adjacent connected domains of the G-th connected domain; Representing the average value of the distance between the G-th connected domain and the adjacent connected domain; /(I) Representing the average value of the distances from the G-th connected domain to all other connected domains; AC G represents the lamp bead constraint coefficient of the G-th connected domain; exp () represents an exponential function based on a natural constant.
And similarly, obtaining the association degree of adjacent connected domains of each connected domain in the LED lamp bead circuit board segmentation result diagram under each threshold.
It should be noted that, by combining the distance regularity between the LED lamp beads in the LED lamp bead circuit board image with the LED lamp bead distribution regularity, and adding the lamp bead constraint coefficient, the reliability degree that each connected domain is a lamp bead in the LED lamp bead circuit board segmentation result diagram under each threshold value is obtained.
Specifically, for the G-th connected domain in the LED lamp bead circuit board segmentation result diagram under any threshold, the reliability degree of the G-th connected domain as the lamp bead is obtained according to the similarity degree of the lamp beads of the G-th connected domain and the association degree of the adjacent connected domains of the G-th connected domain, and the calculation expression formula is as follows:
RG＝DG×CG
Wherein R G represents the reliability of the G-th communication domain as a lamp bead; d G represents the degree of similarity of the lamp beads of the G-th connected domain; c G represents the degree of association between adjacent connected domains of the G-th connected domain.
And similarly, obtaining the reliability degree that each connected domain is a lamp bead in the LED lamp bead circuit board segmentation result diagram under each threshold value.
So far, the reliability degree that each connected domain is a lamp bead in the LED lamp bead circuit board segmentation result diagram under each threshold value is obtained.
Step S004: the change of the number of the lamp beads under different thresholds is obtained according to the reliability degree that the communication domain is the lamp beads, the lamp bead gray scale interval is obtained according to the change of the number of the lamp beads, the enhanced LED lamp bead circuit board image is obtained according to the lamp bead gray scale interval, and intelligent processing of the design data of the LED lamp bead circuit board is realized.
A threshold t1 is preset, where the present embodiment is described by t1=0.8, and the present embodiment is not specifically limited, where t1 depends on the specific implementation.
Specifically, for an LED lamp bead circuit board segmentation result diagram under any threshold value, obtaining the reliability degree that all connected domains are lamp beads of the LED lamp bead circuit board segmentation result diagram under the threshold value, and marking the connected domains corresponding to the reliability degree that the connected domains are the lamp beads which is more than or equal to the threshold value t1 as the LED lamp beads, so as to obtain the quantity of all the LED lamp beads in the LED lamp bead circuit board segmentation result diagram under the threshold value; and similarly, obtaining the number of the lamp beads in the LED lamp bead circuit board segmentation result diagram under each threshold value.
It should be noted that, because the shell of the LED lamp bead is generally made of transparent or semitransparent material, the gray value is higher, when the threshold value is traversed, as the threshold value gradually increases, the smaller the influence of other areas on the LED lamp bead is, the more and more the number of the LED lamp beads in the LED lamp bead circuit board segmentation result diagram will be, until the number of the LED lamp beads in the LED lamp bead circuit board segmentation result diagram reaches the maximum, at this time, along with the continued increase of the threshold value, the gray value of a part of the LED lamp beads will be assigned with value 0, and then the gray value of the corresponding pixel point of the LED lamp bead of the part is smaller than the threshold value at this time, and the number of the LED lamp beads starts to decrease until all the LED lamp beads are covered.
A threshold t2 is preset, where the present embodiment is described by t2=0.5, and the present embodiment is not specifically limited, where t2 depends on the specific implementation.
Specifically, taking a threshold value corresponding to the maximum value of the number of the LED lamp beads in the LED lamp bead circuit board segmentation result diagram as the initial gray level of a lamp bead gray level interval, and marking as I min; and marking a threshold value corresponding to the number of the LED lamp beads in the LED lamp bead circuit board segmentation result diagram as the ending gray level of the lamp bead gray level interval, and marking the ending gray level as I max, wherein the lamp bead gray level interval is [ I min,Imax ].
