CN111678450B - Visual detection method and device for precision part - Google Patents
Visual detection method and device for precision part Download PDFInfo
- Publication number
- CN111678450B CN111678450B CN202010386398.2A CN202010386398A CN111678450B CN 111678450 B CN111678450 B CN 111678450B CN 202010386398 A CN202010386398 A CN 202010386398A CN 111678450 B CN111678450 B CN 111678450B
- Authority
- CN
- China
- Prior art keywords
- detection
- area
- positioning
- precision
- interest
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- 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
- G01B11/16—Measuring arrangements characterised by the use of optical techniques for measuring the deformation in a solid, e.g. optical strain gauge
-
- 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
-
- 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
- G01B11/14—Measuring arrangements characterised by the use of optical techniques for measuring distance or clearance between spaced objects or spaced apertures
Abstract
The invention relates to a method and a device for visual inspection of precision parts, wherein the method comprises the following steps: the method comprises the following steps of 'object image shadow' joint detection, wherein the joint detection step is used for acquiring a gap value between a part and a reflection image of the part; the method comprises a segmentation detection step, a part side view image obtaining step and a part side view image obtaining step, wherein the segmentation detection step is used for dividing the part side view image into a plurality of interested areas and determining the deformation condition of each interested area; a grouping and sorting step, which is used for grouping and detecting the parts with the deformation in the preset deviation range according to the specified tolerance; and a step of accurately positioning a detection area is also included between the step of segment detection and the step of grouping and sorting, and the step of accurately positioning the detection area is used for reducing positioning errors caused by pose change. The device comprises: side looking camera, glass objective table, positioner and computer processing device. The invention can realize flexible control on the detection effect, and improve the detection precision and the detection effect while meeting the requirement of higher detection speed.
Description
Technical Field
The invention relates to the technical field of visual inspection of parts, in particular to a visual inspection method and device for precision parts.
Background
In recent years, in the field of automated detection of small-sized (millimeter-sized) precision parts or large-sized (centimeter-sized) non-precision parts, for example, in the aspect of size detection of fine screws and nuts or large forgings, research and application of machine vision detection technology have been greatly advanced. However, for large-sized ultra-precise parts, factors influencing the precision of a visual detection system are many, and even if high-resolution hardware is used, the detection requirement is still difficult to directly meet, and a detection technology based on machine vision has certain difficulty. For example, a certain ultra-precise flat elongated hook part is composed of a main body and a hook, wherein the main body has a large length, a large length-width ratio and a small thickness, and is in an elongated strip shape in a side view direction; the hook part has fine structure, complex deformation and high requirement on consistency. At present, the detection speed and the detection precision are low by using a manual method, while the existing automatic detection device can realize high-speed feeding, but the detection requirements of large size and high precision are difficult to meet, and the difficulty is very high when the detection speed, the detection precision and the appropriate detection effect are simultaneously achieved.
Disclosure of Invention
The invention aims to provide a visual detection method for a precision part, which is used for improving the detection speed and precision of the part and improving the detection effect of the part.
The technical scheme adopted by the invention for solving the technical problems is as follows: the precision part visual detection method comprises the following steps:
the method comprises the following steps of 'object image shadow' joint detection, wherein the joint detection step is used for acquiring a gap value between a part and a reflection image of the part;
the method comprises a segmentation detection step, a part side view image obtaining step and a part side view image obtaining step, wherein the segmentation detection step is used for dividing the part side view image into a plurality of interested areas and determining the deformation condition of each interested area;
and a grouping and sorting step, which is used for grouping and detecting the parts with the deformation in the preset deviation range according to the specified tolerance.
The object image and shadow combined detection step specifically comprises the following steps: and acquiring a part side view image of the part and the part which are in contact with each other relative to the reflection of the glass object stage, and acquiring a clearance value of which the size is two times of the actual deformation amount between the reflection corresponding to the part and the part.
The step of segment detection specifically comprises: dividing the side view image of the part into a plurality of interested areas, sequentially detecting the maximum gap value or the minimum gap value in each interested area, knowing the maximum deformation of the part through the maximum gap value, and knowing whether the part is in contact with the glass object stage or not through the minimum gap value; and returning a gap value after each interested area is detected, and calibrating each interested area respectively.
