CN107918750A - A kind of adaptive fingerprint image method of adjustment - Google Patents

A kind of adaptive fingerprint image method of adjustment Download PDF

Info

Publication number
CN107918750A
CN107918750A CN201610875713.1A CN201610875713A CN107918750A CN 107918750 A CN107918750 A CN 107918750A CN 201610875713 A CN201610875713 A CN 201610875713A CN 107918750 A CN107918750 A CN 107918750A
Authority
CN
China
Prior art keywords
finger
fingerprint image
data
value
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
Application number
CN201610875713.1A
Other languages
Chinese (zh)
Inventor
程志毅
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Fengyu Technology Co., Ltd
Original Assignee
Shenzhen Ruiwei Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen Ruiwei Technology Co Ltd filed Critical Shenzhen Ruiwei Technology Co Ltd
Priority to CN201610875713.1A priority Critical patent/CN107918750A/en
Publication of CN107918750A publication Critical patent/CN107918750A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/12—Fingerprints or palmprints
    • G06V40/1347—Preprocessing; Feature extraction
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/34—Smoothing or thinning of the pattern; Morphological operations; Skeletonisation

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Human Computer Interaction (AREA)
  • Collating Specific Patterns (AREA)
  • Image Analysis (AREA)

Abstract

A kind of adaptive fingerprint image method of adjustment provided by the invention, including：Before the not upper finger of S1, user, the histogram information of existing empty background image is first preserved, obtains number threshold value and the characteristic point information that background just judges.After S2, the upper finger of user, statistics with histogram is carried out to fingerprint image, and piecemeal processing is carried out to fingerprint image.S3, substitute into characteristic point information, and smoothing operation is carried out to whole fingerprint image.S4, storage smoothing processing after upper finger as a result, judge finger type.S5, after having judged finger type, according to the finger type of judgement, classify fingerprint image, completes data statistics.The present invention need not dispatch from the factory correction, can accomplish real-time matching, can effectively solve sensor surface has situations such as foreign matter, finger is not clean；Parameter can follow user's finger to change because of Four seasons change and finger dry and wet degree；Using the fingerprint image after the method for the present invention, background is uniform, and fingerprint image effect is apparent.

