CN105509657B - A kind of high-precision measuring method of IC card chip scratch area and gray scale parameter - Google Patents
A kind of high-precision measuring method of IC card chip scratch area and gray scale parameter Download PDFInfo
- Publication number
- CN105509657B CN105509657B CN201510845470.2A CN201510845470A CN105509657B CN 105509657 B CN105509657 B CN 105509657B CN 201510845470 A CN201510845470 A CN 201510845470A CN 105509657 B CN105509657 B CN 105509657B
- Authority
- CN
- China
- Prior art keywords
- difference
- image
- detection
- area
- color
- 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
- 238000000034 method Methods 0.000 title claims abstract description 16
- 238000001514 detection method Methods 0.000 claims abstract description 66
- 238000012545 processing Methods 0.000 claims abstract description 16
- 238000003780 insertion Methods 0.000 claims abstract description 4
- 230000037431 insertion Effects 0.000 claims abstract description 4
- 238000005192 partition Methods 0.000 claims description 46
- 230000005611 electricity Effects 0.000 claims description 20
- 230000007547 defect Effects 0.000 claims description 11
- 238000000605 extraction Methods 0.000 claims description 11
- 238000012634 optical imaging Methods 0.000 claims description 10
- XOFYZVNMUHMLCC-ZPOLXVRWSA-N prednisone Chemical compound O=C1C=C[C@]2(C)[C@H]3C(=O)C[C@](C)([C@@](CC4)(O)C(=O)CO)[C@@H]4[C@@H]3CCC2=C1 XOFYZVNMUHMLCC-ZPOLXVRWSA-N 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000000691 measurement method Methods 0.000 claims description 4
- 238000004140 cleaning Methods 0.000 claims description 3
- 239000003086 colorant Substances 0.000 claims description 2
- 238000005286 illumination Methods 0.000 claims description 2
- 230000007704 transition Effects 0.000 claims description 2
- 238000004458 analytical method Methods 0.000 abstract description 3
- 230000000694 effects Effects 0.000 abstract description 3
- 230000009286 beneficial effect Effects 0.000 abstract 1
- 238000002474 experimental method Methods 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 2
- 238000000638 solvent extraction Methods 0.000 description 2
- 238000005299 abrasion Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/28—Measuring arrangements characterised by the use of optical techniques for measuring areas
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J3/00—Spectrometry; Spectrophotometry; Monochromators; Measuring colours
- G01J3/46—Measurement of colour; Colour measuring devices, e.g. colorimeters
- G01J3/462—Computing operations in or between colour spaces; Colour management systems
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J3/00—Spectrometry; Spectrophotometry; Monochromators; Measuring colours
- G01J3/46—Measurement of colour; Colour measuring devices, e.g. colorimeters
- G01J3/50—Measurement of colour; Colour measuring devices, e.g. colorimeters using electric radiation detectors
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N19/00—Investigating materials by mechanical methods
- G01N19/04—Measuring adhesive force between materials, e.g. of sealing tape, of coating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Chemical & Material Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The present invention proposes the high-precision measuring method of a kind of IC card chip scratch area and gray scale parameter, including 7 steps；Before scratch detection, clean no marking power purchase the core of the card piece is gathered by CCD and is used as standard base figure, clean no marking power purchase card will in addition be taken, insertion card slot carries out plug experiment, power purchase card to be measured is scanned by CCD, compared with base figure, it is cut information to analyze difference, cut information is analyzed with certain algorithm, achievees the purpose that cut quantitatively detects.Beneficial technique effect：By the problems such as present invention can overcome eye-observation, the standard evaluated is inconsistent, human error is big, on the basis of Digital Image Processing, using BLOB algorithms, scratch area and gray scale parameter, analysis power purchase card scratch levels accurately and fast, quantitative are calculated.
Description
Technical Field
The invention belongs to the technical field of image detection, and particularly relates to a high-precision measurement method for scratch area and gray scale parameters of an IC card chip.