According to the obtained bead gray interval and the reliability degree that each connected domain is a bead in the LED bead circuit board segmentation result diagram under each threshold, the gray image of the LED bead circuit board is linearly enhanced, and the specific linear enhancement process is as follows: acquiring the gray value of each pixel point in the gray image of the LED lamp bead circuit board, if the gray value of any pixel point in the gray image of the LED lamp bead circuit board is not in the lamp bead gray interval, marking a threshold t2 as the enhancement coefficient of the pixel point, and then taking the result of downward rounding of the product of the gray value of the pixel point and the enhancement coefficient of the pixel point as the new gray value of the pixel point; if the gray value of the pixel is in the light bead gray interval, acquiring a connected domain in an LED light bead circuit board segmentation result diagram corresponding to the pixel under the threshold of I min, marking the connected domain as the sum of the reliability degree of the light bead and the threshold t2 as an enhancement coefficient of the pixel, and then taking the result of downward rounding of the product of the gray value of the pixel and the enhancement coefficient of the pixel as a new gray value of the pixel, wherein the new gray value of the pixel exceeding 255 is assigned as 255; and similarly, linearly enhancing all pixel points in the gray level image of the LED lamp bead circuit board to obtain the enhanced image of the LED lamp bead circuit board.
The method comprises the steps of carrying out Ojin method threshold segmentation on an enhanced LED lamp bead circuit board image, segmenting and extracting various component areas such as lamp beads and circuits and shape characteristics of the circuit board, classifying all acquired image information, combining corresponding circuit board current and voltage information to obtain design data of the LED lamp bead circuit board, analyzing the design data by using a statistical method, including descriptive statistics, frequency distribution, correlation analysis and the like, and modeling and predicting the existing LED lamp bead circuit board design data by using a machine learning algorithm to obtain a design space of the LED lamp bead circuit board. Finally, by using methods such as genetic algorithm, particle swarm algorithm and the like, the optimal parameter configuration is searched in the design space, and intelligent processing of the design data of the LED lamp bead circuit board is realized.
Referring to fig. 2, a block diagram of an intelligent processing system for design data of an LED lamp bead circuit board according to an embodiment of the present invention is shown, where the system includes the following modules:
The image acquisition module is used for acquiring a gray image of the LED lamp bead circuit board;
The lamp bead similarity obtaining module is used for obtaining the lamp bead similarity of each connected domain in the LED lamp bead circuit board segmentation result diagram under each threshold;
The lamp bead reliability obtaining module is used for obtaining the reliability of each connected domain as a lamp bead in the LED lamp bead circuit board segmentation result diagram under each threshold according to the association degree of the adjacent connected domains of each connected domain in the LED lamp bead circuit board segmentation result diagram under each threshold;
The image enhancement module is used for obtaining the change of the number of the lamp beads under different thresholds according to the reliability degree that the connected domain is the lamp beads, obtaining a lamp bead gray scale interval according to the change of the number of the lamp beads, obtaining an enhanced LED lamp bead circuit board image according to the lamp bead gray scale interval, and realizing intelligent processing of design data of the LED lamp bead circuit board.
