CN109584237A - Chip detection method and device, computer equipment and storage medium - Google Patents
Chip detection method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109584237A CN109584237A CN201811486234.6A CN201811486234A CN109584237A CN 109584237 A CN109584237 A CN 109584237A CN 201811486234 A CN201811486234 A CN 201811486234A CN 109584237 A CN109584237 A CN 109584237A
- Authority
- CN
- China
- Prior art keywords
- chip
- image
- operator
- square
- chip image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 70
- 238000000034 method Methods 0.000 claims abstract description 37
- 238000012797 qualification Methods 0.000 claims abstract description 14
- 238000004590 computer program Methods 0.000 claims description 16
- 239000000284 extract Substances 0.000 claims description 12
- 239000000203 mixture Substances 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 11
- 230000006872 improvement Effects 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 235000013399 edible fruits Nutrition 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 230000036039 immunity Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000001360 synchronised effect Effects 0.000 description 3
- 238000013519 translation Methods 0.000 description 3
- 238000005452 bending Methods 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 244000287680 Garcinia dulcis Species 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 238000004925 denaturation Methods 0.000 description 1
- 230000036425 denaturation Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
-
- 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
- G06T2207/30148—Semiconductor; IC; Wafer
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
Abstract
The application relates to a chip detection method, a chip detection device, computer equipment and a storage medium. The method comprises the following steps: acquiring a chip image of a chip to be detected; generating a corresponding image moment according to the chip image; generating an identification operator corresponding to the chip image according to the image moment; if the recognition operator of the chip image is matched with a preset template recognition operator, generating a qualified detection result; and if the recognition operator of the chip image is not matched with the preset template recognition operator, generating a detection unqualified result. By the method and the device, the accuracy of chip qualification detection can be improved.
Description
Technical field
This application involves mounting technology fields, more particularly to a kind of chip detecting method, device, computer equipment and deposit
Storage media.
Background technique
On the production line of chip production, it usually needs carry out qualification detection, positioning attachment etc. to chip.For example,
On SIM (Subscriber Identification Module subscriber identification module) chip production line, need to detect SIM chip
It is whether qualified, SIM chip is positioned to determine the position mounted to SIM chip.
Template matching method is usually used in traditional approach and carries out chip recognition detection, but template matching method exists to making an uproar
Sound sensitive issue, the situation for qualification detection mistake occur is more, and error rate is relatively high.
Summary of the invention
Based on this, it is necessary to which, for the high technical problem of traditional chip qualification detection error rate, providing one kind can
Improve chip detecting method, device, computer equipment and the storage medium of Detection accuracy.
A kind of chip detecting method, which comprises
Obtain the chip image of chip to be detected；
Corresponding image moment is generated according to the chip image；
The identification operator of corresponding chip image is generated according to described image square；
If the identification operator of the chip image is matched with preset template identification operator, detection pass result is generated；
If the identification operator of the chip image and preset template identification operator mismatch, the unqualified knot of detection is generated
Fruit.
A kind of chip-detecting apparatus, described device include:
Image collection module, for obtaining the chip image of chip to be detected；
Image moment computing module, for generating corresponding image moment according to the chip image；
Operator computing module is identified, for generating the identification operator of corresponding chip image according to described image square；
First result-generation module is matched for the identification operator in the chip image with preset template identification operator
When, generate detection pass result；
Second result-generation module, in the chip image identification operator and preset template identification operator not
Timing generates and detects unqualified result.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
Device performs the steps of when executing the computer program
Obtain the chip image of chip to be detected；
Corresponding image moment is generated according to the chip image；
The identification operator of corresponding chip image is generated according to described image square；
If the identification operator of the chip image is matched with preset template identification operator, detection pass result is generated；
If the identification operator of the chip image and preset template identification operator mismatch, the unqualified knot of detection is generated
Fruit.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
It is performed the steps of when row
Obtain the chip image of chip to be detected；
Corresponding image moment is generated according to the chip image；
The identification operator of corresponding chip image is generated according to described image square；
If the identification operator of the chip image is matched with preset template identification operator, detection pass result is generated；
If the identification operator of the chip image and preset template identification operator mismatch, the unqualified knot of detection is generated
Fruit.