Background
Along with the extensive popularization of smart electric meters, the important role is put back in the local fee control mode to the electricity price return, each local fee control electric meter is provided with an electricity purchasing card held by residents and used as a payment and recharging medium, a clamping groove is arranged in the electric meter, and the electricity purchasing card is inserted into the clamping groove to perform data interaction. Because the draw-in groove spring manufacture factory is more, and factors such as material, spring pressure are all inequality, consequently probably cause the draw-in groove spring to the inserting card chip that purchases the mar wearing and tearing, and the mar wearing and tearing of deep degree will lead to damaging to purchasing the card chip of electricity, and the user will be unable to purchase the electricity. According to the mechanical and structural requirements of the card seat specified by the national power grid company intelligent electric energy meter enterprise standard promulgated standard specification, the electricity purchasing card with a clean card surface is continuously inserted and pulled in the card slot for 20 times, and the contact of the electricity purchasing card has no scratch. However, in the past, chip abrasion detection of the electricity purchasing card of the intelligent electric meter is judged by human vision, and the judgment result has no scientific data support. How to quickly and accurately evaluate the scratch degree of the chip of the power card so as to judge the performance of the card slot becomes an important problem.
Disclosure of Invention
The invention provides a high-precision measuring method for the scratch area and the gray scale parameter of an IC card chip, which is a method for quantitatively analyzing the scratch degree of a power purchasing card by calculating the scratch area and the gray scale parameter by using a BLOB algorithm on the basis of digital image processing. The invention specifically comprises the following steps:
a high-precision measurement method for scratch area and gray scale parameters of an IC card chip comprises the following steps:
step 1: two electricity purchasing card chips are prepared, one of the two electricity purchasing card chips is used as a standard sample card, and the other one is used as a chip for detection. And cleaning the standard sample card and the detection chip.
Step 2: and (3) putting the chip for detection into the smart electric meter card slot for continuous plugging and unplugging for N times, wherein the value range of N is 10-10000. And respectively carrying out optical imaging on the standard sample card and the detection chip which is inserted and pulled for N times by using the CCD.
And step 3: and (4) capturing the image of the optical imaging result of the standard sample card by the CCD, and storing the image as a standard base map. And (4) capturing the optical imaging result of the detection chip which is inserted and pulled for N times by the CCD, and storing the image as a detection image.
And 4, step 4: and respectively carrying out digital processing on the standard base map and the detection image.
And 5: and respectively carrying out image feature extraction on the standard base map and the image for detection which are subjected to the digital processing.
Step 6: comparing the detection image extracted by the image features with the standard base map extracted by the image features, searching and judging the difference between the detection image and the standard base map, and acquiring the difference types of the detection chip subjected to N times of insertion and extraction: line differences, surface differences.
And 7: and outputting the result.
Advantageous technical effects
The scratch difference of the electric power purchasing card proposed by the document refers to the scratch difference between the surface of the electric power purchasing card to be purchased and the surface of the clean and scratch-free electric power purchasing card, namely, the scratch is considered to exist when the chip has a mismatch area with the chip and the scratch-free electric power purchasing card. Therefore, the scratch of the power purchase card can be understood even if the surface of the chip of the power purchase card to be detected has the shape difference on the image with the surface of the chip of the standard clean power purchase card.
According to the characteristics of the slot spring, the characteristics of various scratches are integrated, and the differences are classified into 2 types, as shown in table 1.
The detection process of the invention is as follows: before the mar detects, gather through CCD and totally have the mar and purchase the electricity card chip as standard base map, will get clean no mar in addition and purchase the electricity card, insert the draw-in groove and carry out the plug test, await measuring through CCD scanning and purchase the electricity card, compare with the base map, it is mar information promptly to analyze out the difference, carries out the analysis to mar information with certain algorithm, reaches mar quantitative determination's purpose.
The invention can overcome the problems of inconsistent standards of human eye observation and evaluation, large manual error and the like, calculates the scratch area and the gray scale parameter by using the BLOB algorithm on the basis of digital image processing, and accurately, quickly and quantitatively analyzes the scratch degree of the electricity purchasing card.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Fig. 2 is a schematic diagram of a picture divided into square regions with a side of 3 pixels.
Fig. 3 is a flowchart for calculating the scratch area and the gray scale parameter using the BLOB algorithm.
Fig. 4 is a schematic diagram of a difference image obtained by the present invention.