When the acquired side view of the part is divided into a plurality of regions of interest, a plurality of regions of interest with first areas are arranged on the main body part of the part; setting a plurality of interested areas of a second area on the complex-form part of the part to cover the complex-form part of the whole part; wherein the first area is larger than the second area.
The region of interest is a rectangular region.
And each region of interest adopts a sub-pixel measurement technology during detection.
And a step of accurately positioning a detection area is also included between the step of segment detection and the step of grouping and sorting, and the step of accurately positioning the detection area is used for reducing positioning errors caused by pose change.
The accurate positioning detection area specifically comprises the following steps: and setting two side edges of the head and the tail of the part in the side-view image of the part as two positioning references, and selecting one positioning reference which is closer to the interested area for positioning.
The grouping and sorting steps are specifically as follows: and detecting the parts with the deformation amount within the preset deviation range in groups by limiting the gap value of each region of interest, wherein each group specifies a tolerance.
The invention also provides a precision part visual detection device, which comprises: a glass stage; the camera is a side-view camera, the position of a lens of the camera is slightly higher than the part on the glass object stage, and the camera is used for acquiring a digital image of the side-view direction of the part; the positioning device is used for adjusting the pose of the part; and the computer processing device is used for controlling and processing the camera and the positioning device to complete visual detection, receiving feedback information of the camera and the positioning device in real time, and detecting the parts on the glass object stage by adopting any one of the detection methods.
Advantageous effects
Due to the adoption of the technical scheme, compared with the prior art, the invention has the following advantages and positive effects: according to the invention, the deformation is defined by the clearance value between the part and the reflection image of the part, so that the influence of the plane of the objective table is avoided; according to the invention, the deformation of the elongated part in the side view direction is detected by adopting a segmented detection method, so that the flexible control on the detection effect can be realized; in the invention, the situation that the slight pose change of a part on the glass object stage is inevitable is considered, a plurality of interested area positioning benchmarks are adopted, and the positioning error caused by the pose change is reduced by accurately positioning the detection area; the invention detects the parts by a grouping sorting method, thereby improving the detection effect. Under the condition of limited hardware resolution, the detection method is an effective new strategy for detecting large-size ultra-precise parts.
Drawings
FIG. 1 is a schematic view of a machine vision inspection apparatus according to an embodiment of the present invention;
FIG. 2 is a side view of a part lying flat on a glass stage in an embodiment of the invention;
FIG. 3 is a schematic diagram of a segmentation detection method according to an embodiment of the present invention;
FIG. 4 is a view of a variation of the hook of an embodiment of the present invention;
FIG. 5 is a part pose deflection diagram of an embodiment of the present invention;
FIG. 6 is a diagram illustrating the results of a visual inspection method according to an embodiment of the present invention.
Detailed Description
The invention will be further illustrated with reference to the following specific examples. It should be understood that these examples are for illustrative purposes only and are not intended to limit the scope of the present invention. Further, it should be understood that various changes or modifications of the present invention may be made by those skilled in the art after reading the teaching of the present invention, and such equivalents may fall within the scope of the present invention as defined in the appended claims.
The embodiment of the invention relates to a precision part visual detection method, which mainly comprises the following steps: the method comprises the following steps of 'object image shadow' joint detection, wherein the joint detection step is used for acquiring a gap value between a part and a reflection image of the part; the method comprises a segmentation detection step, a part side view image obtaining step and a part side view image obtaining step, wherein the segmentation detection step is used for dividing the part side view image into a plurality of interested areas and determining the deformation condition of each interested area; a grouping and sorting step, which is used for grouping and detecting the parts with the deformation in the preset deviation range according to the specified tolerance; and a step of accurately positioning a detection area is also included between the step of segment detection and the step of grouping and sorting, and the step of accurately positioning the detection area is used for reducing positioning errors caused by pose change.
Use general machine vision detection device as the basis in this embodiment, general vision detection device includes camera, glass objective table, positioner and computer processing device etc. the camera is for looking sideways at the camera for the part looks sideways at the acquirement of direction digital image, the glass objective table is used for bearing and carries the part fast, positioner is used for adjusting the part to certain position appearance. While high-speed detection is realized by the device, because the contact between the part and the objective table cannot be avoided, a proper detection strategy is needed to avoid the influence of the detection strategy on the detection precision.