Said chip detection method, device, computer equipment and storage medium, it is raw according to the chip image of chip to be detected
At corresponding image moment, the identification operator of corresponding chip image is generated further according to image moment, by identification operator and preset template
Identification operator is compared analysis to realize the detection for treating detection chip.If the identification operator of chip image and template identification are calculated
Son matching, then it represents that chip image is qualified, then the chip to be detected for corresponding to chip image is qualified, generates detection pass result；If
The identification operator of chip image and template identification operator mismatch, and indicate that chip image is unqualified, then correspond to chip image to
Detection chip is unqualified, generates and detects unqualified result.In this way, passing through the identification operator generated according to the image moment of chip image
Carry out qualified detection, strong interference immunity, Detection accuracy height.
Detailed description of the invention
Fig. 1 is the flow diagram of chip detecting method in one embodiment；
Fig. 2 is the grey level histogram in one embodiment；
Fig. 3 is to generate corresponding image moment according to chip image in one embodiment, generate corresponding chip according to image moment
The detailed process schematic diagram of the identification operator of image；
Fig. 4 is to carry out rectangle fitting to qualified chip image in one embodiment, obtains four intersection points of fitted rectangle
The centre coordinate of fitted rectangle and the flow diagram of deflection angle are calculated according to intersecting point coordinate for coordinate；
Fig. 5 is in one embodiment to the system structure diagram of SIM chip attachment detection；
Fig. 6 is to be used as identification operator to treat detection chip using traditional HU square to carry out qualification detection and using improvement
The feature vector of HU square and eccentricity composition treats the comparison diagram that detection chip carries out qualification detection as identification operator；
Fig. 7 is the structural schematic diagram of chip-detecting apparatus in one embodiment；
Fig. 8 is the internal structure chart of computer equipment in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
In one embodiment, as shown in Figure 1, providing a kind of chip detecting method, it is applied to terminal in this way
Example is illustrated, comprising the following steps:
S110: the chip image of chip to be detected is obtained.
Chip to be detected refers to that needs detect whether qualified chip.For example, chip to be detected needs after can be production
Detect whether qualified SIM chip.The chip image of chip to be detected is the image that shooting chip to be detected obtains.Specifically,
Terminal can receive the chip image of chip to be detected transmitted by the camera for shooting chip to be detected.
S130: corresponding image moment is generated according to chip image.
Image moment is the operator for describing characteristics of image.Specifically, terminal generates this chip image according to chip image
Image moment.
S150: the identification operator of corresponding chip image is generated according to image moment.
Identify that operator is the operator that characteristics of image is further embodied on the basis of image moment.Specifically, terminal is according to core
The identification operator that the image moment of picture generates is the identification operator of this chip image.
S170: if the identification operator of chip image is matched with preset template identification operator, detection pass result is generated.
Wherein, preset template identification operator is preset, for an identification operator of reference pair ratio.For example, mould
Plate identification operator can be identification operator corresponding to the image of standard qualified chip.Specifically, the identification operator of chip image
It is matched with preset template identification operator, refers to that the identification operator of chip image is consistent with preset template identification operator.It can be with
Understand, meet matched condition and be also possible to other, for example, the identification operator of chip image and preset template identify operator
Difference with the identification operator and template identification operator that may also mean that chip image is within a preset range.
S190: if the identification operator of chip image and preset template identification operator mismatch, it is unqualified to generate detection
As a result.
Identification operator describes the characteristics of image of corresponding image, and characteristics of image can accurately reflect the characteristic information of image；
It, can be with to be detected corresponding to comparative analysis chip image compared with the identification operator of chip image is identified operator with template
Standard qualified chip corresponding to chip and template identification operator.If the identification operator of chip image and template identify operator
Match, then it represents that chip to be detected and standard qualified chip are same or similar, and chip to be detected is qualified, generate the qualified knot of detection at this time
Fruit；Otherwise, if it does not match, indicating that chip to be detected differs larger with standard qualified chip, chip to be detected is unqualified, at this time
It generates and detects unqualified result.
In said chip detection method, corresponding image moment is generated according to the chip image of chip to be detected, further according to figure
As square generates the identification operator of corresponding chip image, identification operator is compared analysis with preset template identification operator and is come in fact
Now treat the detection of detection chip.If the identification operator of chip image is matched with template identification operator, then it represents that chip image closes
Lattice, then the chip to be detected for corresponding to chip image is qualified, generates detection pass result；If the identification operator and template of chip image
It identifies that operator mismatches, indicates that chip image is unqualified, then the chip to be detected for corresponding to chip image is unqualified, generates detection not
Pass result.In this way, by the qualified detection of identification operator progress generated according to the image moment of chip image, strong interference immunity,
Detection accuracy is high.