Description

A kind of adaptive fingerprint image method of adjustment
Technical field
The present invention relates to fingerprint image process field, more particularly to a kind of adaptive fingerprint image method of adjustment.
Background technology
With the popularization that fingerprint recognition is applied, high performance fingerprint recognition system needs accurate and quickly adapts to various answer With environment and the characteristic information that takes the fingerprint.But existing most Acquisition Instruments are caused in fingerprint-collecting process due to various environmental factors In would generally introduce noise, cause fingerprint background unclean, noise can seriously affect later image processing, minutiae extraction Deng so as to influence fingerprint application effect.In order to improve the accuracy of Finger print characteristic abstract, generally when dispatching from the factory, detected by AGC The inconsistency of sensor surface image block, by calculating suitable parameter after digital algorithm calibration one by one, uploads to MCU progress Storage, transfers use again after the power is turned on every time.The prior art needs to do single background correction, and speed is slow, influences volume production speed, and Situation of dispatching from the factory is excessively preferable, it is impossible to adapts to the particularity of user environment.After dispatching from the factory, parameter constant, so the prior art is not The situation for causing finger Drought-wet change big because of Four seasons change can be matched well.
The content of the invention
In order to overcome problems of the prior art, this patent provides a kind of adaptive fingerprint image method of adjustment, Including：
Before the not upper finger of S1, user, the histogram information of existing empty background image is first preserved, obtains the straight of background just judgement Square figure number threshold value and image characteristic point information.
The characteristic point is the maximum point and minimum point of pixel value number；The setting side of the histogram number threshold value Method is the position where the Near The Extreme Point deviation ± 20% in number.
After S2, the upper finger of user, statistics with histogram is carried out to fingerprint image, and piecemeal processing is carried out to fingerprint image.
It is described to fingerprint image carry out piecemeal processing method be：
A1, the image block block that fingerprint image is divided into the size such as N number ofi(i=1,2,3 ... N), to blockiInterior point Carry out wheel and seek minimum Data-Statistics, count the maximum and minimum value of pixel gray value；The N is selected according to fingerprint image size Take.
Described take turns seeks the methods of minimum Data-Statistics and is：Assuming that blockiIn pixel gray value for c, b, a, d, h, g, f, E, wherein a<b<c<d<e<f<g<h；Compare two-by-two, before less be placed on；C first and b compare, b<C, so b and c is exchanged Position；C is compared with a, a<C, so a and c exchanges position；A is again compared with b, a<B, a and b exchange position；And so on, finally All values are arranged according to order from small to large, count the maximum and minimum value of pixel gray value.
A2, the situation in view of sensor array error or abnormal point, the maximum and minimum value counted are cast out Do not have to.
After A3, removal maximum and minimum value, in image block blockiThe remaining fingerprint image picture of (i=1,2,3 ... N) In element value, new maximum DATA_max and minimum value DATA_min are chosen；DATA_max and DATA_min is just sentenced with background Disconnected threshold value is compared, and chooses the image block block for meeting particular decision conditionj(j≦N)；The particular decision condition is： DATA_max>MAX2, or DATA_max<MAX1, or DATA_min>MIN1, or DATA_min<MIN2.
A4, the image block block to meeting particular decision conditionj(j≤N) carries out gain compensation so that maximum DATA_ Max and minimum value DATA_min meet prescribed limit, MAX1<DATA_max<MAX2, and MIN2<DATA_min<MIN1.
A5, calculate and complete all image blocks, ensures all image block blockiThe value of (i=1,2,3 ... N) is described In prescribed limit.
Described MIN1, MIN2, MAX1, MAX2 are the histogram number threshold value that background just judges, wherein MIN1, MIN2 is most Small value number threshold value, MAX1, MAX2 are maximum number threshold value, meet MAX1<MAX2, MIN2<MIN1.
S3, after handling obtained finger print information, substitute into characteristic point information, whole fingerprint image smoothly transported Calculate.
The smoothing operation includes nearby being filtered characteristic point processing mutation value corresponding with valley line is made up；It is described flat The value that the result of sliding processing includes the result of the filtering process of crestal line and valley line makes up.The method of the filtering process includes： The common processing method such as value filtering, medium filtering, gaussian filtering.
The result of smoothing processing, be stored into RAM by S4 according to the form of image block, judges finger type after upper finger.
It is described judge finger type method be：According to statistics with histogram go out as a result, to find out pixel value the largest number of Point position M, is judged with given threshold；When pixel gray value M is more than dry finger threshold value N1, then it is judged as dry finger；Work as picture Vegetarian refreshments gray value M is less than wet finger threshold value N2, then is judged as wet finger；When M is less than N1, and M is more than N2, then is normal finger； The dry finger threshold value N1 and wet finger threshold value N2 are preset according to dry and wet finger characteristic, and N1>N2.The finger type bag Include：Dry finger, wet finger and normal finger.
S5, after having judged finger type, according to the finger type of judgement, classify fingerprint image, completes data system Meter.
A kind of adaptive fingerprint image method of adjustment that this patent provides, without correction of dispatching from the factory, can accomplish real-time matching, Sensor surface can effectively be solved has situations such as foreign matter, finger is not clean.Optimized parameter is selected for each finger, and parameter can be with Change with user's finger because of Four seasons change and finger dry and wet degree.After the adaptive fingerprint method of adjustment of this patent Fingerprint image, background is uniform, and fingerprint image effect is apparent.
Brief description of the drawings
Fig. 1 is the particular flow sheet of the embodiment of the present invention；
Fig. 2 is the uneven fingerprint image of background that the embodiment of the present invention collects；
Fig. 3 is the histogram for the uneven fingerprint image of background that the embodiment of the present invention collects；