The object image and shadow combined detection method adopted in the embodiment is to take an image of a part in contact with an inverted shadow of the part rather than a side view image of the part in contact with an object stage by slightly raising a camera lens above the part placed on the glass object stage, so that the influence of the plane of the object stage is avoided. In the side view, the part body and the reflection image thereof are both in a strip shape, and a gap with the size being two times of the actual deformation amount is formed between the part and the reflection image. That is, the deformation of the part is amplified by one time, and the detection precision is indirectly improved.
In the sectional detection method in the embodiment, the side view of the elongated strip-shaped part is divided into a plurality of interested areas according to a certain detection range, the maximum gap value or the minimum gap value in each area is sequentially detected, and the deformation condition of the area is judged. Each detection area is respectively calibrated, so that the measurement error caused by lens imaging distortion is avoided, and meanwhile, the detection precision is improved by combining a sub-pixel measurement technology under the condition of limited hardware performance. The setting scheme of the region of interest is as follows: arranging an interested area with a larger area on the part main body; in a part of a fine structure having a part of a complicated morphology, a region of interest having a small area and a large number is provided to cover the entire fine structure part. The detection of one interested area returns one gap value, the shape of a fine structure part is complex, the gap value is changed greatly, and the single maximum gap value or the minimum gap value can not control the overall deformation of the hook part. The deformation amount can be limited on the whole by arranging more small-area interested areas at the hook, the false detection is avoided, and the detection effect is improved.
The part is tiled on the objective table, after the pose deflection angle alpha is formed, the position and the projection length are changed, if the interested area cannot be correspondingly adjusted, the detection position of the interested area with a smaller area is greatly deviated, and a larger positioning error is easy to generate.
In view of the above situation, the method for accurately positioning the detection area is adopted in the embodiment: the side lines on the two sides of the head and the tail of the part in the side view are set as positioning references, and the selection of the positioning reference of the region of interest is based on the closer distance, so that the positioning error is reduced, and the positioning precision is improved.
In the embodiment, a grouping sorting method is further added, the gap value of each interested area is limited, the parts with deformation within a certain deviation range are divided into a plurality of groups to be detected, each group specifies a smaller tolerance, and the consistency effect of each group is better.
The present invention is further described below by a specific embodiment, in which a large-sized ultra-precise flat elongated hook part is used as a visual detection object, and a general visual detection device is used as a basis to improve detection precision and detection effect by an innovative detection strategy. The detection strategy adopts methods of 'object image shadow' joint detection, sectional detection, accurate positioning of detection areas, grouping and sorting and the like.
As shown in fig. 1, a schematic view of a machine vision inspection apparatus according to an embodiment of the present invention mainly includes a side-view camera for acquiring a side-view direction digital image of a part, a glass stage capable of rotating rapidly for carrying and rapidly transporting the part, a positioning device for adjusting the part to a certain pose, and a computer processing device. After being sent to the glass objective table, the parts sequentially pass through the positioning device and the side-looking camera and finally enter the classification box. When the machine vision detection device is used for realizing high-speed detection, because the contact between the part and the objective table cannot be avoided, a proper detection strategy is required to avoid the influence of the part on the detection precision, so that the requirement of the part detection precision is met.
As shown in fig. 2, which is a side view of the part laid on the glass stage in the embodiment of the present invention, in the "object image shadow" combined detection method, the camera lens is slightly higher than the plane 3 of the glass stage, so as to capture the part 1 and its reflection 2 relative to the glass stage, the image of the part 1 itself and the image of its reflection 2 are theoretically equal in size, and they can be clearly separated from the plane 3 of the glass stage, thereby avoiding the influence of the stage. The body of the part 1 and its reflection 2 are elongated in side view, and if deformed, there will be a gap between the part 1 and the reflection 2, otherwise they will coincide in contact with each other. In fig. 2, the right side hook of the part 1 always has a gap because the thickness is smaller than the body. The size of the gap is twice the actual gap between the part and the glass stage.
Further, the shape of the region of interest in the embodiment is rectangular, as shown in fig. 3, which is a schematic diagram of a segmentation detection method in the embodiment of the present invention, the segmentation detection method does not directly detect the deformation of the whole part, but divides the part into a plurality of rectangular regions of interest 4-10 according to a certain detection range, wherein 4-7 are rectangular regions of interest with a larger area, that is, regions of interest with a first area; 8-10 are rectangular interested areas with small areas, namely interested areas with second areas, and the maximum gap value or the minimum gap value in each rectangular interested area is detected in sequence. The maximum deformation is known from the maximum gap value, and whether the part is in contact with the glass object stage is known from the minimum gap value.