It is appreciated that in other embodiments, the qualification of chip to be detected can also be detected using other methods.Example
Such as, since the area features of different type chip are relatively stable and have discrimination, the area of utilized chip is known to reach
The purpose not detected.If the normal area of chip floats between S1-S2, if the area of identification chip is recognized between S1-S2
It is set to qualified chip；If not between S1-S2, for unqualified chip.
In one embodiment, step S110 includes: the initial pictures for receiving and sending after camera shooting；To initial pictures into
Row contours extract, if extracting successfully, using initial pictures as the chip image of chip to be detected.
Camera is the equipment for shooting chip to be detected；In actual use, camera can be placed in fixed position into
Row shooting, therefore, the initial pictures that camera is shot may take chip to be detected, it is also possible to be not picked up by
Detection chip.By carrying out contours extract to initial pictures, specifically extraction chip outline extracts wheel if extracting successfully
It is wide, then it represents that initial pictures are the images for taking chip to be detected, can be using initial pictures as the chip figure of chip to be detected
Picture.So, it can be ensured that the image for needing detection chip in chip image improves the validity of detection.Specifically, terminal can lead to
Findcontours () function is crossed to carry out contours extract.
In one embodiment, in step S110, receive camera shooting after send initial pictures the step of after, to first
Beginning image carried out before the step of contours extract, further includes: pre-processes to initial pictures.Accordingly, terminal is to pretreatment
Initial pictures afterwards carry out contours extract.
Wherein, pretreatment includes eliminating the processing of noise jamming.For example, pretreatment can be smooth, filtering processing etc..It is logical
Initial pictures are pre-processed after first, the accuracy of initial pictures can be improved, to improve the accurate of subsequent analysis detection
Property.
Said chip detection method can be used for the qualification detection to SIM chip, and SIM chip is placed on a moving belt,
Conveyer belt is moved by active wheel drive, and camera is used to shoot the SIM chip on conveyer belt.In one embodiment, step S110
Later further include: if extraction is unsuccessful, i.e., do not extract profile, then the movement of active wheel drive conveyer belt is controlled, to convey
SIM chip.Contours extract is unsuccessful, then it represents that camera is not picked up by chip to be detected.At this point, passing through control active wheel drive
Conveyer belt is mobile to convey SIM chip, can be convenient camera shooting to carry out chip detection.
In one embodiment, image moment includes geometric moment and geometrical center to center.Step S130 include: to chip image into
Row threshold division obtains the discrete function of binary image；Riemann integral is carried out to the discrete function of binary image, is obtained pair
Answer the geometric moment and geometrical center to center of chip image.
Threshold segmentation is carried out to chip image, the gray value that specifically can be statistics chip image obtains grey level histogram,
The pixel value of image is divided into 0 and 1 two kinds of value according to grey level histogram, according to given threshold, pixel value is greater than etc.
Then it is 1 in given threshold, is then 0 less than given threshold, obtains binary image.Grey level histogram can be used for pixel set
It is divided, background area and target area is separated, to achieve the purpose that image segmentation.For example, the intensity histogram of SIM chip
Figure is as shown in Figure 2.The discrete function of binary image is the corresponding expression function of binary image.By being carried out to discrete function
Riemann integral, available geometric moment and geometrical center to center, geometric moment and geometrical center to center as corresponding chip image.
Specifically, if the discrete function of binary image is f (x, y), the geometric moment m of the p+q rank of f (x, y) can be calculatedpq
And geometric center square μpqIt is defined as follows:
Wherein, x and y is the abscissa value of binary image, ordinate value respectively,WithIt is being averaged for abscissa respectively
The average value of value, ordinate, N and M are the ranks size of binary image respectively.
In one embodiment, step S150 includes: that HU square is calculated according to geometrical center to center；According to geometrical center to center
HU square is optimized, obtains improving HU square；Eccentricity is calculated according to geometric moment；HU square will be improved and eccentricity composition is special
Vector is levied, the identification operator of chip image is obtained.