Fig. 4 is that the wheel of the embodiment of the present invention seeks the method schematic diagram of minimum Data-Statistics；
Fig. 5 is the method schematic diagram for judging finger type of the embodiment of the present invention, and figure (a) is dry finger histogram, is schemed (b) For wet finger histogram, figure (c) is normal finger histogram；
Fig. 6 is the front and rear comparison diagram of the adaptive fingerprint method of adjustment of the use of the embodiment of the present invention, and figure (a) is unused Fingerprint image design sketch, figure (b) be use after fingerprint image design sketch.
Embodiment
In order to be better understood from the present invention, with reference to instantiation, and referring to the drawings, the present invention is made further detailed Explanation.
As shown in Figure 1, a kind of adaptive fingerprint image method of adjustment, including：
Before the not upper finger of step 1, user, the histogram information of existing empty background image is first preserved, background is obtained and just judges Histogram number threshold value and image characteristic point information.By taking background is uneven as an example, the adaptive fingerprint of this patent is not used During method of adjustment, the uneven fingerprint image of background collected is as shown in Fig. 2, its histogram distribution is as shown in Figure 3.
Characteristic point is the maximum point and minimum point of pixel value number；The method to set up of histogram number threshold value is a Position where several Near The Extreme Point deviations ± 20%.In the present embodiment, it is threshold value-the 20% of number extreme point A MIN2 ,+20% is threshold value MIN1；- the 20% of number extreme point D is threshold value MAX1, and+20% is threshold value MAX2.
In Fig. 3, Gray Histogram value interval range is big, after statistics preserve background just judge threshold value MIN1, MIN2, The positional information of characteristic point in MAX1, MAX2, and figure, for the adjustment parameter after upper finger.In the present embodiment, characteristic point A, D is number maximum point, and B, C are number minimum point.
After step 2, the upper finger of user, statistics with histogram is carried out to fingerprint image, and piecemeal processing is carried out to fingerprint image.
To fingerprint image carry out piecemeal processing method be：
A1, the image block block that fingerprint image is divided into the size such as N number ofi(i=1,2,3 ... N), N is according to fingerprint image Size is chosen.To blockiInterior point carries out wheel and seeks minimum Data-Statistics, counts the maximum and minimum value of pixel gray value. As shown in figure 4, the method that wheel seeks minimum Data-Statistics is：Assuming that blockiIn pixel gray value be c, b, a, d, h, g, f, e, Wherein a<b<c<d<e<f<g<h.Compare two-by-two, before less be placed on.C first and b compare, b<C, so b and c exchanges position Put；C is compared with a, a<C, so a and c exchanges position；A is again compared with b, a<B, a and b exchange position.And so on, final institute Some values are arranged according to order from small to large, count the maximum and minimum value of pixel gray value.
A2, the situation in view of sensor array error or abnormal point, the maximum and minimum value counted are cast out Do not have to.
After A3, removal maximum and minimum value, in image block blockiThe remaining fingerprint image picture of (i=1,2,3 ... N) In element value, new maximum DATA_max and minimum value DATA_min are chosen.DATA_max and DATA_min is just sentenced with background Disconnected threshold value is compared, and chooses the image block block for meeting particular decision conditionj(j≦N).The particular decision condition is： DATA_max>MAX2, or DATA_max<MAX1, or DATA_min>MIN1, or DATA_min<MIN2.
A4, the image block block to meeting particular decision conditionj(j≤N) carries out gain compensation so that maximum DATA_ Max and minimum value DATA_min meet prescribed limit, MAX1<DATA_max<MAX2, and MIN2<DATA_min<MIN1.
A5, calculate and complete all image blocks, ensures all image block blockiThe value of (i=1,2,3 ... N) is providing In the range of.
Wherein, MIN1, MIN2, MAX1, MAX2 are the histogram number threshold value that background just judges, MIN1, MIN2 are minimum It is worth number threshold value, MAX1, MAX2 are maximum number threshold value, meet MAX1<MAX2, MIN2<MIN1.
Step 3, because fingerprint is non-discrete, there is certain continuity, after handling obtained finger print information, generation Enter characteristic point information, smoothing operation is carried out to whole fingerprint image.Characteristic point information is A, B, C, D tetra- in Fig. 3 in the present embodiment The information of a point.Crestal line near characteristic point is undergone mutation, so need nearby to be filtered processing to characteristic point, and it is corresponding Make up the corresponding mutation value of valley line.The method of filtering process includes：The common place such as mean filter, medium filtering, gaussian filtering Reason method.
Step 4, the form storage by value made up to the result of the filtering process of crestal line, valley line etc. according to image block block It is stored in RAM, judges finger type after upper finger.Finger type includes：Dry finger, wet finger and normal finger.
As shown in figure 5, the method for judging finger type is：According to statistics with histogram go out as a result, finding out pixel value number Most point position M, is judged with given threshold.When pixel gray value M is more than dry finger threshold value N1, then it is judged as dry hand Refer to；When pixel gray value M is less than wet finger threshold value N2, then it is judged as wet finger；When M is less than N1, and M is more than N2, then for just Normal finger.Dry finger threshold value N1 and wet finger threshold value N2 are preset according to dry and wet finger characteristic, and N1>N2.
Step 5, after having judged finger type, according to the finger type of judgement, classify fingerprint image, completes data Statistics.Fig. 6 is the front and rear comparison diagram using adaptive fingerprint method of adjustment, and figure (a) is untapped fingerprint image design sketch, It is the fingerprint image design sketch after use to scheme (b).As can be seen that the fingerprint image back of the body of adaptive fingerprint method of adjustment is not used Scape is uneven, and image is from left to right successively from secretly brightening；It is equal using the fingerprint image after adaptive fingerprint method of adjustment, background Even, fingerprint image effect is apparent.
The detailed description and the accompanying drawings of the embodiment of the present invention are only intended to the explanation present invention, rather than limitation by claim and The scope of the present invention that its equivalent defines.

