CN108647713A - Embryo's Boundary Recognition and laser trace approximating method - Google Patents
Embryo's Boundary Recognition and laser trace approximating method Download PDFInfo
- Publication number
- CN108647713A CN108647713A CN201810435730.2A CN201810435730A CN108647713A CN 108647713 A CN108647713 A CN 108647713A CN 201810435730 A CN201810435730 A CN 201810435730A CN 108647713 A CN108647713 A CN 108647713A
- Authority
- CN
- China
- Prior art keywords
- embryo
- laser
- path
- boundary
- approximating method
- 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.)
- Granted
Links
- 210000001161 mammalian embryo Anatomy 0.000 title claims abstract description 46
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000005457 optimization Methods 0.000 claims abstract description 12
- 238000000605 extraction Methods 0.000 claims abstract description 6
- 239000011159 matrix material Substances 0.000 claims description 13
- 230000009467 reduction Effects 0.000 claims description 10
- 238000006073 displacement reaction Methods 0.000 claims description 8
- 210000002308 embryonic cell Anatomy 0.000 claims description 7
- 238000011946 reduction process Methods 0.000 claims description 5
- 210000004027 cell Anatomy 0.000 claims description 4
- 238000003708 edge detection Methods 0.000 claims description 3
- 238000003698 laser cutting Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 claims description 2
- 238000005259 measurement Methods 0.000 claims description 2
- 230000005611 electricity Effects 0.000 claims 1
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 239000012528 membrane Substances 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 210000000170 cell membrane Anatomy 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000032692 embryo implantation Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000003631 expected effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004080 punching Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/181—Segmentation; Edge detection involving edge growing; involving edge linking
-
- 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
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- 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
- G06T2207/30004—Biomedical image processing
- G06T2207/30044—Fetus; Embryo
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Image Processing (AREA)
Abstract
The present invention provides a kind of embryo's Boundary Recognitions and laser trace approximating method, include the following steps：(A1) pattern image of the micro-image of the embryo of extraction acquisition；(A2) pattern image is analyzed, to obtain the geometrical edge boundary line of the embryo；(A3) presetting laser boring path and the geometrical edge boundary line are compared, to decide whether to carry out path optimization；If so, entering step (A4)；If not, utilizing presetting laser boring path；(A4) re-optimization laser trace path avoids injuring the embryo.The present invention have many advantages, such as to assess laser path to the damage risk of embryo, reset laser boring track.
Description
Technical field
The present invention relates to embryo operations, more particularly to embryo's Boundary Recognition and laser trace approximating method.
Background technology
In supplementary reproduction system, in the operation of hatched blastocyst implantation, user is needed first when using laser rupture of membranes instrument
The position for needing to drill is determined on MIcrosope image, and suitable laser boring rail is then chosen on cell oolemma
Mark, this laser boring track are shown as a narrow curve over the display, and human eye would become hard to whether distinguish other laser aperture
The boundary of embryonic cell film can be touched, laser trace selects to be easy that expected effect is not achieved farther out from cell, selects too close
It is easy to damage in cell membrane again, embryonic cell sample is precious, and operation failure will be unable to restore, therefore leans on the default punching of human eye completely
The uncertain factor of track is more, this also considerably increases the operational risk of experiment.It is directed to the assessment of this risk at present and answers
To upper specific embodiment not yet.
Invention content
For the deficiency for solving in above-mentioned prior art, the present invention provides a kind of embryo's Boundary Recognition and laser traces
Approximating method can assess damage risk of the laser path to embryo, and energy re-optimization claims the path of best laser boring.
The purpose of the present invention is what is be achieved through the following technical solutions：
A kind of embryo's Boundary Recognition and laser trace approximating method, embryo's Boundary Recognition and laser trace approximating method
Including：
(A1) pattern image of the micro-image of the embryo of extraction acquisition；
(A2) pattern image is analyzed, to obtain the geometrical edge boundary line of the embryo；
(A3) presetting laser boring path and the geometrical edge boundary line are compared, to decide whether to carry out path
Optimization；
If so, entering step (A4)；
If not, utilizing presetting laser boring path；
(A4) re-optimization laser trace path avoids injuring the embryo.