In the figure 3, rectangular interested areas 8-10 are arranged at a hook with a complex shape, the main characteristics are that the area is small, the quantity is large, and the hook is wholly subdivided into a plurality of rectangular interested areas. The reason for setting more rectangular interesting areas is that each rectangular interesting area can return a maximum gap value or a minimum gap value, the bending forms of the inner side and the outer side of the hook are complex, and the change of the gap value is large.
As shown in fig. 4, a hook deformation diagram of the component according to the embodiment of the present invention is shown, the hook has various deformations as shown in fig. 4, and a single gap value index cannot reflect the deformation of the hook portion. The small-area rectangular region of interest is arranged at the hook, so that the deformation can be limited on the whole, the false detection is avoided, and the detection effect is improved.
As shown in fig. 5, for the part pose deflection diagram according to the embodiment of the present invention, the part is tiled on the object stage, and after the pose deflection angle α is obtained, the position coordinate and the projection length are changed, if the rectangular region of interest divided as above cannot be adjusted accordingly, the rectangular region of interest with a smaller area at the hook is likely to generate a larger positioning error, and the detection area will generate a larger offset and even exceed the hook. For this case, the method for accurately locating the detection area: as shown in FIG. 3, two side lines of the head and the tail of the part image are set as a positioning reference 11 and a positioning reference 12, and the region of interest is positioned by the closer positioning reference. The rectangular regions of interest 4-5 are determined by specifying a distance from a positioning reference 11, and the rectangular regions of interest 6-10 are determined by specifying a distance from a positioning reference 12.
The group sorting method according to the present embodiment detects the parts deformed within a certain deviation range by limiting the gap value of each rectangular region of interest, and divides the parts into several groups, each group defining a small tolerance, and preferably detects the parts having a hook portion deformation within ± 2a in 4 groups of deformations (-2a, -a), (-a, 0), (0, a), (a, 2a), for example, so that the uniformity effect of each group is good.
As shown in fig. 6, which is a schematic diagram illustrating the result of the visual inspection method according to the embodiment of the present invention, a batch of parts obtained by the visual inspection method have good consistency after being arranged at equal intervals, and have no obvious bending phenomenon, which indicates that the inspection method has good inspection effect.
The invention also relates to a precision part visual inspection device, which comprises: a glass stage; the camera is a side-view camera, the position of a lens of the camera is slightly higher than the part on the glass object stage, and the camera is used for acquiring a digital image of the side-view direction of the part; the positioning device is used for adjusting the pose of the part; and the computer processing device is used for controlling and processing the camera and the positioning device to complete visual detection, receiving feedback information of the camera and the positioning device in real time, and detecting the parts on the glass object stage by adopting the detection method in the embodiment.
Therefore, the invention can realize flexible control on the detection effect of the precision parts, reduce the positioning error, improve the detection effect and provide a new idea for the detection of large-size ultra-precision parts by adopting a series of precision part visual detection methods such as 'object image shadow' combined detection step, sectional detection step and grouping sorting step and further combining with the step of accurately positioning the detection area.
Claims (7)
1. A precision part visual inspection method is characterized by comprising the following steps:
the method comprises the following steps of 'object image shadow' joint detection, wherein the joint detection step is used for acquiring a gap value between a part and a reflection image of the part;
the method comprises a segmentation detection step, a part side view image obtaining step and a part side view image obtaining step, wherein the segmentation detection step is used for dividing the part side view image into a plurality of interested areas and determining the deformation condition of each interested area;
the step of segment detection specifically comprises: dividing the side view image of the part into a plurality of interested areas, sequentially detecting the maximum gap value or the minimum gap value in each interested area, knowing the maximum deformation of the part through the maximum gap value, and knowing whether the part is in contact with the glass object stage or not through the minimum gap value; returning a gap value after each region of interest is detected, and calibrating each region of interest respectively;
a grouping and sorting step, which is used for grouping and detecting the parts with the deformation in the preset deviation range according to the specified tolerance;
the step of accurately positioning a detection area is also included between the step of segment detection and the step of grouping and sorting, and the step of accurately positioning the detection area is used for reducing positioning errors caused by pose changes;
the accurate positioning detection area specifically comprises the following steps: and setting two side edges of the head and the tail of the part in the side-view image of the part as two positioning references, and selecting one positioning reference which is closer to the interested area for positioning.