According to the method, the device and the system, the purpose of determining the positions and the gray ranges of the bead areas in the gray level image of the LED bead circuit board is achieved according to the reliability that the connected areas are the bead areas under different thresholds, the maximum association degree of the pixel points in the gray level range is combined to obtain the enhancement coefficient of the pixel points, and finally, the linear enhancement of the adaptive parameters of the gray level image of the LED bead circuit board is achieved.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (4)
1. The intelligent processing method for the design data of the LED lamp bead circuit board is characterized by comprising the following steps of:
Acquiring a gray level image of an LED lamp bead circuit board;
dividing the gray level images of the LED lamp bead circuit board by different thresholds to obtain LED lamp bead circuit board division result diagrams under different thresholds;
The segmentation result diagram of the LED lamp bead circuit board under any threshold is recorded as a segmentation result diagram; obtaining the similarity degree of the lamp beads of each connected domain in the segmentation result diagram; acquiring adjacent connected domains of each connected domain; acquiring the distance average value from each connected domain to the adjacent connected domain according to the adjacent connected domain of each connected domain, and recording the distance average value as a first distance average value of each connected domain; acquiring the distance average value from each connected domain to other connected domains, and recording the distance average value as a second distance average value of each connected domain; obtaining a lamp bead constraint coefficient of each connected domain; obtaining the association degree of adjacent connected domains of each connected domain according to the first distance average value of each connected domain, the second distance average value of each connected domain and the lamp bead constraint coefficient of each connected domain; obtaining the reliability degree of each connected domain of the segmentation result diagram under different thresholds according to the association degree of adjacent connected domains of each connected domain and the similarity degree of the lamp beads;
obtaining the change of the number of the lamp beads according to the reliability degree that all the connected domains of the segmentation result diagram under all the threshold values are the lamp beads; obtaining a lamp bead gray scale interval according to the change of the number of the lamp beads; linearly enhancing the LED lamp bead circuit board image according to the lamp bead gray scale interval to obtain an enhanced LED lamp bead circuit board image, extracting information of the enhanced LED lamp bead circuit board image, and analyzing the information to realize intelligent processing of LED lamp bead circuit board design data;
The method for obtaining the similarity degree of the lamp beads of each connected domain in the segmentation result graph comprises the following specific steps:
K-Means clustering is carried out on all gradient directions of the G connected domain in the segmentation result diagram to obtain clusters C 1,C2,C3,C4 of four gradient directions; acquiring the average value of adjacent gradient directions in each cluster, and respectively marking the included angles of the average values of the adjacent gradient directions in each cluster as Acquisition/>The average value of (2) is denoted as/>
The calculation expression of the similarity degree of the lamp beads of the G-th connected domain is as follows:
Wherein D G represents the degree of similarity of the lamp beads of the G-th connected domain; k represents the number of clusters; Representing the included angle of the average value of the first adjacent gradient directions in each cluster of the G connected domain; /(I) Representing the average value of included angles of the average values of all adjacent gradient directions in each cluster of the G connected domain;
the method for obtaining the constraint coefficients of the lamp beads of each connected domain comprises the following specific steps:
For the G-th connected domain in the segmentation result diagram, setting the barycenter coordinate of the connected domain G as (x G,yG), taking the center point of the segmentation result diagram as a point O, and taking the point O as the circle center to obtain the same-direction boundary of the G-th connected domain; wherein the communicating domain A, B is a homodromous adjacent communicating domain on the homodromous boundary of the communicating domain G, and the centroid coordinate of the communicating domain B is (x B,yB); the lamp bead constraint coefficient of the G-th connected domain
The method for obtaining the association degree of adjacent connected domains of each connected domain according to the first distance average value of each connected domain, the second distance average value of each connected domain and the lamp bead constraint coefficient of each connected domain comprises the following specific steps:
The calculation expression of the association degree of the adjacent connected domains of the G-th connected domain is as follows:
wherein C G represents the degree of association between adjacent connected domains of the G-th connected domain; Representing the average value of the distance between the G-th connected domain and the adjacent connected domain; /(I) Representing the average value of the distances from the G-th connected domain to all other connected domains; AC G represents the lamp bead constraint coefficient of the G-th connected domain; exp () represents an exponential function based on a natural constant;