Claims (7)

  1. A kind of 1. adaptive fingerprint image method of adjustment, it is characterised in that including：
    Before the not upper finger of S1, user, the histogram information of existing empty background image is first preserved, obtains the histogram that background just judges Number threshold value and image characteristic point information；
    After S2, the upper finger of user, statistics with histogram is carried out to fingerprint image, and piecemeal processing is carried out to fingerprint image；
    S3, after handling obtained finger print information, substitute into characteristic point information, and smoothing operation is carried out to whole fingerprint image；
    The result of smoothing processing, be stored into RAM by S4 according to the form of image block, judges finger type after upper finger；
    S5, after having judged finger type, according to the finger type of judgement, classify fingerprint image, completes data statistics.
  2. 2. a kind of adaptive fingerprint image method of adjustment according to claim 1, it is characterised in that the characteristic point is The maximum point and minimum point of pixel value number；The method to set up of the histogram number threshold value is attached for the extreme point in number Position where nearly deviation ± 20%.
  3. 3. a kind of adaptive fingerprint image method of adjustment according to claim 1, it is characterised in that described to fingerprint image As the method for carrying out piecemeal processing is：
    A1, the image block block that fingerprint image is divided into the size such as N number ofi(i=1,2,3 ... N), to blockiInterior point carries out Wheel seeks minimum Data-Statistics, counts the maximum and minimum value of pixel gray value；The N chooses according to fingerprint image size；
    A2, the situation in view of sensor array error or abnormal point, the maximum and minimum value counted, which is cast out, not to be had to；
    After A3, removal maximum and minimum value, in image block blockiThe remaining fingerprint image pixel value of (i=1,2,3 ... N) In, choose new maximum DATA_max and minimum value DATA_min；DATA_max and DATA_min and background are just judged Threshold value is compared, and chooses the image block block for meeting particular decision conditionj(j≦N)；The particular decision condition is： DATA_max>MAX2, or DATA_max<MAX1, or DATA_min>MIN1, or DATA_min<MIN2；
    A4, the image block block to meeting particular decision conditionj(j≤N) carry out gain compensation so that maximum DATA_max and Minimum value DATA_min meets prescribed limit, MAX1<DATA_max<MAX2, and MIN2<DATA_min<MIN1；
    A5, calculate and complete all image blocks, ensures all image block blockiThe value of (i=1,2,3 ... N) is in the regulation In the range of；
    Described MIN1, MIN2, MAX1, MAX2 are the histogram number threshold value that background just judges, wherein MIN1, MIN2 is minimum value Number threshold value, MAX1, MAX2 are maximum number threshold value, meet MAX1<MAX2, MIN2<MIN1.
  4. 4. a kind of adaptive fingerprint image method of adjustment according to claim 3, it is characterised in that the wheel seeks minimum The method of Data-Statistics is：Assuming that blockiIn pixel gray value be c, b, a, d, h, g, f, e, wherein a<b<c<d<e<f<g< h；Compare two-by-two, before less be placed on；C first and b compare, b<C, so b and c exchanges position；C is compared with a, a<C, institute Position is exchanged with a and c；A is again compared with b, a<B, a and b exchange position；And so on, final all values are according to from small to large Order arrangement, count the maximum and minimum value of pixel gray value.
  5. A kind of 5. adaptive fingerprint image method of adjustment according to claim 1, it is characterised in that the smoothing operation Including being nearby filtered processing mutation value corresponding with valley line is made up to characteristic point；The result of the smoothing processing includes crestal line Filtering process result and the value that makes up of valley line.
  6. A kind of 6. adaptive fingerprint image method of adjustment according to claim 1, it is characterised in that the judgement finger The method of type is：According to statistics with histogram go out as a result, find out pixel value it is the largest number of point position M, with given threshold carry out Judge；When pixel gray value M is more than dry finger threshold value N1, then it is judged as dry finger；When pixel gray value M is less than wet finger Threshold value N2, then be judged as wet finger；When M is less than N1, and M is more than N2, then is normal finger；The dry finger threshold value N1 and wet hand Refer to threshold value N2 to be preset according to dry and wet finger characteristic, and N1>N2.
  7. A kind of 7. adaptive fingerprint image method of adjustment according to claim 1, it is characterised in that the finger type Including：Dry finger, wet finger and normal finger.
CN201610875713.1A 2016-10-08 2016-10-08 A kind of adaptive fingerprint image method of adjustment Pending CN107918750A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610875713.1A CN107918750A (en) 2016-10-08 2016-10-08 A kind of adaptive fingerprint image method of adjustment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610875713.1A CN107918750A (en) 2016-10-08 2016-10-08 A kind of adaptive fingerprint image method of adjustment