With improve HU square include R1, R2, R3, R4, R5, R6, R7, R8, R9, eccentricity be e be illustrated, HU will be improved
Square and eccentricity composition characteristic vector, specifically composition [R1, R2, R3, R4, R5, R6, R7, R8, R9, R10, e] feature to
Amount, as identification operator.HU square is improved by optimizing to obtain to HU square, on this basis, in conjunction with eccentricity, composition identification
Operator, feature identify that accuracy is high.
Specifically, HU square is calculated according to geometrical center to center in step S150, comprising: normalizing is carried out to geometrical center to center
Change, obtain normalization center away from；According to normalization center away from linear composition HU square.
The geometric center square μ of chip imagepqOnly have translation invariance without rotational invariance.To make chip image
Meet rotational invariance and constant rate, it can be normalized, obtains normalization center away from normalization center
Away from formula be defined as follows:
Further, normalization central moment can be by linearly forming with translation invariance, rotational invariance and ratio not
7 HU squares of denaturation, i.e. 7 Image Moment Invariants, formula are expressed as follows:
Wherein,ExtremelyRespectively 7 HU squares.
In one embodiment, in step S150, HU square is optimized according to geometrical center to center, obtains improving HU square,
Include: the geometrical center to center for removing 0 rank in HU square by ratio calculation, obtains improving HU square.
For example, μpqIndicate geometrical center to center, the geometrical center to center of 0 rank is μ00, by removing scale factor μ00, obtain
The not bending moment of new unification, and variation caused by the area or scaling of target image can be ignored in newly unified not bending moment, and only with
Geometry is related, is suitble to the object component of different zones structure.In this way, obtaining improving HU square by optimizing HU square, based on changing
Qualification detection is carried out into HU square, efficient identification may be implemented, and recognition correct rate is high.
Specifically, the geometrical center to center for removing 0 rank in HU square by ratio calculation obtains improving HU square, comprising:
Wherein, R1, R2, R3, R4, R5, R6, R7, R8, R9, R10 are respectively to improve HU square.Eliminate μ00, but its is flat
It moves, scale and rotational invariance still meet.
In one embodiment, in step S150, eccentricity is calculated according to geometric moment, comprising:
Wherein, e is eccentricity, m20、m02And m11It can be according to formulaIt obtains.Eccentricity is
The ratio of image maximum axis and minimum axis, meets geometrical characteristic invariance.By using eccentricity e, enhancing improves HU square to core
The recognition capability of piece profile.
For example, being the detail flowchart of step S130 and step S150 in a specific embodiment with reference to Fig. 3.
In one embodiment, further include positioning step after step S170: it is quasi- to carry out rectangle to qualified chip image
It closes, obtains four intersecting point coordinates of fitted rectangle；The centre coordinate and deflection angle of fitted rectangle are calculated according to intersecting point coordinate
Degree.
Centre coordinate is the coordinate of the center of fitted rectangle, and deflection angle is fitted rectangle relative to presetting zero
Spend the angle of the inflection point in direction.Centre coordinate and deflection angle can reflect the position of chip image, to realize to core
The positioning of picture.Specifically, after getting centre coordinate and deflection angle, patch can be generated according to centre coordinate and deflection angle
Holding position instruction carries out chip attachment according to center and deflection angle for controlling chip mounter.By using rectangle fitting
Method realize positioning to chip, positioning accuracy is high, positioning accuracy specifically may be implemented within 0.5 pixel and rotation angle
In 0.10.