Fig. 5 is a schematic diagram of the search for connected color difference points.
Fig. 6 is a schematic illustration of the expansion of a defect.
Detailed Description
The structural features of the present invention will now be described in detail with reference to the accompanying drawings.
Referring to fig. 1, a method for measuring scratch area and gray scale parameter of an IC card chip with high precision is performed according to the following steps:
step 1: two electricity purchasing card chips are prepared, one of the two electricity purchasing card chips is used as a standard sample card, and the other one is used as a chip for detection. And cleaning the standard sample card and the detection chip.
Step 2: and (3) putting the chip for detection into the smart electric meter clamping groove for continuous plugging and unplugging for N times, wherein the value range of N is between 10 and 10000. And respectively carrying out optical imaging on the standard sample card and the detection chip which is inserted and pulled for N times by using the CCD.
And step 3: and (4) capturing the image of the optical imaging result of the standard sample card by the CCD, and storing the image as a standard base map. And (4) capturing the optical imaging result of the detection chip which is inserted and pulled for N times by the CCD, and storing the optical imaging result as a detection image.
And 4, step 4: and respectively carrying out digital processing on the standard base image and the detection image.
And 5: and respectively carrying out image feature extraction on the standard base map and the image for detection which are subjected to the digital processing.
And 6: comparing the detection image extracted by the image features with the standard base map extracted by the image features, searching and judging the difference between the detection image and the standard base map, and acquiring the difference types of the detection chip subjected to N times of insertion and extraction: line differences, area differences.
And 7: and outputting the result.
Furthermore, in step 6, the image for detection extracted by the image features is compared with the standard base map extracted by the image features, the difference between the image for detection and the standard base map is searched and judged, the pixel difference is divided and compared, and the Blob algorithm is used for carrying out parameter analysis on the difference areas, so that the line difference and the area difference are distinguished.
Further, the digital processing of the detection image and the standard base map is performed by converting the image color of the detection image subjected to the image feature extraction and the image color of the standard base map subjected to the image feature extraction from RGB to Lab color space, respectively, using XYZ space as a transition. The specific conversion formula is as follows:
wherein L is * 、a * 、b * Are the values of the three channels of the final LAB color space. X, Y, Z is a value calculated after RGB has been converted into XYZ. X z 、Y z 、Z z The value is 1.
The digital processing also has the effect of reducing the loss of color.
RGB cannot be directly converted into LAB, and needs to be converted into XYZ first and then into LAB, that is: RGB-XYZ-LAB thus the conversion formula is divided into two parts:
first, RGB is converted into XYZ.
Assuming that r, g and b are three channels of pixels and the value range is [0, 255], the conversion formula is as follows:
the gamma function is used to make non-linear tone editing to the image, and the aim is to raise the contrast of the image. Subsequently, XYZ was again converted to LAB.
L * ＝116f(Y/Y n )-16
a * ＝500[f(X/X n )-f(Y/Y n )]
b * ＝200[f(Y/Y n )-f(Z/Z n )]
Further, the resolution of the CCD was 500ppi, i.e., the minimum difference detectable by the CCD was 0.04mm 2 . And one pixel has a size of 0.0026mm 2 That is, the minimum scratch area can be detected to occupy 9 pixels, and 3 × 3 pixels, each 9 pixels, are regarded as a partition, as shown in fig. 2. Respectively adding standard baseThe upper left corner of the image for detection and the standard base image are taken as the origin of coordinates, the x axis and the y axis are taken, a coordinate system is established, the pictures of the standard base image and the image for detection are respectively divided according to a square area with the side length of 3 pixels, the average value of RGB of 9 pixels in each partition is taken as the color information of the partition during calculation, and then the partitions corresponding to the standard base image and the image for detection are compared.
Further, the image feature extraction of the detection image, that is, the search for the image difference between the detection image and the standard base map is determined by comparing the color differences of all corresponding positions of the detection image and the standard base map.
Let S (L, a, b), T (L, a, b) be the Lab value of the divisional pixel in the standard image and the Lab value of the divisional pixel in the detection image, respectively, and the color difference threshold Δ E be set as follows:
if Δ E<(SL-TL) 2 +(Sa-Ta) 2 +(Sb-Tb) 2 The partition is considered to be a color difference point.