Publications (1)

Publication Number Publication Date
CN107918750A true CN107918750A (en) 2018-04-17

Family

ID=61892179

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610875713.1A Pending CN107918750A (en) 2016-10-08 2016-10-08 A kind of adaptive fingerprint image method of adjustment

Country Status (1)

Country Link
CN (1) CN107918750A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111444486A (en) * 2019-12-31 2020-07-24 深圳贝特莱电子科技股份有限公司 Startup self-adaptive fingerprint parameter initialization method based on android system
CN112685588A (en) * 2020-11-09 2021-04-20 北京达佳互联信息技术有限公司 Resource recommendation method, device, equipment and storage medium
TWI796552B (en) * 2019-12-27 2023-03-21 大陸商敦泰電子(深圳)有限公司 Method and device for fingerprint identification

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050069178A1 (en) * 2001-12-07 2005-03-31 Jon Nysaether Sensor for measurement for wet and dry fingers
CN202748806U (en) * 2012-09-19 2013-02-20 成都方程式电子有限公司 Image gray level information-based finger detection realization architecture
CN103065134A (en) * 2013-01-22 2013-04-24 江苏超创信息软件发展股份有限公司 Fingerprint identification device and method with prompt information
CN105740753A (en) * 2014-12-12 2016-07-06 比亚迪股份有限公司 Fingerprint identification method and fingerprint identification system
CN105912915A (en) * 2016-05-27 2016-08-31 广东欧珀移动通信有限公司 Fingerprint unlocking method and terminal