the method for obtaining the reliability degree of the lamp beads of each connected domain of the segmentation result diagram under different thresholds according to the association degree of the adjacent connected domains of each connected domain and the similarity degree of the lamp beads comprises the following specific steps:
And for the G-th connected domain in the segmentation result diagram under different thresholds, obtaining the reliability degree of the G-th connected domain as the lamp bead according to the similarity degree of the lamp bead of the G-th connected domain and the association degree of the adjacent connected domains of the G-th connected domain, wherein the calculation expression formula is as follows:
RG＝DG×CG
Wherein R G represents the reliability of the G-th communication domain as a lamp bead; d G represents the degree of similarity of the lamp beads of the G-th connected domain; c G represents the association degree of adjacent connected domains of the G-th connected domain;
Obtaining the change of the number of the lamp beads according to the reliability degree of the lamp beads of all the connected domains of the segmentation result diagram under all the thresholds; the method for obtaining the light bead gray scale interval according to the change of the number of the light beads comprises the following specific steps:
presetting a threshold t1, for an LED lamp bead circuit board segmentation result diagram under any threshold, acquiring the reliability degree of all connected domains of the LED lamp bead circuit board segmentation result diagram under the threshold as lamp beads, and marking the connected domains corresponding to the reliability degree of the connected domains as the lamp beads being greater than or equal to the threshold t1 as the LED lamp beads, thereby acquiring the quantity of all the LED lamp beads in the LED lamp bead circuit board segmentation result diagram under the threshold; similarly, the number of the lamp beads in the LED lamp bead circuit board segmentation result diagram under each threshold value is obtained;
Taking a threshold value corresponding to the maximum value of the number of the LED lamp beads in the LED lamp bead circuit board segmentation result diagram as the initial gray level of a lamp bead gray level interval, and marking as I min; marking a threshold value corresponding to the number of the LED lamp beads in the LED lamp bead circuit board segmentation result diagram as the ending gray level of a lamp bead gray level interval, and marking the ending gray level as I max, wherein the lamp bead gray level interval is [ I min,Imax ];
the LED lamp bead circuit board image is linearly enhanced according to the lamp bead gray scale interval, the enhanced LED lamp bead circuit board image is obtained, and the method comprises the following specific steps:
Presetting a threshold t2, acquiring the gray value of each pixel point in the gray image of the LED lamp bead circuit board, marking any pixel point in the gray image of the LED lamp bead circuit board as a target pixel point, marking the threshold t2 as an enhancement coefficient of the target pixel point if the gray value of the target pixel point is not in a lamp bead gray interval, and taking the product of the gray value of the target pixel point and the enhancement coefficient of the target pixel point as a new gray value of the target pixel point; if the gray value of the target pixel point is in the bead gray interval, marking a connected domain in an LED bead circuit board segmentation result diagram corresponding to the target pixel point under the threshold value of I min as a target connected domain, marking the sum of the reliability of the target connected domain as a bead and the threshold value t2 as an enhancement coefficient of the pixel point, and taking the product of the gray value of the target pixel point and the enhancement coefficient of the target pixel point as a new gray value of the target pixel point; and similarly, linearly enhancing all pixel points in the gray level image of the LED lamp bead circuit board to obtain the enhanced image of the LED lamp bead circuit board.
2. The intelligent processing method for design data of LED lamp bead circuit board according to claim 1, wherein the method comprises the following steps of
The method for acquiring the adjacent connected domain of each connected domain comprises the following specific steps:
Presetting a parameter n, for the G-th connected domain in the segmentation result diagram, acquiring the mass centers of all connected domains in the segmentation result diagram, taking the distance between the mass center of the G-th connected domain and the mass centers of all other connected domains as the distance between the G-th connected domain and all connected domains in the segmentation result diagram, and taking the average value of the distances between the G-th connected domain and all connected domains as And defining n connected domains corresponding to n minimum values in the distances from the centroid of the G connected domain to the centroids of other connected domains as adjacent connected domains of the G connected domain.
3. The intelligent processing method for design data of LED lamp bead circuit board according to claim 1, wherein the method comprises the following steps of
The method comprises the steps of obtaining the average value of the distance from each connected domain to the adjacent connected domain according to the adjacent connected domain of each connected domain, wherein the average value comprises
The specific method comprises the following steps:
The calculation expression of the distance average value between the G-th connected domain and the adjacent connected domain is as follows:
In the method, in the process of the invention, Representing the average value of the distance between the G-th connected domain and the adjacent connected domain; l G,i represents a distance between the G-th communicating region and the i-th communicating region in the adjacent communicating region of the G-th communicating region; n is a preset parameter.