2. The visual inspection method for precision parts according to claim 1, wherein the object image shadow combined inspection step comprises: and acquiring a part side view image of the part and the part which are in contact with each other relative to the reflection of the glass object stage, and acquiring a clearance value of which the size is two times of the actual deformation amount between the reflection corresponding to the part and the part.
3. The visual inspection method for precision parts according to claim 1, wherein when the acquired side view of the part is divided into a plurality of regions of interest, a plurality of regions of interest of a first area are set in a main body portion of the part; setting a plurality of interested areas of a second area on the complex-form part of the part to cover the complex-form part of the whole part; wherein the first area is larger than the second area.
4. The visual inspection method of precision parts according to claim 1, wherein the region of interest is a rectangular region.
5. The precision part visual inspection method of claim 1, wherein each of the regions of interest is inspected using a sub-pixel measurement technique.
6. The visual inspection method for precision parts according to claim 1, wherein the step of grouping and sorting comprises: and detecting the parts with the deformation amount within the preset deviation range in groups by limiting the gap value of each region of interest, wherein each group specifies a tolerance.
7. A precision part vision inspection device, comprising:
a glass stage;
the camera is a side-view camera, the position of a lens of the camera is slightly higher than the part on the glass object stage, and the camera is used for acquiring a digital image of the side-view direction of the part;
the positioning device is used for adjusting the pose of the part;
computer processing means for controlling and processing the camera and the positioning means to perform visual inspection, and receiving feedback information of the camera and the positioning means in real time, and inspecting the part on the glass stage by using the inspection method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010386398.2A CN111678450B (en) | 2020-05-09 | 2020-05-09 | Visual detection method and device for precision part |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010386398.2A CN111678450B (en) | 2020-05-09 | 2020-05-09 | Visual detection method and device for precision part |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111678450A CN111678450A (en) | 2020-09-18 |
| CN111678450B true CN111678450B (en) | 2022-01-11 |
Family
ID=72451802
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010386398.2A Active CN111678450B (en) | 2020-05-09 | 2020-05-09 | Visual detection method and device for precision part |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111678450B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112906167B (en) * | 2021-05-06 | 2021-07-23 | 中国人民解放军国防科技大学 | Assembly precision evaluation method, system and equipment based on dynamic tolerance |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003035681A (en) * | 2001-07-19 | 2003-02-07 | Sony Corp | Appearance inspection apparatus of semiconductor apparatus |
| CN103292701A (en) * | 2013-06-24 | 2013-09-11 | 哈尔滨工业大学 | Machine-vision-based online dimensional measurement method of precise instrument |
| CN103438836A (en) * | 2013-08-23 | 2013-12-11 | 中联重科股份有限公司 | Device, system and method for measuring bending angle of bent piece |
| CN104154885A (en) * | 2014-07-24 | 2014-11-19 | 大连理工大学 | Slight warping detecting method for small-sized annular part |
| CN104296665A (en) * | 2014-09-28 | 2015-01-21 | 苏州镭络视觉技术有限公司 | Workpiece size measuring method and system based on machine vision |
| CN104697456A (en) * | 2013-12-04 | 2015-06-10 | 华闽南配集团股份有限公司 | Method of using optical projection method to determine end gap of piston ring |
| CN107726995A (en) * | 2017-09-28 | 2018-02-23 | 东华大学 | A kind of knitting needle automatic detection device based on machine vision |
| CN108317966A (en) * | 2018-03-19 | 2018-07-24 | 河南科技大学 | A kind of anode guide rod steel claw deformation detection method and device |
| CN109579735A (en) * | 2018-12-03 | 2019-04-05 | 广州沧恒自动控制科技有限公司 | Piston ring contour detecting method for identifying and classifying and its device based on machine vision |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103390277B (en) * | 2013-07-23 | 2016-07-20 | 济南凌空信息科技有限公司 | image analysis method |