According to above-mentioned embryo's Boundary Recognition and laser trace approximating method, optionally, embryo's Boundary Recognition with swash
Optical track mark approximating method is further comprising the steps of：
(A5) pixel coordinate value after optimization is decomposed to the angle of rotation measurement for being converted into motor on two-dimensional movement platform and offset
Amount.
It is optionally, special in extraction in step (A1) according to above-mentioned embryo's Boundary Recognition and laser trace approximating method
Before levying figure, also need to carry out noise reduction process to the micro-image of the embryo of acquisition.
According to above-mentioned embryo's Boundary Recognition and laser trace approximating method, it is preferable that the specific side of the noise reduction process
Formula is：
Noise reduction is carried out to the black white image pixel of acquisition using Wiener Filter Method；
Wherein I indicates that picture element matrix, N indicate that horizontal pixel is wide, and M indicates that longitudinal pixel is wide, and μ indicates average value, the expression sides δ
Difference；Result A (i, j) after noise reduction is：
According to above-mentioned embryo's Boundary Recognition and laser trace approximating method, it is preferable that in step (A1), the feature
The extracting mode of figure is：
(A11) contrast enhances：The all pixels point on micro-image is counted using histogram, then to all
The gray value of pixel be multiplied by a drawing coefficient k, to enhance the contrast of image, keep black more black, white is whiter；
(A12) gradient detects：Feature extraction is carried out to image pixel point, convolution is carried out using sobel convolution collecting images
Processing；The obtained overall situation is combined using Laplace formula to the convolution results in the convolution results and the directions y on the directions x again
Features of edge gradient maps：
According to above-mentioned embryo's Boundary Recognition and laser trace approximating method, it is preferable that in step (A2), the geometry
The acquisition pattern of boundary line is：
Gray value by the gray value in the image obtained after edge detection less than the pixel of threshold value is all reset, from
And obtain geometrical edge boundary line.
According to above-mentioned embryo's Boundary Recognition and laser trace approximating method, it is preferable that in step (A3), the comparison
Mode be：
(A31) laser hits path is inputted in software interface figure layer, according to the aperture of the laser boring of setting and
The boundary coordinate matrix of laser trace is calculated in track pixel point coordinates；
(A32) boundary coordinate matrix is compared with profile diagram boundary, if intersection can be detected, needs optimization road
Diameter.
According to above-mentioned embryo's Boundary Recognition and laser trace approximating method, it is preferable that in step (A4), path optimization
Mode is：
An immediate geometric path track is taken along cell boundaries line selection；Pixel value on the path meets：
Indicate the Grads threshold set, this threshold value the big more can reduce what embryonic cell was damaged in laser cutting track
Risk.
According to above-mentioned embryo's Boundary Recognition and laser trace approximating method, it is preferable that in step (A5),
If the coordinate of existing laser point is (x on screens1, ys1), coordinates of targets is (xs2, ys2) the then converted conversion of matrix A -1
It is to show coordinate for (x to motor coordinatem1, ym1), coordinates of targets is (xm2, ym2), two motor displacement distances are respectively | xm2-xm1|、|
ym2-ym1|, direction depends on (x2-x1)、(y2-y1) positive negativity, as be it is negative if be left/lower direction, canonical is right/upper direction.
Compared with prior art, the device have the advantages that being：
1. in laser rupture of membranes instrument, which can assist user to set laser hits path, and assessment laser road automatically
Damage risk of the diameter to embryonic cell；
2. pair generating the paths of best laser hits with this scheme energy re-optimization of the track of damage risk, use is reduced
The difficulty in laser boring path is arranged in family, reduces time cost, while improving the success rate of experiment.