Where S (L, a, b) is the Lab value of the partition pixel in the standard image, and T (L, a, b) is the Lab value of the partition pixel in the detection image.
The Lab color model is composed of three elements of illumination (L) and a and b related to colors. L represents illuminance (luminance), which corresponds to brightness, a represents a range from red to green, and b represents a range from blue to yellow.
Referring to fig. 3, further, a Blob algorithm is used to analyze and process the points on the detection image that have differences from the standard base map, so as to obtain difference points, and find the positions, sizes, shapes, and areas of the difference points. The method comprises the following specific steps:
1) And storing the label and the difference area of each difference, namely the pixel number of the color difference point by using a two-dimensional array.
2) Color difference marked partitions: and judging the color difference of the partition from left to right and from top to bottom, and marking the partition as 1 if the color difference value exceeds a color difference threshold delta E. Otherwise, it is marked as 0.
3) And (3) difference marking: the image is rescanned and if the partition is marked as 1, the color difference point is obtained. If the difference sign is not marked, the following steps are executed:
(1) Let the label of the difference be f, the f variable is incremented starting with 1.
(2) The area of the difference is increased by the corresponding number of pixels, i.e., 4 pixels if the partition is 2.
(3) The positions of the partitions, i.e., the row number and the column number in the image in units of pixels, are noted.
4) And (3) difference merging: if the partition is marked with 1 and has been marked with a difference number, the number is not increased with the marked difference number as a standard. And increasing the corresponding pixel number of the area of the difference, and recording the position of the partition to realize the combination of the color difference points of the adjacent areas.
5) Differential expansion: merging the different disconnected areas, and respectively detecting whether the marks of the right and lower 8 subareas of the subarea are 1:
if yes, the difference labels of the partitions are changed into the partition difference labels, the areas of the differences are increased by corresponding pixel numbers, and the positions of the partitions are recorded.
If not, no processing is performed until all the partitions are detected. The detection of the difference can be successfully completed by detecting the full picture of the image through the steps.
6) Determining the difference position: finding out the minimum and maximum column number and row number of all the partitions in the same difference to determine the circumscribed rectangle of the difference and the central position of the defect: firstly, finding out the connected color difference points, and endowing the connected color difference points with corresponding difference labels. The differences within 8 pixels apart are then combined into one difference.
In summary, the Blob algorithm is used to process the detection image to obtain the label, position, area of the difference point and the area of the circumscribed rectangle, and the difference image information is converted into shape information for use in determining the difference type.
The resolution of the CCD used is 500ppi, and in the design, the minimum defect that we generally require to detect is 0.04mm 2 And the size of one pixel is 0.0026mm 2 I.e. detectable minimum defectSince the trap area is approximately 9 pixels, each 9 pixels can be regarded as a whole, that is, a partition. The whole picture is thus subdivided into a number of square regions of 3 pixels on a side. The specific partitioning mode is shown in FIG. 2;
in fig. 2, the upper left corner of the image is taken as the origin of coordinates and the x and y axes are taken, respectively. A coordinate system. The image is divided into a plurality of areas according to the partition size specified by the program, namely 9 pixels, and partition coordinates are defined according to the coordinate system respectively. During calculation, the RGB average value of 9 pixels in each partition is used for replacing the color information of the partition, and then the corresponding partitions of the image to be measured and the standard image are compared. Through partitioning, the calculation amount is greatly reduced, and the execution speed of the program is accelerated; moreover, due to the relevance among pixels of the continuous tone image and the redundancy of data, the method has no great influence on the detection result.
Neglecting the complex situation in the algorithm, the Blob algorithm is simply understood, namely firstly, the connected color difference points are found out and are endowed with corresponding defect labels; defects within 8 pixels of each other are then merged into one defect, see fig. 5 and 6.
Referring to fig. 3, further, the method for determining the type of the difference is as follows:
first, by processing the detection image by Blob algorithm, the image information of the difference is converted into shape information: and obtaining the difference points, and the labels, positions and areas of the difference points and the area of the circumscribed rectangle.