With reference to Fig. 4, the detailed process of positioning step is analyzed as follows: when carrying out rectangle fitting, first having to determine target area
Four vertex on domain.Four apex coordinates and fitted rectangle found are linear, and four vertex are more accurate, rectangle fitting
Precision it is higher.Then using four vertex as boundary, marginal point is divided into four groups, the pixel coordinate collection of each group of sampled equidistant
Number be respectively n1、n2、n3、n4, then every group of pixel coordinate expressions are as follows:
Wherein, Xi(i=1,2,3,4) is its four vertex, and x and y are belonging respectively to different four groups of transverse and longitudinal coordinates.According to square
Geometrical characteristic, that is, opposite side of shape is parallel and adjacent side is vertical, if linear equation indicates where four sides of rectangle minimum are as follows:
Wherein, a, b, ci(i=1,2,3,4) be linear equation parameter.By four while where straight line to it is each while pixel
Distance most it is short i.e. 4 equations deviation it is all minimum, it will be able to fit standard rectangular, in this way can be accurately to chip wheel
It is expressed at wide edge.Since there are positive and negative deviations, positive and negative deviation can be made to cancel out each other by summation, in conjunction with
The geometrical property of rectangle, i.e. adjacent side slope are mutually fallen, opposite side slope is equal, then rectangle fitting equation indicates are as follows:
N in formula1、n2、n3、n4It include the number of point corresponding to four side of target, then respectively to a, b, c1、c2、c3、c4It asks
Partial derivative obtains parameter a, b and the corresponding intercept c in every side1、c2、c3、c4, the linear equation where each edge is finally obtained, is solved
Obtain four intersection point A (xA,yA), B (xB,yB), C (xC,yC), D (xD,yD), and the average value of intersecting point coordinate is in chip image
Heart coordinate (x0,y0), location parameter is as follows:
In addition, indicating that chip to be detected does not deflect, then core to be detected when setting one side of rectangle and x-axis angle as 90 °
The deflection angle of piece:
Specifically, when being mounted using centre coordinate and deflection angle control chip mounter, when deflection angle is less than 0o,
Chip to be detected can control to rotate counterclockwise into capable compensation；When deflection angle is greater than 0o, it can control chip to be detected clockwise
Rotation compensates.
It should be understood that although each step in the flow chart of Fig. 1, Fig. 3-4 is successively shown according to the instruction of arrow,
But these steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly state otherwise herein, these
There is no stringent sequences to limit for the execution of step, these steps can execute in other order.Moreover, in Fig. 1, Fig. 3-4
At least part step may include multiple sub-steps perhaps these sub-steps of multiple stages or stage be not necessarily
Synchronization executes completion, but can execute at different times, and the execution sequence in these sub-steps or stage also need not
Be so successively carry out, but can at least part of the sub-step or stage of other steps or other steps in turn or
Person alternately executes.
It is illustrated below with a concrete application example, with reference to Fig. 5, when SIM chip mounts, driving wheel 9 and driven wheel 7 are together
Effect driving synchronous belt 6 moves, and synchronous belt 6 drives the SIM plate 5 to get stuck in mechanism to move synchronously, and SIM chip is sent to accurately
Station after, identification positioning is carried out to it using vision system.The hardware of vision system is generally by benchmark camera 2 and identification camera
OpenCV can be used in 10 both cameras composition, software section.Benchmark camera 2 is mounted on suction nozzle 1 and moves along the direction x-y
It is dynamic, pass through 3 absorption chip 4 of suction nozzle and the top for being moved to identification camera 10 is shot to obtain the chip figure of chip to be detected
Picture.Then, the chip that OpenCV obtains chip to be detected executes, and executes said chip detection method, and it is qualified to carry out to SIM chip
Property detection.Further, qualified chip can be positioned, obtains centre coordinate and deflection angle.It is improved due to using
HU square and eccentricity identify the SIM chip of rotation, translation and scaling as feature vector, recycle rectangle fitting side
Method is positioned, and can carry out high accuracy positioning to SIM chip on the basis of efficient identification.
With reference to Fig. 6, to treat detection chip progress qualification detection as identification operator using traditional HU square and using
The feature vector for improving HU square and eccentricity composition treats the comparison diagram that detection chip carries out qualification detection as identification operator.
By calculating the relationship of different number of chips and correct recognition rata come the recognition performance of parser, it is known that using improve HU square and
The feature vector of eccentricity composition has better performance as identification operator in terms of SIM chip identification.
In one embodiment, as shown in fig. 7, providing a kind of chip-detecting apparatus, comprising: image collection module 710,
Image moment computing module 730, identification operator computing module 750, the first result-generation module 770 and the second result-generation module
790, in which:
Image collection module 710 is used to obtain the chip image of chip to be detected.Image moment computing module 730 is used for basis
Chip image generates corresponding image moment.Identify that operator computing module 750 is used to generate corresponding chip image according to image moment
Identify operator.First result-generation module 770 is used to match in the identification operator of chip image with preset template identification operator
When, generate detection pass result.Second result-generation module 790 is used to know in the identification operator of chip image and preset template
When other operator mismatches, generates and detect unqualified result.
Said chip detection device generates corresponding image moment according to the chip image of chip to be detected, further according to image
Square generates the identification operator of corresponding chip image, and identification operator is compared analysis with preset template identification operator to realize
Treat the detection of detection chip.If the identification operator of chip image is matched with template identification operator, then it represents that chip image is qualified,
The chip to be detected for then corresponding to chip image is qualified, generates detection pass result；If the identification operator of chip image and template are known
Other operator mismatches, and indicates that chip image is unqualified, then the chip to be detected for corresponding to chip image is unqualified, generates detection and does not conform to
Lattice result.In this way, carrying out qualified detection, strong interference immunity, inspection by the identification operator generated according to the image moment of chip image
It is high to survey accuracy rate.
In one embodiment, image collection module 710 receives the initial pictures sent after camera shooting；To initial pictures
Contours extract is carried out, if extracting successfully, using initial pictures as the chip image of chip to be detected.By to initial pictures into
Row contours extract will extract successfully using initial pictures as the chip image of chip to be detected.So, it can be ensured that chip image
The image for inside needing detection chip improves the validity of detection.
In one embodiment, image moment includes geometric moment and geometrical center to center.Image moment computing module 730 is used for core
Picture carries out Threshold segmentation, obtains the discrete function of binary image；Riemann's product is carried out to the discrete function of binary image
Point, obtain the geometric moment and geometrical center to center of corresponding chip image.
In one embodiment, identification operator computing module 750 is used to that HU square to be calculated according to geometrical center to center；According to
Geometrical center to center optimizes HU square, obtains improving HU square；Eccentricity is calculated according to geometric moment；Will improve HU square and from
Heart rate composition characteristic vector obtains the identification operator of chip image.HU square is improved by optimizing to obtain to HU square, in this base
On plinth, in conjunction with eccentricity, composition identification operator, feature identifies that accuracy is high.
In one embodiment, said chip detection device further includes locating module, for qualified chip image into
Row rectangle fitting obtains four intersecting point coordinates of fitted rectangle；The centre coordinate of fitted rectangle is calculated according to intersecting point coordinate
And deflection angle.The positioning to chip is realized by using the method for rectangle fitting, and positioning accuracy is high.
Specific about chip-detecting apparatus limits the restriction that may refer to above for chip detecting method, herein not
It repeats again.Modules in said chip detection device can be realized fully or partially through software, hardware and combinations thereof.On
Stating each module can be embedded in the form of hardware or independently of in the processor in computer equipment, can also store in a software form
In memory in computer equipment, the corresponding operation of the above modules is executed in order to which processor calls.
In one embodiment, a kind of computer equipment is provided, which can be terminal, internal structure
Figure can be as shown in Figure 8.The computer equipment includes processor, the memory, network interface, display connected by system bus
Screen and input unit.Wherein, the processor of the computer equipment is for providing calculating and control ability.The computer equipment is deposited
Reservoir includes non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system and computer journey
Sequence.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The network interface of machine equipment is used to communicate with external terminal by network connection.When the computer program is executed by processor with
Realize a kind of chip detecting method.The display screen of the computer equipment can be liquid crystal display or electric ink display screen,
The input unit of the computer equipment can be the touch layer covered on display screen, be also possible to be arranged on computer equipment shell
Key, trace ball or Trackpad, can also be external keyboard, Trackpad or mouse etc..
It will be understood by those skilled in the art that structure shown in Fig. 8, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor are provided, is stored in memory
The step of computer program, which realizes aforementioned chip detecting method when executing computer program.
Due to the step of realizing aforementioned chip detecting method similarly, chip qualification can be improved in above-mentioned computer equipment
The accuracy of detection.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
The step of machine program realizes aforementioned chip detecting method when being executed by processor.
Due to the step of realizing aforementioned chip detecting method similarly, core can be improved in above-mentioned computer readable storage medium
The accuracy of piece qualification detection.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of embodiment described above can be combined arbitrarily, for simplicity of description, not to above-mentioned reality
It applies all possible combination of each technical characteristic in example to be all described, as long as however, the combination of these technical characteristics is not deposited
In contradiction, all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of chip detecting method, which is characterized in that the described method includes:
Obtain the chip image of chip to be detected；
Corresponding image moment is generated according to the chip image；
The identification operator of corresponding chip image is generated according to described image square；
If the identification operator of the chip image is matched with preset template identification operator, detection pass result is generated；
If the identification operator of the chip image and preset template identification operator mismatch, the unqualified result of detection is generated.
2. the method according to claim 1, wherein the chip image for obtaining chip to be detected, comprising:
Receive the initial pictures sent after camera shooting；
Contours extract is carried out to the initial pictures, if extracting successfully, using the initial pictures as the core of chip to be detected
Picture.