Description of the drawings
With reference to attached drawing, the disclosure will be easier to understand.Skilled addressee readily understands that be：This
A little attached drawings are used only for the technical solution illustrated the present invention, and are not intended to and are construed as limiting to protection scope of the present invention.
In figure：
Fig. 1 is the flow chart of embryo's Boundary Recognition and laser trace approximating method according to the ... of the embodiment of the present invention.
Specific implementation mode
Fig. 1 and following description describe the present invention optional embodiment with instruct those skilled in the art how to implement and
Reproduce the present invention.In order to instruct technical solution of the present invention, some conventional aspects are simplified or have been omitted.Those skilled in the art answer
The understanding is originated from the modification of these embodiments or replacement will within the scope of the invention.Under those skilled in the art should understand that
Stating feature can combine in various ways to form multiple modifications of the present invention.The invention is not limited in following optional as a result,
Embodiment, and be only limited by the claims and their equivalents.
Embodiment：
Fig. 1 schematically illustrates the flow of the embryo's Boundary Recognition and laser trace approximating method of the embodiment of the present invention 1
Figure, as shown in Figure 1, embryo's Boundary Recognition includes the following steps with laser trace approximating method：
(A1) image of embryo, minimalist configuration requirement of the camera to computer are collected using Watec black and white cameras：
Four core 1.8GHZ, 1G memory of Pentium, 80GB hard disks；Support USB3.0 functions；
Noise reduction process：Noise reduction process is carried out to the black white image that camera collects, a pictures are taken out first, to picture
In all pixels gray value average and variance：
Noise reduction is carried out to the black white image pixel of acquisition using Wiener Filter Method；
Wherein I indicates that picture element matrix, N indicate that horizontal pixel is wide, and M indicates that longitudinal pixel is wide, and μ indicates average value, the expression sides δ
Difference；Result A (i, j) after noise reduction is：
Pattern image is extracted：
(A11) contrast enhances：Contrast enhancement processing is done to the image after noise reduction, using histogram to the figure after noise reduction
As upper all pixels point gray value is counted, then the gray value (gray value 0-255) of all pixels is multiplied by
One drawing coefficient k keeps black more black to enhance the contrast of image, and white is whiter；
K is enhancing coefficient, and A (i, j) is the picture element matrix after noise reduction, and B (i, j) is the enhanced picture element matrix of contrast；
To reduce the calculation amount of image procossing below, then grey scale pixel value is divided into totally 10 groups, and respectively [0-10), [10-
20), [20-30) ...；
(A12) gradient detects：Process of convolution is carried out to the image after stretching using convolution kernel；Convolutional calculation can regard one as
The process of a weighted sum makes each pixel of image area carry out convolutional calculation to following two-dimentional operator respectively：
Again to the directions x on convolution results and the directions y on convolution results combined and obtain using Laplace formula
Global features of edge gradient maps：
(A2) pixel by the gray value in the image obtained after edge detection less than a certain threshold value is all disposed,
Obtain most rational embryonic cell graph edge boundary line；
(A3) trajectory path of a laser boring is drawn in software interface figure layer, which is one continuous bent
Line；
Trajectory coordinates are compared with the boundary line pixel coordinate obtained in step (A2), if detecting and boundary pixel
Whether point has coincidence；
If there is coincidence, enter step (A4)；
If without coincidence, then it is assumed that preset laser boring trajectory path is reasonable, will directly execute step (A6)；
(A4) an immediate geometric path track is chosen along embryo boundary line；Pixel value on the path meets：
Indicate the Grads threshold set, this threshold value the big more can reduce what embryonic cell was damaged in laser cutting track
Risk；
(A5) pixel coordinate on the laser boring trajectory path that will eventually determine takes out, by transformational relation matrix by this
The coordinate of a little pixels is converted into the coordinate points on laser displacement platform；
If it is (xs1, ys1) that track, which shows coordinate, on screen, coordinates of targets is that (xs2, ys2) then converted matrix A -1 is converted
To motor coordinate be existing coordinate it is (xm1, ym1), coordinates of targets is (xm2, ym2), and two motor displacement distances are respectively | xm2-
Xm1 |, | ym2-ym1 |, direction depends on the positive negativity of x2-x1, y2-y1, as be it is negative if be left/lower direction, canonical for the right side/on
Direction
(A6) in SCM system, the rotation that displacement distance obtains stepper motor by displacement angle conversion formula again walks
Number
N is stepper motor steps, and L is motor displacement distance, △ s be the corresponding displacement platform of single stepping angle movement away from
From.