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050069178A1 (en) * 2001-12-07 2005-03-31 Jon Nysaether Sensor for measurement for wet and dry fingers
CN202748806U (en) * 2012-09-19 2013-02-20 成都方程式电子有限公司 Image gray level information-based finger detection realization architecture
CN103065134A (en) * 2013-01-22 2013-04-24 江苏超创信息软件发展股份有限公司 Fingerprint identification device and method with prompt information
CN105740753A (en) * 2014-12-12 2016-07-06 比亚迪股份有限公司 Fingerprint identification method and fingerprint identification system
CN105912915A (en) * 2016-05-27 2016-08-31 广东欧珀移动通信有限公司 Fingerprint unlocking method and terminal

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
付玉虎: "指纹图像预处理与伪特征点删除算法的研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI796552B (en) * 2019-12-27 2023-03-21 大陸商敦泰電子(深圳)有限公司 Method and device for fingerprint identification
CN111444486A (en) * 2019-12-31 2020-07-24 深圳贝特莱电子科技股份有限公司 Startup self-adaptive fingerprint parameter initialization method based on android system
CN112685588A (en) * 2020-11-09 2021-04-20 北京达佳互联信息技术有限公司 Resource recommendation method, device, equipment and storage medium
CN112685588B (en) * 2020-11-09 2024-05-17 北京达佳互联信息技术有限公司 Resource recommendation method, device, equipment and storage medium

Similar Documents

Publication Publication Date Title
CN116205919B (en) Hardware part production quality detection method and system based on artificial intelligence
CN107918750A (en) A kind of adaptive fingerprint image method of adjustment
CN111192237A (en) Glue coating detection system and method based on deep learning
CN112819772A (en) High-precision rapid pattern detection and identification method
CN111445512B (en) Hub parameter feature extraction method in complex production line background
CN107169979A (en) A kind of method for detecting image edge of improvement Canny operators
CN104537650B (en) Polarity direction determination method and device for aluminum electrolytic capacitor
CN104282027B (en) Circle detecting method based on Hough transformation
CN111539437B (en) Detection and identification method of oracle-bone inscription components based on deep learning
CN109949324B (en) Contour detection method based on non-classical receptive field nonlinear subunit response
CN107967471A (en) A kind of table tool automatic identifying method based on machine vision
CN116934763B (en) Medical rubber plug defect detection method based on visual characteristics
CN110852388A (en) Improved SMOTE algorithm based on K-means
CN117314925B (en) Metal workpiece surface defect detection method based on computer vision
CN114663427B (en) Boiler part size detection method based on image processing
CN115797361B (en) Aluminum template surface defect detection method
CN116310845A (en) Intelligent monitoring system for sewage treatment
CN113781413B (en) Electrolytic capacitor positioning method based on Hough gradient method
CN112329845A (en) Method and device for replacing paper money, terminal equipment and computer readable storage medium
CN110349119B (en) Pavement disease detection method and device based on edge detection neural network
CN117173030A (en) Definition determining method and device for sharpened image
CN109919945A (en) Profile testing method based on the non-linear two sides subunit response of non-classical receptive field
CN112581487B (en) Method for automatically extracting detection area and positioning kernel
CN113379744B (en) Nozzle device surface defect detection method and system based on image processing
CN110909781A (en) Vehicle detection method based on vehicle rearview mirror

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
TA01 Transfer of patent application right

Effective date of registration: 20200508

Address after: 518000 No.103, No.3, Fuyong first industrial village, Zhengcheng 1st Road, Xintian community, Fuhai street, Bao'an District, Shenzhen City, Guangdong Province

Applicant after: Shenzhen Fengyu Technology Co., Ltd

Address before: 518101 Guangdong city of Shenzhen province Baoan District Fuyong street Xintian Road No. 71-6 Funing High-tech Industrial Park building F F301

Applicant before: SHENZHEN ZHIRUIWEI TECHNOLOGY Co.,Ltd.

TA01 Transfer of patent application right
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20180417

WD01 Invention patent application deemed withdrawn after publication