| CN108416763B (en) * | 2018-01-22 | 2021-06-29 | 浙江大学 | Image edge processing method for relay measurement |
| CN109606548A (en) * | 2018-10-31 | 2019-04-12 | 沪东中华造船(集团)有限公司 | The localization method that a kind of ship parallel middle body area p-type block is always organized |
-
2020
- 2020-05-09 CN CN202010386398.2A patent/CN111678450B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003035681A (en) * | 2001-07-19 | 2003-02-07 | Sony Corp | Appearance inspection apparatus of semiconductor apparatus |
| CN103292701A (en) * | 2013-06-24 | 2013-09-11 | 哈尔滨工业大学 | Machine-vision-based online dimensional measurement method of precise instrument |
| CN103438836A (en) * | 2013-08-23 | 2013-12-11 | 中联重科股份有限公司 | Device, system and method for measuring bending angle of bent piece |
| CN104697456A (en) * | 2013-12-04 | 2015-06-10 | 华闽南配集团股份有限公司 | Method of using optical projection method to determine end gap of piston ring |
| CN104154885A (en) * | 2014-07-24 | 2014-11-19 | 大连理工大学 | Slight warping detecting method for small-sized annular part |
| CN104296665A (en) * | 2014-09-28 | 2015-01-21 | 苏州镭络视觉技术有限公司 | Workpiece size measuring method and system based on machine vision |
| CN107726995A (en) * | 2017-09-28 | 2018-02-23 | 东华大学 | A kind of knitting needle automatic detection device based on machine vision |
| CN108317966A (en) * | 2018-03-19 | 2018-07-24 | 河南科技大学 | A kind of anode guide rod steel claw deformation detection method and device |
| CN109579735A (en) * | 2018-12-03 | 2019-04-05 | 广州沧恒自动控制科技有限公司 | Piston ring contour detecting method for identifying and classifying and its device based on machine vision |
Non-Patent Citations (3)
| Title |
|---|
| Needle shape quality control by shadowgraphic image processing;Fabrice Mairesse等;《Optical Engineering》;20110228;第1-24页 * |
| 长条状细薄带钩零件变形自动检测系统;朱世根等;《纺织学报》;20201031;第158-163页 * |
| 高精密微小零件尺寸合理性的图像校对方法研究分析;卫星等;《现代电子技术》;20160315;第110-113页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111678450A (en) | 2020-09-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110006905B (en) | Large-caliber ultra-clean smooth surface defect detection device combined with linear area array camera | |
| US5574801A (en) | Method of inspecting an array of solder ball connections of an integrated circuit module | |
| US8855399B2 (en) | System, a method and a computer program product for CAD-based registration | |
| US9599575B2 (en) | System, a method and a computer program product for CAD-based registration | |
| EP1884740A2 (en) | Method and system for sensing the surface shape of a reflective object | |
| JP2003526935A (en) | Election and placement device with improved imaging system | |
| CN110030923B (en) | Connector Pin detection system and detection method thereof | |
| CN112505056A (en) | Defect detection method and device | |
| US20110010122A1 (en) | Calibrating separately located cameras with a double sided visible calibration target for ic device testing handlers | |
| CN113418933B (en) | Flying shooting visual imaging detection system and method for detecting large-size object | |
| KR20180081820A (en) | Registration and design in the die internal inspection Reduction of the noise caused by the peripheral part | |
| CN111678450B (en) | Visual detection method and device for precision part | |
| KR102641333B1 (en) | Die bonding apparatus and manufacturing method of semiconductor device | |
| CN108322736B (en) | Calibration plate and calibration method for calibrating rotation angles of multiple linear array cameras around visual axis | |
| JP4299688B2 (en) | Substrate inspection method and substrate inspection apparatus | |
| CN114071133B (en) | Semiconductor chip detection image imaging method | |
| CN102856214A (en) | Circuit board mounting method | |
| CN114299049A (en) | Detection method and device, electronic equipment and storage medium | |
| CN114994850A (en) | Light path calibration method | |
| JPH0658215B2 (en) | Method and apparatus for inspecting a pattern to be inspected on a semiconductor wafer | |
| US7576769B2 (en) | Inspection device and inspection method | |
| JP5280918B2 (en) | Shape measuring device | |
| US10055849B2 (en) | Image measurement device and controlling method of the same | |
| JP7377655B2 (en) | Die bonding equipment and semiconductor device manufacturing method | |
| CN112763506A (en) | Flaw detection method and device with AOI and AI functions |
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 |