Claims (9)
1. a kind of embryo's Boundary Recognition and laser trace approximating method, it is characterised in that：Embryo's Boundary Recognition and laser rail
Mark approximating method includes the following steps：
(A1) pattern image of the micro-image of the embryo of extraction acquisition；
(A2) pattern image is analyzed, to obtain the geometrical edge boundary line of the embryo；
(A3) presetting laser boring path and the geometrical edge boundary line are compared, to decide whether that progress path is excellent
Change；
If so, entering step (A4)；
If not, utilizing presetting laser boring path；
(A4) re-optimization laser trace path avoids injuring the embryo.
2. embryo's Boundary Recognition according to claim 1 and laser trace approximating method, it is characterised in that：The embryo side
Boundary's identification is further comprising the steps of with laser trace approximating method：
(A5) pixel coordinate value after optimization is decomposed to the angle of rotation measurement and offset for being converted into motor on two-dimensional movement platform.
3. embryo's Boundary Recognition according to claim 1 and laser trace approximating method, it is characterised in that：In step (A1)
In, before extracting pattern image, also need to carry out noise reduction process to the micro-image of the embryo of acquisition.
4. embryo's Boundary Recognition according to claim 3 and laser trace approximating method, it is characterised in that：At the noise reduction
The concrete mode of reason is：
Noise reduction is carried out to the black white image pixel of acquisition using Wiener Filter Method；
Wherein I indicates that picture element matrix, N indicate that horizontal pixel is wide, and M indicates that longitudinal pixel is wide, and μ indicates that average value, δ indicate variance；
Result A (i, j) after noise reduction is：
5. embryo's Boundary Recognition according to claim 1 and laser trace approximating method, it is characterised in that：In step (A1)
In, the extracting mode of the pattern image is：
(A11) contrast enhances：The all pixels point on micro-image is counted using histogram, then to all pictures
The gray value of vegetarian refreshments is multiplied by a drawing coefficient k, to enhance the contrast of image, keeps black more black, and white is whiter；
(A12) gradient detects：Feature extraction is carried out to image pixel point, process of convolution is carried out using sobel convolution collecting images；
Obtained global edge is combined using Laplace formula to the convolution results in the convolution results and the directions y on the directions x again
Gradient map：
6. embryo's Boundary Recognition according to claim 5 and laser trace approximating method, it is characterised in that：In step (A2)
In, the acquisition pattern in the geometrical edge boundary line is：
Gray value by the gray value in the image obtained after edge detection less than the pixel of threshold value is all reset, to
To geometrical edge boundary line.
7. embryo's Boundary Recognition according to claim 1 and laser trace approximating method, it is characterised in that：In step (A3)
In, the mode of the comparison is：
(A31) laser hits path is inputted in software interface figure layer, according to the aperture and track of the laser boring of setting
The boundary coordinate matrix of laser trace is calculated in pixel point coordinates；
(A32) boundary coordinate matrix is compared with profile diagram boundary, if intersection can be detected, needs path optimizing.
8. embryo's Boundary Recognition according to claim 1 and laser trace approximating method, it is characterised in that：In step (A4)
In, path optimization's mode is：
An immediate geometric path track is taken along cell boundaries line selection；Pixel value on the path meets：
Indicate the Grads threshold set, this threshold value the big more can reduce the risk that embryonic cell is damaged in laser cutting track.