Then, setting the difference area as S and the corresponding circumscribed rectangle size as W,
further, when the resolution of the CCD employed is 500ppi, the minimum defect to be detected is 0.04mm 2 And the size of one pixel is 0.0026mm 2 The minimum detectable defect area comprises 9 pixels, so that the area of each minimum partition is 0.0026mm 2 *9＝0.0234mm 2 . The difference area is equal to the difference quantity 0.0234mm 2 。
If S/W is more than or equal to 0.3, the difference is classified as a surface, otherwise, the difference is classified as a line.
Then, manually presetting the length of the short side of the difference circumscribed rectangle as c, wherein the unit is mm, and setting the ratio of the long side to the short side of the difference circumscribed rectangle as d.
If the difference circumscribes a rectangle with a short side less than or equal to c and a ratio of long to short sides is large by d, the difference is considered a line and is approximately parallel to the x-axis or y-axis. Conversely, the difference is a line that is not parallel to either the x-axis or the y-axis.
Referring to fig. 4, in order to place the chip for detection in the smart meter card slot, chip images and difference images are obtained through 10 times of plugging and unplugging, 100 times of plugging and unplugging, and 1000 times of plugging and unplugging. The method of the invention can overcome the problems of large randomness, inconsistent standards and large manual errors of human eye observation and evaluation. The scratch degree of the electricity purchasing card can be quantitatively analyzed accurately and quickly by adopting a unified standard.
Claims (1)
1. A high-precision measurement method for scratch area and gray scale parameters of an IC card chip is characterized by comprising the following steps: the method comprises the following steps:
step 1: preparing two electricity purchasing card chips, taking one of the two electricity purchasing card chips as a standard sample card, and taking the other one of the two electricity purchasing card chips as a chip for detection; cleaning the standard sample card and the detection chip;
and 2, step: placing the detection chip into a smart electric meter card slot for continuous plugging and unplugging for N times, wherein the value range of N is 10-10000; respectively carrying out optical imaging on the standard sample card and the detection chip which is inserted and pulled for N times through the CCD;
and step 3: the CCD captures the optical imaging result of the standard sample card and stores the result as a standard base map; the CCD captures the optical imaging result of the detection chip which is inserted and pulled for N times and stores the image as a detection image;
the resolution of the CCD is 500ppi, and the minimum difference detectable by the CCD is 0.04mm 2 (ii) a And one pixel has a size of 0.0026mm 2 Then, the minimum scratch area can be detected to occupy 9 pixels, and 3 × 3 pixels, each 9 pixels, are regarded as a partition; respectively using the upper left corner of the standard base image and the image for detection as the origin of coordinates, making x-axis and y-axis to establish coordinate system, and calculating the coordinate systemDividing the pictures of the standard base image and the image for detection respectively according to a square area with the side length of 3 pixels, using the average value of RGB of 9 pixels in each partition as the color information of the partition during calculation, and then comparing the corresponding partitions of the standard base image and the image for detection;
and 4, step 4: respectively carrying out digital processing on the standard base map and the image for detection;
converting the image color of the detection image subjected to the image feature extraction and the image color of the standard base map subjected to the image feature extraction from RGB to Lab color space respectively by adopting an XYZ space as a transition; the specific conversion formula is as follows:
wherein L is * 、a * 、b * Are the values of the three channels of the final LAB color space; x, Y, Z is a value calculated by converting RGB to XYZ; x 0 、Y 0 、Z 0 The value is 1;
and 5: respectively carrying out image feature extraction on the standard base map and the image for detection which are subjected to digital processing;
searching image differences between the image for detection and the standard base map, and judging by comparing color differences of all corresponding positions of the image for detection and the standard base map;
let S (L, a, b), T (L, a, b) be the Lab value of the divisional pixel in the standard image and the Lab value of the divisional pixel in the detection image, respectively, and the color difference threshold Δ E be set as follows:
if Δ E<(SL-TL) 2 +(Sa-Ta) 2 +(Sb-Tb) 2 The partition is considered to be a color difference point,
wherein S (L, a, b) is the Lab value of the partition pixel in the standard image, and T (L, a, b) is the Lab value of the partition pixel in the image for detection;