4. The intelligent processing system for the design data of the LED lamp bead circuit board is characterized by comprising the following modules:
The image acquisition module is used for acquiring a gray image of the LED lamp bead circuit board;
The lamp bead similarity obtaining module is used for obtaining the lamp bead similarity of each connected domain in the LED lamp bead circuit board segmentation result diagram under each threshold;
The lamp bead reliability obtaining module is used for obtaining the reliability of each connected domain as a lamp bead in the LED lamp bead circuit board segmentation result diagram under each threshold according to the association degree of the adjacent connected domains of each connected domain in the LED lamp bead circuit board segmentation result diagram under each threshold;
The image enhancement module is used for obtaining the change of the number of the lamp beads under different thresholds according to the reliability degree of the lamp beads in the communication domain, obtaining a lamp bead gray scale interval according to the change of the number of the lamp beads, obtaining an enhanced LED lamp bead circuit board image according to the lamp bead gray scale interval, and realizing intelligent processing of design data of the LED lamp bead circuit board;
The method for obtaining the similarity degree of the lamp beads of each connected domain in the segmentation result graph comprises the following specific steps:
K-Means clustering is carried out on all gradient directions of the G connected domain in the segmentation result diagram to obtain clusters C 1,C2,C3,C4 of four gradient directions; acquiring the average value of adjacent gradient directions in each cluster, and respectively marking the included angles of the average values of the adjacent gradient directions in each cluster as Acquisition/>The average value of (2) is denoted as/>
The calculation expression of the similarity degree of the lamp beads of the G-th connected domain is as follows:
Wherein D G represents the degree of similarity of the lamp beads of the G-th connected domain; k represents the number of clusters; Representing the included angle of the average value of the first adjacent gradient directions in each cluster of the G connected domain; /(I) Representing the average value of included angles of the average values of all adjacent gradient directions in each cluster of the G connected domain;
the method for obtaining the constraint coefficients of the lamp beads of each connected domain comprises the following specific steps:
For the G-th connected domain in the segmentation result diagram, setting the barycenter coordinate of the connected domain G as (x G,yG), taking the center point of the segmentation result diagram as a point O, and taking the point O as the circle center to obtain the same-direction boundary of the G-th connected domain; wherein the communicating domain A, B is a homodromous adjacent communicating domain on the homodromous boundary of the communicating domain G, and the centroid coordinate of the communicating domain B is (x B,yB); the lamp bead constraint coefficient of the G-th connected domain
The method for obtaining the association degree of adjacent connected domains of each connected domain according to the first distance average value of each connected domain, the second distance average value of each connected domain and the lamp bead constraint coefficient of each connected domain comprises the following specific steps:
The calculation expression of the association degree of the adjacent connected domains of the G-th connected domain is as follows:
wherein C G represents the degree of association between adjacent connected domains of the G-th connected domain; Representing the average value of the distance between the G-th connected domain and the adjacent connected domain; /(I) Representing the average value of the distances from the G-th connected domain to all other connected domains; AC G represents the lamp bead constraint coefficient of the G-th connected domain; exp () represents an exponential function based on a natural constant;
the method for obtaining the reliability degree of the lamp beads of each connected domain of the segmentation result diagram under different thresholds according to the association degree of the adjacent connected domains of each connected domain and the similarity degree of the lamp beads comprises the following specific steps:
And for the G-th connected domain in the segmentation result diagram under different thresholds, obtaining the reliability degree of the G-th connected domain as the lamp bead according to the similarity degree of the lamp bead of the G-th connected domain and the association degree of the adjacent connected domains of the G-th connected domain, wherein the calculation expression formula is as follows:
RG＝DG×CG
Wherein R G represents the reliability of the G-th communication domain as a lamp bead; d G represents the degree of similarity of the lamp beads of the G-th connected domain; c G represents the association degree of adjacent connected domains of the G-th connected domain;
Obtaining the change of the number of the lamp beads according to the reliability degree of the lamp beads of all the connected domains of the segmentation result diagram under all the thresholds; the method for obtaining the light bead gray scale interval according to the change of the number of the light beads comprises the following specific steps:
presetting a threshold t1, for an LED lamp bead circuit board segmentation result diagram under any threshold, acquiring the reliability degree of all connected domains of the LED lamp bead circuit board segmentation result diagram under the threshold as lamp beads, and marking the connected domains corresponding to the reliability degree of the connected domains as the lamp beads being greater than or equal to the threshold t1 as the LED lamp beads, thereby acquiring the quantity of all the LED lamp beads in the LED lamp bead circuit board segmentation result diagram under the threshold; similarly, the number of the lamp beads in the LED lamp bead circuit board segmentation result diagram under each threshold value is obtained;
Taking a threshold value corresponding to the maximum value of the number of the LED lamp beads in the LED lamp bead circuit board segmentation result diagram as the initial gray level of a lamp bead gray level interval, and marking as I min; marking a threshold value corresponding to the number of the LED lamp beads in the LED lamp bead circuit board segmentation result diagram as the ending gray level of a lamp bead gray level interval, and marking the ending gray level as I max, wherein the lamp bead gray level interval is [ I min,Imax ];
the LED lamp bead circuit board image is linearly enhanced according to the lamp bead gray scale interval, the enhanced LED lamp bead circuit board image is obtained, and the method comprises the following specific steps:
Presetting a threshold t2, acquiring the gray value of each pixel point in the gray image of the LED lamp bead circuit board, marking any pixel point in the gray image of the LED lamp bead circuit board as a target pixel point, marking the threshold t2 as an enhancement coefficient of the target pixel point if the gray value of the target pixel point is not in a lamp bead gray interval, and taking the product of the gray value of the target pixel point and the enhancement coefficient of the target pixel point as a new gray value of the target pixel point; if the gray value of the target pixel point is in the bead gray interval, marking a connected domain in an LED bead circuit board segmentation result diagram corresponding to the target pixel point under the threshold value of I min as a target connected domain, marking the sum of the reliability of the target connected domain as a bead and the threshold value t2 as an enhancement coefficient of the pixel point, and taking the product of the gray value of the target pixel point and the enhancement coefficient of the target pixel point as a new gray value of the target pixel point; and similarly, linearly enhancing all pixel points in the gray level image of the LED lamp bead circuit board to obtain the enhanced image of the LED lamp bead circuit board.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310999665.7A CN117115197B (en) | 2023-08-09 | 2023-08-09 | Intelligent processing method and system for design data of LED lamp bead circuit board |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310999665.7A CN117115197B (en) | 2023-08-09 | 2023-08-09 | Intelligent processing method and system for design data of LED lamp bead circuit board |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117115197A CN117115197A (en) | 2023-11-24 |
| CN117115197B true CN117115197B (en) | 2024-05-17 |
Family
ID=88795733
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310999665.7A Active CN117115197B (en) | 2023-08-09 | 2023-08-09 | Intelligent processing method and system for design data of LED lamp bead circuit board |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117115197B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117934798A (en) * | 2024-03-22 | 2024-04-26 | 济宁职业技术学院 | Child behavior online identification system based on computer vision |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6834124B1 (en) * | 2000-10-16 | 2004-12-21 | Xerox Corporation | Adaptive image enhancement filter |
| CN101995325A (en) * | 2009-08-25 | 2011-03-30 | 比亚迪股份有限公司 | Appearance detection method and system of image sensor |
| KR20170123392A (en) * | 2016-04-28 | 2017-11-08 | 주식회사 케이엘디 | An apparatus of control for LED electric lighting board for Flicker Reduction using Grey Image Scale and that of method for control |
| CN110930407A (en) * | 2020-02-07 | 2020-03-27 | 西南交通大学 | Suspension gap visual detection method based on image processing |
| CN111028202A (en) * | 2019-11-14 | 2020-04-17 | 苏州斯玛维科技有限公司 | X-ray bubble defect image processing method, device, storage medium and system for LED chip |
| CN111257348A (en) * | 2020-03-27 | 2020-06-09 | 河海大学常州校区 | LED light guide plate defect detection method based on machine vision |
| CN114235837A (en) * | 2021-12-20 | 2022-03-25 | 重庆大学 | LED packaging surface defect detection method, device, medium and equipment based on machine vision |
| CN115440159A (en) * | 2022-08-22 | 2022-12-06 | 杭州海康威视数字技术股份有限公司 | Image correction method, and correction method and device for LED display screen image |
| CN115526883A (en) * | 2022-10-19 | 2022-12-27 | 深圳达四海科技有限公司 | LED lamp bead detection method and device, computer equipment and storage medium |
| WO2023279862A1 (en) * | 2021-07-07 | 2023-01-12 | 荣耀终端有限公司 | Image processing method and apparatus, and electronic device |
| CN115601367A (en) * | 2022-12-15 | 2023-01-13 | 苏州迈创信息技术有限公司（Cn） | LED lamp wick defect detection method |
-
2023
- 2023-08-09 CN CN202310999665.7A patent/CN117115197B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6834124B1 (en) * | 2000-10-16 | 2004-12-21 | Xerox Corporation | Adaptive image enhancement filter |
| CN101995325A (en) * | 2009-08-25 | 2011-03-30 | 比亚迪股份有限公司 | Appearance detection method and system of image sensor |
| KR20170123392A (en) * | 2016-04-28 | 2017-11-08 | 주식회사 케이엘디 | An apparatus of control for LED electric lighting board for Flicker Reduction using Grey Image Scale and that of method for control |
| CN111028202A (en) * | 2019-11-14 | 2020-04-17 | 苏州斯玛维科技有限公司 | X-ray bubble defect image processing method, device, storage medium and system for LED chip |
| CN110930407A (en) * | 2020-02-07 | 2020-03-27 | 西南交通大学 | Suspension gap visual detection method based on image processing |
| CN111257348A (en) * | 2020-03-27 | 2020-06-09 | 河海大学常州校区 | LED light guide plate defect detection method based on machine vision |
| WO2023279862A1 (en) * | 2021-07-07 | 2023-01-12 | 荣耀终端有限公司 | Image processing method and apparatus, and electronic device |
| CN114235837A (en) * | 2021-12-20 | 2022-03-25 | 重庆大学 | LED packaging surface defect detection method, device, medium and equipment based on machine vision |
| CN115440159A (en) * | 2022-08-22 | 2022-12-06 | 杭州海康威视数字技术股份有限公司 | Image correction method, and correction method and device for LED display screen image |
| CN115526883A (en) * | 2022-10-19 | 2022-12-27 | 深圳达四海科技有限公司 | LED lamp bead detection method and device, computer equipment and storage medium |
| CN115601367A (en) * | 2022-12-15 | 2023-01-13 | 苏州迈创信息技术有限公司（Cn） | LED lamp wick defect detection method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117115197A (en) | 2023-11-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110378324B (en) | Quality dimension-based face recognition algorithm evaluation method | |
| CN109271991B (en) | License plate detection method based on deep learning | |
| CN104778457B (en) | Video face identification method based on multi-instance learning | |
| CN117115197B (en) | Intelligent processing method and system for design data of LED lamp bead circuit board | |
| CN103577838A (en) | Face recognition method and device | |
| CN109993221B (en) | Image classification method and device | |
| CN107729809A (en) | A kind of method, apparatus and its readable storage medium storing program for executing of adaptive generation video frequency abstract | |
| CN114492619B (en) | Point cloud data set construction method and device based on statistics and concave-convex performance | |
| CN111695373B (en) | Zebra stripes positioning method, system, medium and equipment | |
| Kosarevych et al. | Image segmentation based on the evaluation of the tendency of image elements to form clusters with the help of point field characteristics | |
| CN116403094A (en) | Embedded image recognition method and system | |
| CN110188864B (en) | Small sample learning method based on distribution representation and distribution measurement | |
| CN114359632A (en) | Point cloud target classification method based on improved PointNet + + neural network | |
| CN108122000B (en) | Vehicle logo recognition method based on feature learning | |
| CN111199228B (en) | License plate positioning method and device | |
| CN113344047A (en) | Platen state identification method based on improved K-means algorithm | |
| Al-Jubouri et al. | Adaptive clustering based segmentation for image classification | |
| Akther et al. | Detection of Vehicle's Number Plate at Nighttime using Iterative Threshold Segmentation (ITS) Algorithm | |
| CN111428064A (en) | Small-area fingerprint image fast indexing method, device, equipment and storage medium | |
| CN116415210A (en) | Image infringement detection method, device and storage medium | |
| Promsuk et al. | Numerical Reader System for Digital Measurement Instruments Embedded Industrial Internet of Things. | |
| CN112818779B (en) | Human behavior recognition method based on feature optimization and multiple feature fusion | |
| CN115527024A (en) | Detection positioning method and system based on image information | |
| Chi et al. | Saliency detection via integrating deep learning architecture and low-level features | |
| CN113963295A (en) | Method, device, equipment and storage medium for recognizing landmark in video clip |
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 |