9. embryo's Boundary Recognition according to claim 2 and laser trace approximating method, it is characterised in that：In step (A5)
In,
If the coordinate of existing laser point is (x on screens1, ys1), coordinates of targets is (xs2, ys2) then converted matrix A -1 be transformed into electricity
Machine coordinate is that existing coordinate is (xm1, ym1), coordinates of targets is (xm2, ym2), two motor displacement distances are respectively | xm2-xm1|、|ym2-
ym1|, direction depends on (x2-x1)、(y2-y1) positive negativity, as be it is negative if be left/lower direction, canonical is right/upper direction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810435730.2A CN108647713B (en) | 2018-05-07 | 2018-05-07 | Embryo boundary identification and laser track fitting method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810435730.2A CN108647713B (en) | 2018-05-07 | 2018-05-07 | Embryo boundary identification and laser track fitting method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108647713A true CN108647713A (en) | 2018-10-12 |
| CN108647713B CN108647713B (en) | 2021-04-02 |
Family
ID=63749605
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810435730.2A Active CN108647713B (en) | 2018-05-07 | 2018-05-07 | Embryo boundary identification and laser track fitting method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108647713B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112656542A (en) * | 2020-12-17 | 2021-04-16 | 南京师范大学 | Method for assisting blastocyst incubation at specific site |
| CN112734782A (en) * | 2021-01-25 | 2021-04-30 | 中科和光（天津）应用激光技术研究所有限公司 | Laser path planning visual algorithm |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6724938B1 (en) * | 1999-12-16 | 2004-04-20 | Ge Medical Systems Global Technology Company, Llc | Boundary line detecting method and apparatus, image processing method and apparatus, non-boundary line detecting method and apparatus |
| CN102175625A (en) * | 2010-11-29 | 2011-09-07 | 樊潮 | Method for identifying cancer cells |
| CN102509067A (en) * | 2011-09-22 | 2012-06-20 | 西北工业大学 | Detection method for lane boundary and main vehicle position |
| CN104408711A (en) * | 2014-10-30 | 2015-03-11 | 西北工业大学 | Multi-scale region fusion-based salient region detection method |
| CN105374039A (en) * | 2015-11-16 | 2016-03-02 | 辽宁大学 | Monocular image depth information estimation method based on contour acuity |
| CN105844655A (en) * | 2016-04-19 | 2016-08-10 | 南京工程学院 | Laser line stripe edge extraction method |
| CN107498052A (en) * | 2017-09-22 | 2017-12-22 | 华中科技大学 | A kind of load balancing for more laser SLM building mortions scans manufacturing process |
| CN107578403A (en) * | 2017-08-22 | 2018-01-12 | 浙江大学 | The stereo image quality evaluation method of binocular view fusion is instructed based on gradient information |
-
2018
- 2018-05-07 CN CN201810435730.2A patent/CN108647713B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6724938B1 (en) * | 1999-12-16 | 2004-04-20 | Ge Medical Systems Global Technology Company, Llc | Boundary line detecting method and apparatus, image processing method and apparatus, non-boundary line detecting method and apparatus |
| CN102175625A (en) * | 2010-11-29 | 2011-09-07 | 樊潮 | Method for identifying cancer cells |
| CN102509067A (en) * | 2011-09-22 | 2012-06-20 | 西北工业大学 | Detection method for lane boundary and main vehicle position |
| CN104408711A (en) * | 2014-10-30 | 2015-03-11 | 西北工业大学 | Multi-scale region fusion-based salient region detection method |
| CN105374039A (en) * | 2015-11-16 | 2016-03-02 | 辽宁大学 | Monocular image depth information estimation method based on contour acuity |
| CN105844655A (en) * | 2016-04-19 | 2016-08-10 | 南京工程学院 | Laser line stripe edge extraction method |
| CN107578403A (en) * | 2017-08-22 | 2018-01-12 | 浙江大学 | The stereo image quality evaluation method of binocular view fusion is instructed based on gradient information |
