CN107085707A - A kind of license plate locating method based on Traffic Surveillance Video - Google Patents
A kind of license plate locating method based on Traffic Surveillance Video Download PDFInfo
- Publication number
- CN107085707A CN107085707A CN201710243966.1A CN201710243966A CN107085707A CN 107085707 A CN107085707 A CN 107085707A CN 201710243966 A CN201710243966 A CN 201710243966A CN 107085707 A CN107085707 A CN 107085707A
- Authority
- CN
- China
- Prior art keywords
- image
- license plate
- surveillance video
- traffic surveillance
- method based
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- 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
- G06V10/30—Noise filtering
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/625—License plates
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Processing (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a kind of license plate locating method based on Traffic Surveillance Video, specifically include 1, the original image in Traffic Surveillance Video is changed, original image is converted to gray level image, and original color space is converted to HSV space;2nd, the image after conversion is pre-processed, 3rd, rim detection is carried out to pretreated image, 4th, on the basis of rim detection, integrated use local thresholding method, Global thresholding and dynamic thresholding method, divide the image into black, white dichromatism region according to the relation of pixel value and threshold value and realize image binaryzation;5th, after image binaryzation, using the expansion in mathematical morphology, area filling and etching operation, realize that region merging technique and noise are further rejected;6th, floor projection and upright projection are carried out successively to the edge image detected, determines the border up and down of car plate;7th, projection carries out License Plate after confirming by SVMs.The problems such as ambient noise pattern similar with background that the present invention can overcome prior art to exist is disturbed, characters on license plate is discontinuous.
Description
Technical field
The invention belongs to field of video processing, more particularly to a kind of license plate locating method based on Traffic Surveillance Video.
Background technology
With the economic development and improvement of people's living standards, car ownership also rapidly increases, and gives urban transportation band
Carry out lot of challenges, therefore the license auto-recognition system based on intelligent image treatment theory is obtained more and more with analytical technology
Concern.License Plate is as the vital link of Car license recognition, and its accuracy rate and recall rate are directly connected to follow-up ring
The work of section or even the performance of whole system.
Common license plate locating method has the method based on image texture characteristic, the method based on conversion, based on artificial god
Method through network, method based on mathematical morphology etc..Method based on image texture characteristic usually requires first to select suitable
Edge detection operator, and be aided with image preprocessing and could obtain preferable result;Method based on conversion is often difficult to tackle
The situation that car plate frame is obscured or deformed, it is also difficult to eliminate the influence of noise;Method based on artificial neural network has preferable
Fault-tolerance and learning ability, but training need time it is often longer, convergence and convergence rate all cannot be guaranteed;It is based on
The method of mathematical morphology is difficult to the problems such as processing character is connected, character is not connected in itself.
The content of the invention
Goal of the invention:For problems of the prior art, the present invention, which provides one kind, to overcome prior art to exist
The interference of ambient noise similar with background pattern, the License Plate based on Traffic Surveillance Video the problems such as characters on license plate is discontinuous
Method.
Technical scheme:In order to solve the above technical problems, the present invention provides a kind of License Plate based on Traffic Surveillance Video
Method, is comprised the following steps that:
The first step:Original image in Traffic Surveillance Video is changed, original image is converted to gray level image, original
Color space is converted to HSV space;
Second step:Image after conversion is pre-processed,
3rd step:Rim detection is carried out to pretreated image,
4th step:On the basis of rim detection, integrated use local thresholding method, Global thresholding and dynamic thresholding method,
Black, white dichromatism region is divided the image into according to the relation of pixel value and threshold value and realizes image binaryzation;
5th step:After image binaryzation, operated using the expansion in mathematical morphology, area filling and etching operation, it is real
Existing region merging technique and noise are further rejected;
6th step:Floor projection and upright projection are carried out successively to the edge image detected, the upper bottom left of car plate is determined
Right margin;
7th step:Projection carries out License Plate after confirming by SVMs.
Further, the step of being pre-processed in the second step to the image after conversion is as follows:Utilize traffic monitoring
The characteristic of video eliminates camera background, and noise spot is further eliminated to gained video image application prefilter.
Further, rim detection described in the 3rd step is calculated especially by gradient operator, Roberts operators, Sobel
Son, Prewitt operators or Canny operators are realized to suppress background characteristics of low-frequency.
Further, the gray-scale map to generation is needed during original image being converted into gray level image in the first step
As carrying out gray scale stretching processing.
Further, the specific steps of camera background are eliminated in the characteristic using Traffic Surveillance Video in the second step
It is as follows:Take above some two field pictures disposably determined;Calculate after the difference for obtaining each image and background image, then enter
Row Gauss pre filtering operation.
Further, the step of carrying out License Plate by SVMs in the 7th step is as follows:Specification positive example sample
Originally with the size of negative data, off-line training is carried out using SVMs, training is applied to pending video, realization after finishing
License Plate.
Compared with prior art, the advantage of the invention is that:
The present invention first, has merged the method based on image texture characteristic, the method based on artificial neural network, based on number
The advantage of this three classes method of morphologic method is learned, License Plate result can more rapidly, be more reliably obtained;Second, utilize
The inherent characteristicses of Traffic Surveillance Video eliminate background, further improve the speed and robustness of system.
Brief description of the drawings
Fig. 1 is overview flow chart of the invention.
Embodiment
Below against accompanying drawing, the present invention is described in further detail with reference to embodiment.It is emphasized that under
State it is bright be merely exemplary, the scope being not intended to be limiting of the invention and its application.
License plate locating method proposed by the present invention based on Traffic Surveillance Video comprises the following steps:
(1) image is changed:Original image in Traffic Surveillance Video is converted into gray level image, original color space is turned
It is changed to HSV space.Wherein, in the conversion of original image to gray level image, in order to avoid because expose it is incorrect caused by ash
Level concentration problem is spent, may also need to carry out gray scale stretching processing to the gray level image of generation.
By taking common yuv video form as an example, Y is luminance component (profile of representative image) here, and U and V are colourity point
Measure (color of representative image).According to existing rgb space, Y value can be calculated as follows out:
Y=0.299*R+0.587*G+0.114*B
Weights in formula derive from the vision mode of human eye, and the more sensitive green component G weights of human eye are larger, and human eye compared with
Then weights are smaller by insensitive blue B.
When it is implemented, in order to avoid causing gray level to be concentrated because exposure is incorrect, can be using following steps to generation
Gray level image carry out gray scale stretching processing:
Step 1:Since gray level 0, histogram is searched for gray level augment direction, if slope absolute value is more than 20,
This gray level is saved as into fmin。
Step 2:Since gray level 255, reduce direction search histogram to gray level, if slope absolute value is more than
20, this gray level is saved as into fmax。
Step 3:The result of gray scale stretching is as follows:
Here f (x, y), g (x, y) represent value of the image after present image and stretching at coordinate (x, y) place respectively.
(2) image preprocessing:Camera background is eliminated using the characteristic of Traffic Surveillance Video, to gained video image application
Gauss pre-filtering further eliminates noise spot.Wherein, camera background eliminates the characteristic that make use of monitor video, takes above some
Two field picture is disposably determined;Calculate after the difference for obtaining each image and background image, then carry out Gauss pre-filtering behaviour
Make.When it is implemented, preceding 100 width image is can use to Traffic Surveillance Video generates background frames, Gauss pre-filtering as training set
The window that can select 5 × 5 is carried out.
(3) rim detection:With gradient operator, Roberts operators, Sobel operators, Prewitt operators or Canny operators come
Suppress background characteristics of low-frequency.Wherein, gradient operator first-order difference approximate calculation:
Here
Interference in order to avoid floor projection to horizontal boundary, can only detect the border of vertical direction:
(4) image binaryzation:On the basis of rim detection, integrated use local thresholding method, Global thresholding and dynamic
Threshold method, black, white dichromatism region is divided the image into according to the relation of pixel value and threshold value, so that each pixel is only with a bit
Represent.
When it is implemented, assuming that f (n) is the pixel number that grey scale change value is n, n_max is maximum intensity change value,
Binary-state threshold can be then determined with following false code, wherein r is default percentage, and grey scale change is worth into larger one
Divide edge as the binaryzation edge of subsequent step.
(5) mathematical morphology is operated:On the basis of binaryzation, filled out successively using the expansion in mathematical morphology, region
Fill and etching operation, realize that region merging technique and noise are further rejected.When it is implemented, the color of area filling is according to research pair
As and set.By taking the pony car of China's standard as an example, blueness should be filled to extract car plate.
(6) projection confirms:Floor projection and upright projection are carried out successively to the edge image detected, the upper of car plate is determined
Lower right boundary.
When it is implemented, the step of floor projection is as follows:
Step 1:The number of boundary point in being represented with f (j) per a line, wherein j is the corresponding height of the row, is regarded as water
Flat drop shadow curve.
Step 2:Enter line width to above-mentioned floor projection curve smooth for 5 sliding window, smooth algorithm is on virgin curve
Each location of pixels, take 5 × 1 window average as correspondence position on new curve value, if new curve is g (j).
Step 3:For each position on new curve, if the average of its 5 × 1 neighborhood is not less than 16, down=j, j
=j+1, skips to the 4th step;Otherwise j=j+1, continues the 3rd step.
Step 4:For each position on new curve, if the average of its 5 × 1 neighborhood is less than 16, up=j, skip to
5th step;Otherwise j=j+1, continues the 4th step.
Step 5:If up-down>20, then projection terminates, and otherwise j=up, jumps to the 3rd step.
The step of upright projection, is as follows:
Step 1:The number of boundary point in each row is represented with v (i), wherein i is the corresponding width of the row, is regarded as hanging down
Straight drop shadow curve.
Step 2:Enter line width to above-mentioned upright projection curve smooth for 11 sliding window, smooth algorithm is on virgin curve
Each location of pixels, take 11 × 1 window average as correspondence position on new curve value, if new curve is w (j).
Step 3:For each position on new curve, if the average of its 11 × 1 neighborhood not less than 3 and its right side 50 ×
The average of 1 neighborhood is nor less than 3, then left=i, i=i+1, skip to the 4th step;Otherwise i=i+1, continues the 3rd step.
Step 4:For each position on new curve, if the average of its 11 × 1 neighborhood is less than 3 and its left side 50 × 1
The average of neighborhood is again smaller than 3, then right=i, skips to the 5th step;Otherwise i=i+1, continues the 4th step.
Step 5:If right-left<5* (up-down), then projection terminates, and otherwise i=left, jumps to the 3rd step.
(7) SVMs is positioned:The size of specification positive example sample and negative data, is carried out offline using SVMs
Training, training is applied to pending video after finishing, and realizes License Plate.
In a word, license plate locating method proposed by the present invention combines the method based on image texture characteristic, based on artificial god
The advantage of this three classes method of method through network, the method based on mathematical morphology, and combine consolidating for urban transportation monitor video
There is feature to carry out the elimination of camera background image, it is more efficient, more reliably obtain License Plate result, it is follow-up car
Board is split and Recognition of License Plate Characters link has tamped basis.
Embodiments of the invention is the foregoing is only, is not intended to limit the invention.All principles in the present invention
Within, the equivalent substitution made should be included in the scope of the protection.The content category that the present invention is not elaborated
In prior art known to this professional domain technical staff.
Claims (6)
1. a kind of license plate locating method based on Traffic Surveillance Video, it is characterised in that comprise the following steps that:
The first step:Original image in Traffic Surveillance Video is changed, original image is converted to gray level image, original color
Space is converted to HSV space;
Second step:Image after conversion is pre-processed,
3rd step:Rim detection is carried out to pretreated image,
4th step:On the basis of rim detection, integrated use local thresholding method, Global thresholding and dynamic thresholding method, according to
The relation of pixel value and threshold value divides the image into black, white dichromatism region and realizes image binaryzation;
5th step:After image binaryzation, operated using the expansion in mathematical morphology, area filling and etching operation, realize area
Domain merges and noise is further rejected;
6th step:Floor projection and upright projection are carried out successively to the edge image detected, the side up and down of car plate is determined
Boundary;
7th step:Projection carries out License Plate after confirming by SVMs.
2. a kind of license plate locating method based on Traffic Surveillance Video according to claim 1, it is characterised in that described
The step of being pre-processed in two steps to the image after conversion is as follows:The camera back of the body is eliminated using the characteristic of Traffic Surveillance Video
Scape, noise spot is further eliminated to gained video image application prefilter.
3. a kind of license plate locating method based on Traffic Surveillance Video according to claim 1, it is characterised in that described
Rim detection described in three steps is calculated especially by gradient operator, Roberts operators, Sobel operators, Prewitt operators or Canny
Son is realized to suppress background characteristics of low-frequency.
4. a kind of license plate locating method based on Traffic Surveillance Video according to claim 1, it is characterised in that described
Need to carry out gray scale stretching processing to the gray level image of generation during original image is converted into gray level image in one step.
5. a kind of license plate locating method based on Traffic Surveillance Video according to claim 1, it is characterised in that described
In two steps comprising the following steps that for camera background is being eliminated using the characteristic of Traffic Surveillance Video:Take above some two field pictures enter
Row is disposable to be determined;Calculate after the difference for obtaining each image and background image, then carry out Gauss pre filtering operation.
6. a kind of license plate locating method based on Traffic Surveillance Video according to claim 1, it is characterised in that described
The step of carrying out License Plate by SVMs in seven steps is as follows:The size of specification positive example sample and negative data, is utilized
SVMs carries out off-line training, and training is applied to pending video after finishing, realizes License Plate.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710243966.1A CN107085707A (en) | 2017-04-14 | 2017-04-14 | A kind of license plate locating method based on Traffic Surveillance Video |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710243966.1A CN107085707A (en) | 2017-04-14 | 2017-04-14 | A kind of license plate locating method based on Traffic Surveillance Video |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107085707A true CN107085707A (en) | 2017-08-22 |
Family
ID=59612073
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710243966.1A Pending CN107085707A (en) | 2017-04-14 | 2017-04-14 | A kind of license plate locating method based on Traffic Surveillance Video |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107085707A (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107895492A (en) * | 2017-10-24 | 2018-04-10 | 河海大学 | A kind of express highway intelligent analysis method based on conventional video |
CN108876784A (en) * | 2018-06-27 | 2018-11-23 | 清华大学 | A kind of image processing method and device removing flat work pieces connecting component |
CN109523527A (en) * | 2018-11-12 | 2019-03-26 | 北京地平线机器人技术研发有限公司 | The detection method in dirty region, device and electronic equipment in image |
CN109559518A (en) * | 2018-12-10 | 2019-04-02 | 安徽四创电子股份有限公司 | A kind of novel intelligent traffic block port based on structured image recognizer |
CN109993167A (en) * | 2019-04-03 | 2019-07-09 | 刘西 | A kind of safety inspection method of construction vehicle |
CN110660039A (en) * | 2019-10-10 | 2020-01-07 | 杭州雄迈集成电路技术有限公司 | Multi-frame weighted wide dynamic image processing method |
CN111369570A (en) * | 2020-02-24 | 2020-07-03 | 成都空御科技有限公司 | Multi-target detection tracking method for video image |
CN111696084A (en) * | 2020-05-20 | 2020-09-22 | 平安科技(深圳)有限公司 | Cell image segmentation method, cell image segmentation device, electronic equipment and readable storage medium |
CN112017157A (en) * | 2020-07-21 | 2020-12-01 | 中国科学院西安光学精密机械研究所 | Method for identifying damage point in optical element laser damage threshold test |
CN111696084B (en) * | 2020-05-20 | 2024-05-31 | 平安科技(深圳)有限公司 | Cell image segmentation method, device, electronic equipment and readable storage medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060120602A1 (en) * | 2004-12-03 | 2006-06-08 | Bei Tang | Character segmentation method and apparatus |
CN101246551A (en) * | 2008-03-07 | 2008-08-20 | 北京航空航天大学 | Fast license plate locating method |
CN101325690A (en) * | 2007-06-12 | 2008-12-17 | 上海正电科技发展有限公司 | Method and system for detecting human flow analysis and crowd accumulation process of monitoring video flow |
CN103324958A (en) * | 2013-06-28 | 2013-09-25 | 浙江大学苏州工业技术研究院 | License plate locating method based on projection method and SVM under complex background |
CN105303153A (en) * | 2014-07-23 | 2016-02-03 | 中兴通讯股份有限公司 | Vehicle license plate identification method and apparatus |
CN105354570A (en) * | 2015-10-15 | 2016-02-24 | 深圳市捷顺科技实业股份有限公司 | Method and system for precisely locating left and right boundaries of license plate |
CN106529592A (en) * | 2016-11-07 | 2017-03-22 | 湖南源信光电科技有限公司 | License plate recognition method based on mixed feature and gray projection |
-
2017
- 2017-04-14 CN CN201710243966.1A patent/CN107085707A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060120602A1 (en) * | 2004-12-03 | 2006-06-08 | Bei Tang | Character segmentation method and apparatus |
CN101325690A (en) * | 2007-06-12 | 2008-12-17 | 上海正电科技发展有限公司 | Method and system for detecting human flow analysis and crowd accumulation process of monitoring video flow |
CN101246551A (en) * | 2008-03-07 | 2008-08-20 | 北京航空航天大学 | Fast license plate locating method |
CN103324958A (en) * | 2013-06-28 | 2013-09-25 | 浙江大学苏州工业技术研究院 | License plate locating method based on projection method and SVM under complex background |
CN105303153A (en) * | 2014-07-23 | 2016-02-03 | 中兴通讯股份有限公司 | Vehicle license plate identification method and apparatus |
CN105354570A (en) * | 2015-10-15 | 2016-02-24 | 深圳市捷顺科技实业股份有限公司 | Method and system for precisely locating left and right boundaries of license plate |
CN106529592A (en) * | 2016-11-07 | 2017-03-22 | 湖南源信光电科技有限公司 | License plate recognition method based on mixed feature and gray projection |
Non-Patent Citations (4)
Title |
---|
刘小飞: "基于边缘检测和形态学的车牌定位", 《高新技术产业发展》 * |
吕昆 等: "一种基于OpenCV的车牌识别方法", 《软件导刊》 * |
王一丁 等: "《数字图像处理》", 31 August 2015, 西安电子科技大学出版社 * |
贺光: "基于粗糙集合模糊SVM的车牌识别技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107895492A (en) * | 2017-10-24 | 2018-04-10 | 河海大学 | A kind of express highway intelligent analysis method based on conventional video |
CN108876784B (en) * | 2018-06-27 | 2021-07-30 | 清华大学 | Image processing method and device for removing connecting part of planar workpiece |
CN108876784A (en) * | 2018-06-27 | 2018-11-23 | 清华大学 | A kind of image processing method and device removing flat work pieces connecting component |
CN109523527A (en) * | 2018-11-12 | 2019-03-26 | 北京地平线机器人技术研发有限公司 | The detection method in dirty region, device and electronic equipment in image |
CN109559518A (en) * | 2018-12-10 | 2019-04-02 | 安徽四创电子股份有限公司 | A kind of novel intelligent traffic block port based on structured image recognizer |
CN109993167A (en) * | 2019-04-03 | 2019-07-09 | 刘西 | A kind of safety inspection method of construction vehicle |
CN110660039A (en) * | 2019-10-10 | 2020-01-07 | 杭州雄迈集成电路技术有限公司 | Multi-frame weighted wide dynamic image processing method |
CN110660039B (en) * | 2019-10-10 | 2022-04-22 | 杭州雄迈集成电路技术股份有限公司 | Multi-frame weighted wide dynamic image processing method |
CN111369570A (en) * | 2020-02-24 | 2020-07-03 | 成都空御科技有限公司 | Multi-target detection tracking method for video image |
CN111369570B (en) * | 2020-02-24 | 2023-08-18 | 成都空御科技有限公司 | Multi-target detection tracking method for video image |
CN111696084A (en) * | 2020-05-20 | 2020-09-22 | 平安科技(深圳)有限公司 | Cell image segmentation method, cell image segmentation device, electronic equipment and readable storage medium |
CN111696084B (en) * | 2020-05-20 | 2024-05-31 | 平安科技(深圳)有限公司 | Cell image segmentation method, device, electronic equipment and readable storage medium |
CN112017157A (en) * | 2020-07-21 | 2020-12-01 | 中国科学院西安光学精密机械研究所 | Method for identifying damage point in optical element laser damage threshold test |
CN112017157B (en) * | 2020-07-21 | 2023-04-11 | 中国科学院西安光学精密机械研究所 | Method for identifying damage point in optical element laser damage threshold test |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107085707A (en) | A kind of license plate locating method based on Traffic Surveillance Video | |
CN103400150B (en) | A kind of method and device that road edge identification is carried out based on mobile platform | |
US7747071B2 (en) | Detecting and correcting peteye | |
US8154591B2 (en) | Eyelid opening level determination device and computer readable medium storing computer program thereof | |
CN103679733B (en) | A kind of signal lamp image processing method and its device | |
US8295593B2 (en) | Method of detecting red-eye objects in digital images using color, structural, and geometric characteristics | |
CN105828065B (en) | A kind of video pictures overexposure detection method and device | |
JP5975598B2 (en) | Image processing apparatus, image processing method, and program | |
CN103310422B (en) | Obtain the method and device of image | |
CN105069801A (en) | Method for preprocessing video image based on image quality diagnosis | |
CN105303160A (en) | Method for detecting and tracking vehicles at night | |
CN109086724A (en) | A kind of method for detecting human face and storage medium of acceleration | |
WO2018233637A1 (en) | Video processing method and apparatus, electronic device, and storage medium | |
CN110751635B (en) | Oral cavity detection method based on interframe difference and HSV color space | |
CN102610104B (en) | Onboard front vehicle detection method | |
CN105447491A (en) | Signboard image binaryzation method and device | |
CN107730487A (en) | A kind of image detecting method and device | |
CN111126191B (en) | Iris image acquisition method, iris image acquisition device and storage medium | |
CN110501339B (en) | Cloth cover positioning method in complex environment | |
JP2012023572A (en) | White balance coefficient calculating device and program | |
CN103729624A (en) | Photometry method and system based on skin color recognition | |
CN106384103A (en) | Vehicle face recognition method and device | |
CN111192280A (en) | Method for detecting optic disc edge based on local feature | |
CN110633705A (en) | Low-illumination imaging license plate recognition method and device | |
US11625886B2 (en) | Storage medium storing program, training method of machine learning model, and image generating apparatus |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170822 |
|
RJ01 | Rejection of invention patent application after publication |