3. the method according to claim 1, wherein described image square includes geometric moment and geometrical center to center；Institute
It states and corresponding image moment is generated according to the chip image, comprising:
Threshold segmentation is carried out to the chip image, obtains the discrete function of binary image；
Riemann integral is carried out to the discrete function of the binary image, obtains the geometric moment and geometric center of corresponding chip image
Away from.
4. according to the method described in claim 3, it is characterized in that, described generate corresponding chip image according to described image square
Identify operator, comprising:
HU square is calculated according to the geometrical center to center；
The HU square is optimized according to the geometrical center to center, obtains improving HU square；
Eccentricity is calculated according to the geometric moment；
By the improvement HU square and the eccentricity composition characteristic vector, the identification operator of the chip image is obtained.
5. according to the method described in claim 4, it is characterized in that, described carry out the HU square according to the geometrical center to center
Optimization obtains improving HU square, comprising:
The geometrical center to center for removing 0 rank in the HU square by ratio calculation obtains the improvement HU square.
6. the method according to claim 1, which is characterized in that if the identification of the chip image
Operator is matched with preset template identification operator, then is generated after detecting pass result, further includes:
Rectangle fitting is carried out to qualified chip image, obtains four intersecting point coordinates of fitted rectangle；
The centre coordinate and deflection angle of the fitted rectangle are calculated according to the intersecting point coordinate.
7. a kind of chip-detecting apparatus, which is characterized in that described device includes:
Image collection module, for obtaining the chip image of chip to be detected；
Image moment computing module, for generating corresponding image moment according to the chip image；
Operator computing module is identified, for generating the identification operator of corresponding chip image according to described image square；
First result-generation module, when being matched for the identification operator in the chip image with preset template identification operator,
Generate detection pass result；
Second result-generation module, for the identification operator and preset template identification operator mismatch in the chip image
When, it generates and detects unqualified result.
8. chip-detecting apparatus according to claim 7, which is characterized in that further include locating module, for qualification
Chip image carries out rectangle fitting, obtains four intersecting point coordinates of fitted rectangle；It is calculated according to the intersecting point coordinate described
The centre coordinate and deflection angle of fitted rectangle.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 6 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 6 is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811486234.6A CN109584237A (en) | 2018-12-06 | 2018-12-06 | Chip detection method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811486234.6A CN109584237A (en) | 2018-12-06 | 2018-12-06 | Chip detection method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109584237A true CN109584237A (en) | 2019-04-05 |
Family
ID=65927644
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811486234.6A Pending CN109584237A (en) | 2018-12-06 | 2018-12-06 | Chip detection method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109584237A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111257296A (en) * | 2020-03-20 | 2020-06-09 | 京东方科技集团股份有限公司 | Method, device and storage medium for detecting biochip sample |
| CN112082480A (en) * | 2020-09-08 | 2020-12-15 | 浙江清华柔性电子技术研究院 | Method and system for measuring spatial orientation of chip, electronic device and storage medium |
| CN112635346A (en) * | 2020-12-08 | 2021-04-09 | 深圳中科飞测科技股份有限公司 | Wafer detection method, semiconductor detection device and storage medium |
| CN113269743A (en) * | 2021-05-20 | 2021-08-17 | 北京理工大学重庆创新中心 | Chip quantity detection method based on iterative translation verification |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20010029597A1 (en) * | 2000-03-28 | 2001-10-11 | Kabushiki Kaisha Toshiba | Semiconductor inspecting system, semiconductor defect anlyzing system, semiconductor design data modifying system, semiconductor inspecting method, semiconductor defect analyzing method, semiconductor design data modifying method, and computer |
| US20030228048A1 (en) * | 2002-06-11 | 2003-12-11 | Fujitsu Limited | Pattern image comparison method, pattern image comparison device, and program |