| CN107498052A (en) * | 2017-09-22 | 2017-12-22 | 华中科技大学 | A kind of load balancing for more laser SLM building mortions scans manufacturing process |
Non-Patent Citations (3)
| Title |
|---|
| CHRISTOPHER YEE WONG等: ""Automation and Optimization of Multipulse Laser Zona Drilling of Mouse Embryos During Embryo Biopsy"", 《IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING》 * |
| CHRISTOPHER YEE WONG等: "《2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)》", 5 November 2015 * |
| 李永强等: ""基于车载LiDAR数据的道路边界精细提取"", 《河南理工大学学报(自然科学版)》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112656542A (en) * | 2020-12-17 | 2021-04-16 | 南京师范大学 | Method for assisting blastocyst incubation at specific site |
| CN112656542B (en) * | 2020-12-17 | 2024-05-10 | 南京师范大学 | Method for hatching blastula assisted by specific sites |
| CN112734782A (en) * | 2021-01-25 | 2021-04-30 | 中科和光（天津）应用激光技术研究所有限公司 | Laser path planning visual algorithm |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108647713B (en) | 2021-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021238030A1 (en) | Water level monitoring method for performing scale recognition on the basis of partitioning by clustering | |
| JP6347815B2 (en) | Method, apparatus and device for detecting lane boundaries | |
| EP3358298B1 (en) | Building height calculation method and apparatus, and storage medium | |
| CN103824066B (en) | A kind of licence plate recognition method based on video flowing | |
| RU2601185C2 (en) | Method, system and computer data medium for face detection | |
| CN104794421B (en) | A kind of positioning of QR codes and recognition methods | |
| EP3859593A1 (en) | Vehicle feature acquisition method and device | |
| US8055016B2 (en) | Apparatus and method for normalizing face image used for detecting drowsy driving | |
| CN104700072B (en) | Recognition methods based on lane line historical frames | |
| CN106971185B (en) | License plate positioning method and device based on full convolution network | |
| CN113486828B (en) | Image processing method, device, equipment and storage medium | |
| EP3036730A1 (en) | Traffic light detection | |
| CN105457908B (en) | The sorting method for rapidly positioning and system of small size glass panel based on monocular CCD | |
| CN109426814A (en) | A kind of positioning of the specific plate of invoice picture, recognition methods, system, equipment | |
| US10916013B2 (en) | Method of segmentation and annotation of images | |
| CN111353961B (en) | Document curved surface correction method and device | |
| CN109409378A (en) | A kind of digitalized processing method of Nahsi Dongba Confucian classics | |
| US20200134326A1 (en) | Advanced driver assistance system and method | |
| CN104346621A (en) | Method and device for creating eye template as well as method and device for detecting eye state | |
| CN108647713A (en) | Embryo's Boundary Recognition and laser trace approximating method | |
| CN105023002A (en) | Vehicle logo positioning method based on active vision | |
| CN104537627B (en) | A kind of post-processing approach of depth image | |
| WO2020001631A1 (en) | Visual camera-based method for identifying edge of self-shadowing object, device, and vehicle | |
| US10692230B2 (en) | Document imaging using depth sensing camera | |
| CN112434640B (en) | Method, device and storage medium for determining rotation angle of document image |
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 | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: West side of 1st floor, 1st floor, Building A, No. 288 Jingu Middle Road (East), Yinzhou District, Ningbo City, Zhejiang Province, 315000 Patentee after: CHINA INNOVATION INSTRUMENT Co.,Ltd. Country or region after: China Address before: Room 304, D Building, Kexin Building, 655 Xueshi Road, Yinzhou District, Ningbo City, Zhejiang Province, 315000 Patentee before: CHINA INNOVATION INSTRUMENT Co.,Ltd. Country or region before: China |