the Lab color model consists of three elements, namely illumination L and a and b related to colors;
l represents illuminance (luminance), a represents a range from red to green, and b represents a range from blue to yellow;
step 6: comparing the detection image extracted by the image characteristics with the standard base map extracted by the image characteristics, searching and judging the difference between the detection image extracted by the image characteristics and the standard base map, and acquiring the difference types of the detection chip subjected to N times of insertion and extraction: line difference and surface difference;
the specific operation steps are as follows:
1) Storing the label and the difference area of each difference by using a two-dimensional array, and representing the number of pixels of the color difference point;
2) Color difference marked partitions: judging the color difference of the subareas from left to right and from top to bottom, and marking the subareas as 1 if the color difference value exceeds a color difference threshold delta E; otherwise, it is marked as 0;
3) And (3) difference marking: re-scanning the image, and if the partition mark is 1, determining the partition mark as a color difference point; if the difference sign is not marked, the following steps are executed:
(1) Marking the mark number of the difference as f, increasing the variable of f from 1, and increasing the increment to 4 pixels;
(2) The area of the difference is increased by the corresponding pixel number;
(3) Recording the positions of the partitions, wherein the positions refer to a row number and a column number in the image with the pixel as a unit;
4) And (3) difference merging: if the partition is marked as 1 and is marked with the difference number, the marked difference number is taken as the standard and is not increased any more; increasing the corresponding pixel number of the area of the difference, and recording the position of the partition to realize the combination of the color difference points of the adjacent areas;
5) Differential expansion: merging the different disconnected areas, and respectively detecting whether the marks of the right and lower 8 subareas of the subarea are 1;
if yes, changing the difference labels of the partitions into the partition difference labels, increasing the areas of the differences by corresponding pixel numbers, and recording the positions of the partitions;
if not, not performing any processing until all the partitions are detected; the detection of the difference can be successfully completed by detecting the full picture of the image through the steps;
6) Determining the difference position: finding out the minimum and maximum column number and row number of all the partitions in the same difference to determine the circumscribed rectangle of the difference and the central position of the defect: firstly, finding out communicated color difference points, and giving corresponding difference labels; then combining the differences within 8 pixels into one difference;
in summary, the Blob algorithm is used for processing the detection image to obtain the label, position and area of the difference point and the area of the circumscribed rectangle, and the difference image information is converted into shape information for use in judging the difference type;
the method for judging the difference type comprises the following steps:
first, by processing the detection image by Blob algorithm, the image information of the difference is converted into shape information: obtaining difference points, and the labels, positions and areas of the difference points and the area of the circumscribed rectangle;
then, setting the difference area as S and the size of the corresponding external rectangle as W;
when the resolution of the CCD used is 500ppi, the minimum defect to be detected is 0.04mm 2 And the size of one pixel is 0.0026mm 2 The minimum detectable defect area then contains 9 pixels, so the area of each minimum partition is 0.0026mm 2 *9＝0.0234mm 2 ；
The difference area is equal to the difference quantity 0.0234mm 2 ；
If S/W is more than or equal to 0.3, classifying the difference as a surface, and if not, classifying the difference as a line;
then, manually presetting the length of the short side of the difference circumscribed rectangle as c, wherein the unit is mm, and setting the ratio of the long side to the short side of the difference circumscribed rectangle as d;
if the short side of the difference bounding rectangle is less than or equal to c and the ratio of the long side to the short side is greater than d, the difference is considered to be a line and is approximately parallel to the x-axis or the y-axis; otherwise, the line difference is not parallel to the x-axis or the y-axis;