| CN108171102A (en) * | 2016-12-07 | 2018-06-15 | 广州映博智能科技有限公司 | A kind of part method for quickly identifying of view-based access control model |
-
2018
- 2018-12-06 CN CN201811486234.6A patent/CN109584237A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20010029597A1 (en) * | 2000-03-28 | 2001-10-11 | Kabushiki Kaisha Toshiba | Semiconductor inspecting system, semiconductor defect anlyzing system, semiconductor design data modifying system, semiconductor inspecting method, semiconductor defect analyzing method, semiconductor design data modifying method, and computer |
| US20030228048A1 (en) * | 2002-06-11 | 2003-12-11 | Fujitsu Limited | Pattern image comparison method, pattern image comparison device, and program |
| CN108171102A (en) * | 2016-12-07 | 2018-06-15 | 广州映博智能科技有限公司 | A kind of part method for quickly identifying of view-based access control model |
Non-Patent Citations (4)
| Title |
|---|
| ZUOWEN SHAO ETAL.: "Design of image detection and target tracking system under sea condition", 《2009 4TH IEEE CONFERENCE ON INDUSTRIAL ELECTRONICS AND APPLICATIONS》 * |
| 寸毛毛 等: "基于改进Hu 矩和矩形拟合的芯片识别定位算法", 《包装工程》 * |
| 谭智仁 等: "基于图像传感器的标签缺陷检测方法", 《组合机床与自动化加工技术》 * |
| 黄勇 等: "基于形状不变矩的图像检索算法的研究", 《计算机应用研究》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111257296A (en) * | 2020-03-20 | 2020-06-09 | 京东方科技集团股份有限公司 | Method, device and storage medium for detecting biochip sample |
| CN111257296B (en) * | 2020-03-20 | 2023-04-11 | 京东方科技集团股份有限公司 | Method, device and storage medium for detecting biochip sample |
| CN112082480A (en) * | 2020-09-08 | 2020-12-15 | 浙江清华柔性电子技术研究院 | Method and system for measuring spatial orientation of chip, electronic device and storage medium |
| CN112635346A (en) * | 2020-12-08 | 2021-04-09 | 深圳中科飞测科技股份有限公司 | Wafer detection method, semiconductor detection device and storage medium |
| CN112635346B (en) * | 2020-12-08 | 2023-12-26 | 深圳中科飞测科技股份有限公司 | Wafer inspection method, semiconductor inspection apparatus, and storage medium |
| CN113269743A (en) * | 2021-05-20 | 2021-08-17 | 北京理工大学重庆创新中心 | Chip quantity detection method based on iterative translation verification |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109584237A (en) | Chip detection method and device, computer equipment and storage medium | |
| US11227405B2 (en) | Determining positions and orientations of objects | |
| US10534957B2 (en) | Eyeball movement analysis method and device, and storage medium | |
| US10635946B2 (en) | Eyeglass positioning method, apparatus and storage medium | |
| KR101298024B1 (en) | Method and interface of recognizing user's dynamic organ gesture, and electric-using apparatus using the interface | |
| EP1678659B1 (en) | Method and image processing device for analyzing an object contour image, method and image processing device for detecting an object, industrial vision apparatus, smart camera, image display, security system, and computer program product | |
| US20140088765A1 (en) | Method for invalidating sensor measurements after a picking action in a robot system | |
| CN102156978B (en) | Industrial device rapid locating method based on machine vision | |
| CN109840524B (en) | Text type recognition method, device, equipment and storage medium | |
| US10650234B2 (en) | Eyeball movement capturing method and device, and storage medium | |
| CN109492642B (en) | License plate recognition method, license plate recognition device, computer equipment and storage medium | |
| KR101517359B1 (en) | Method for tracking of object and appaaratus using the same | |
| CN109816634B (en) | Detection method, model training method, device and equipment | |
| KR101298023B1 (en) | Method and interface of recognizing user's dynamic organ gesture, and electric-using apparatus using the interface | |
| CN111259908A (en) | Machine vision-based steel coil number identification method, system, equipment and storage medium | |
| CN112164050B (en) | Method and device for detecting surface defects of products on production line and storage medium | |
| CN111702756B (en) | Object grabbing method based on machine vision, robot and storage medium | |
| US10386930B2 (en) | Depth determining method and depth determining device of operating body | |
| CN107194971B (en) | Golden finger positioning method and device and computer readable storage medium | |
| CN111145254B (en) | Door valve blank positioning method based on binocular vision | |
| CN109741302B (en) | SD card form recognition system and method based on machine vision | |
| CN115330997A (en) | YOLOv4 neural network-based control box assembly defect detection method, device and medium | |
| CN116071562A (en) | Plant seed identification method and device, electronic equipment and storage medium | |
| CN115187769A (en) | Positioning method and device | |
| JP2023535005A (en) | Method and system or apparatus for recognizing objects in electronic images |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190405 |