and 7: and outputting the result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510845470.2A CN105509657B (en) | 2015-11-26 | 2015-11-26 | A kind of high-precision measuring method of IC card chip scratch area and gray scale parameter |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510845470.2A CN105509657B (en) | 2015-11-26 | 2015-11-26 | A kind of high-precision measuring method of IC card chip scratch area and gray scale parameter |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105509657A CN105509657A (en) | 2016-04-20 |
| CN105509657B true CN105509657B (en) | 2018-05-18 |
Family
ID=55717816
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510845470.2A Active CN105509657B (en) | 2015-11-26 | 2015-11-26 | A kind of high-precision measuring method of IC card chip scratch area and gray scale parameter |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105509657B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109556721B (en) * | 2018-10-29 | 2020-12-08 | 北京市计量检测科学研究院 | Method for detecting color chips |
| CN110208284B (en) * | 2019-05-27 | 2021-09-17 | 武汉中导光电设备有限公司 | Method and system for multi-channel defect merging analysis |
| CN110487801B (en) * | 2019-07-30 | 2022-07-19 | 厦门三安光电有限公司 | Method, device and equipment for identifying high-temperature baking result of graphite plate and storage medium |
| CN110807969A (en) * | 2019-11-28 | 2020-02-18 | 深圳市华兴鼎盛科技有限公司 | Machine vision recognition teaching system and teaching method |
| CN113362288B (en) * | 2021-05-24 | 2024-03-08 | 深圳明锐理想科技股份有限公司 | Golden finger scratch detection method and device and electronic equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201397305Y (en) * | 2009-05-05 | 2010-02-03 | 北京凌云光视数字图像技术有限公司 | Hard card surface quality detection device |
| CN102053093A (en) * | 2010-11-08 | 2011-05-11 | 北京大学深圳研究生院 | Method for detecting surface defects of chip cut from wafer surface |
| CN103926256A (en) * | 2014-03-20 | 2014-07-16 | 上海华力微电子有限公司 | CMP scratch automatic detection system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101180549A (en) * | 2005-04-11 | 2008-05-14 | 株式会社爱德万测试 | Processing device of electronic component |
-
2015
- 2015-11-26 CN CN201510845470.2A patent/CN105509657B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201397305Y (en) * | 2009-05-05 | 2010-02-03 | 北京凌云光视数字图像技术有限公司 | Hard card surface quality detection device |
| CN102053093A (en) * | 2010-11-08 | 2011-05-11 | 北京大学深圳研究生院 | Method for detecting surface defects of chip cut from wafer surface |
| CN103926256A (en) * | 2014-03-20 | 2014-07-16 | 上海华力微电子有限公司 | CMP scratch automatic detection system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105509657A (en) | 2016-04-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105509657B (en) | A kind of high-precision measuring method of IC card chip scratch area and gray scale parameter | |
| US11915407B2 (en) | Automated system and method for clarity measurements and clarity grading | |
| CN109829914B (en) | Method and device for detecting product defects | |
| RU2567863C2 (en) | Method and system for image colour definition | |
| TWI291561B (en) | PC board inspecting apparatus, inspection logic setting method, and inspection logic setting apparatus | |
| US20190086340A1 (en) | Smart defect calibration system and the method thereof | |
| TW555969B (en) | Method for non-destructive inspection, apparatus thereof and digital camera system | |
| CN109685760B (en) | MATLAB-based SLM powder bed powder laying image convex hull depression defect detection method | |
| CN109472271B (en) | Printed circuit board image contour extraction method and device | |
| CN103852034B (en) | A kind of method for measuring perendicular | |
| CN106157286A (en) | Image processing method and screen light leak test method | |
| CN111624203B (en) | Relay contact point alignment non-contact measurement method based on machine vision | |
| CN109819245B (en) | On-line measuring method and device for chroma and brightness data based on AOI platform | |
| CN108564631A (en) | Car light light guide acetes chinensis method, apparatus and computer readable storage medium | |
| JP5466099B2 (en) | Appearance inspection device | |
| CN116091506B (en) | Machine vision defect quality inspection method based on YOLOV5 | |
| CN111598851B (en) | Solar cell broken piece detection method based on morphological image processing | |
| CN112326681B (en) | Method for correcting and detecting lens cleanliness by utilizing defocusing difference flat field | |
| JP7380332B2 (en) | Image processing device, control method and program for the image processing device | |
| CN107389677B (en) | Method and device for detecting quality of flannelette fluff | |
| CN112419431A (en) | Method and system for detecting product color | |
| Appolonia et al. | Computer-aided monitoring of buildings of historical importance based on color | |
| CN111428796A (en) | General article detection method and system based on deep learning | |
| US20130163871A1 (en) | System and method for segmenting image data to identify a character-of-interest | |
| CN115908242B (en) | Chip gold thread whole line detection method and system for multichannel image fusion |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |