CN108196729A - A kind of finger tip point rapid detection method based on infrared video - Google Patents
A kind of finger tip point rapid detection method based on infrared video Download PDFInfo
- Publication number
- CN108196729A CN108196729A CN201810040023.3A CN201810040023A CN108196729A CN 108196729 A CN108196729 A CN 108196729A CN 201810040023 A CN201810040023 A CN 201810040023A CN 108196729 A CN108196729 A CN 108196729A
- Authority
- CN
- China
- Prior art keywords
- finger tip
- area
- image
- fingertip
- pixel
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/03—Arrangements for converting the position or the displacement of a member into a coded form
- G06F3/041—Digitisers, e.g. for touch screens or touch pads, characterised by the transducing means
- G06F3/042—Digitisers, e.g. for touch screens or touch pads, characterised by the transducing means by opto-electronic means
- G06F3/0425—Digitisers, e.g. for touch screens or touch pads, characterised by the transducing means by opto-electronic means using a single imaging device like a video camera for tracking the absolute position of a single or a plurality of objects with respect to an imaged reference surface, e.g. video camera imaging a display or a projection screen, a table or a wall surface, on which a computer generated image is displayed or projected
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
- G06T7/248—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments involving reference images or patches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
- G06T7/74—Determining position or orientation of objects or cameras using feature-based methods involving reference images or patches
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Collating Specific Patterns (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to a kind of finger tip point rapid detection methods based on infrared video, include the following steps：Current infrared image is obtained, and binary conversion treatment is carried out to the image, obtains fingertip location；Fingertip location is stored, search range is determined according to fingertip location；According to the search range of present frame, in next frame image, corresponding region parts of images is intercepted, obtains subgraph；Binary conversion treatment is carried out to subgraph；Connected domain detection is carried out to the figure after binary conversion treatment, by the connected domain of area maximum, as the corresponding candidate region of finger tip；Candidate area size and shape are analyzed, complete fingertip location screening；By front and rear two frames similarity-rough set, fingertip area is determined；The average value of fingertip area frame image respective coordinates point is calculated, obtains finger tip center.The present invention makes full use of the information of previous frame image, the periphery of the fingertip location in previous frame image, searches for the fingertip location of present frame, so as to improve the accuracy rate of finger tip detection and speed.
Description
Technical field
The present invention relates to projection interaction technique fields, and in particular to a kind of quick side of detection of finger tip point based on infrared video
Method.
Background technology
In interactive system is projected, the detection of fingertip location in infrared image has very important for whole system
Meaning.Fingertip location detection efficiency and quality are how improved, is the key that guarantee system even running.For current finger tip
For detection, most of is based on for single needle image, and the range of detection finger tip is whole image, thus the rate of its detection by
To influence, while also it is highly susceptible to the interference of noise spot.And for this patent, by the finger tip position for combining previous frame
It puts, can largely exclude the interference of the noise spot far from fingertip location.
Invention content
The purpose of the present invention is to provide a kind of finger tip point rapid detection methods based on infrared video, make full use of previous
The fingertip location of present frame is searched for, so as to improve finger tip in the information of frame image, the periphery of the fingertip location in previous frame image
The accuracy rate and speed of detection.
To achieve the above object, present invention employs following technical schemes：
A kind of finger tip point rapid detection method based on infrared video, includes the following steps：
(1) current infrared image is obtained, and binary conversion treatment is carried out to the image, obtains fingertip location；
(2) fingertip location is stored, search range is determined according to fingertip location；
(3) according to the search range of present frame, in next frame image, corresponding region parts of images is intercepted, obtains subgraph；
(4) binary conversion treatment is carried out to subgraph；
(5) connected domain detection is carried out to the figure after binary conversion treatment, the connected domain of area maximum is corresponded to as finger tip
Candidate region；
(6) candidate area size and shape are analyzed, completes fingertip location screening；
(7) by front and rear two frames similarity-rough set, fingertip area is determined；
(8) average value of fingertip area frame image respective coordinates point is calculated, obtains finger tip center.
Further, in step (1), described image binary conversion treatment, using following steps：
(11) search range according to determined by former frame, the corresponding position interception area model in a later frame infrared image
Enclose image；
(12) each pixel of traversal interception range image, if the gray value corresponding to the coordinate of pixel is less than valve
It is worth, then the pixel value 0, otherwise pixel value is 1.
Further, in step (5), the connected domain detection specifically comprises the following steps：
(51) point traverses binary image pixel-by-pixel, if the pixel value of two adjacent pixels is 1, by two pictures
Element is included in same connected domain；
(52) area detecting is carried out to the connected domain of acquisition, if area is less than threshold values, as noise filtering, if area is big
In threshold values, then as the corresponding candidate region of finger tip.
Further, it is described by front and rear two frames similarity-rough set in step (7), fingertip area is determined, using following step
Suddenly：
(71) current frame image is extracted, calculates the Luminance Distribution histogram per frame image；
(72) similarity of the corresponding Luminance Distribution histogram of two field pictures before and after calculating, if similarity is more than threshold values,
For fingertip area, otherwise, the finger tip detection failure of present frame.
As shown from the above technical solution, the finger tip point rapid detection method of the present invention based on infrared video, passes through
Between being detected in infrared image during position, the information of previous frame image, the fingertip location in previous frame image are made full use of
Periphery, the fingertip location of present frame is searched for, so as to improve the accuracy rate of finger tip detection and speed.The present invention passes through to finger tip position
The periphery put scans for, and not only reduces detection range, while calculation amount is significantly reduced, so as to improve efficiency.
Description of the drawings
Fig. 1 is flow chart of the method for the present invention；
Fig. 2 is the method flow diagram of the two frame similarity-rough sets of the present invention.
Specific embodiment
The present invention will be further described below in conjunction with the accompanying drawings：
As shown in Figs. 1-2, a kind of finger tip point rapid detection method based on infrared video, includes the following steps：
S1：Current infrared image, i.e. S are obtained using video camerai(i >=0) frame infrared image, and two are carried out to the image
Value is handled, and obtains fingertip location；
S2：Fingertip location is stored, as SiThe fingertip location of (i >=0) frame, search range is determined according to fingertip location；
Such as with SiIn the infrared image of (i >=0) frame, point centered on fingertip location draws square (length of side is set as 20 pixels),
This square is exactly search range.
S3：According to the search range of present frame, in next frame image, corresponding region parts of images is intercepted, obtains subgraph；
For a new frame image, i.e. Si+1(i >=0) frame infrared image, according to SiThe search range of (i >=0) frame, in Si+1(i
>=0) in frame infrared image, corresponding region parts of images is intercepted, obtains subgraph.
S4：Binary conversion treatment is carried out to subgraph:
S41：According to SiSearch range determined by (i >=0) frame, in Si+1It is corresponding in (i >=0) frame infrared image
Position intercepts out the image of regional extent, is denoted as Pi+1(i≥0)；
S42：To image Pi+1(i >=0) carries out binarization operation, threshold value k be rule of thumb set (for example threshold value is
50), the image after binaryzation is denoted as Bi+1(i≥0).Due to image Pi+1The size of (i >=0) is far smaller than image Si+1(i
>=0), therefore to image Pi+1(i >=0) carries out binarization operation, relative to image Si+1(i >=0) carries out binarization operation, calculates
Amount is substantially reduced.
Binaryzation principle is as follows：Traverse image Pi+1Each pixel of (i >=0), such as the corresponding gray scale of fruit dot (x, y)
Value, less than threshold value k, is then set to 0 by the pixel value, and otherwise pixel value is set to 1, pixel point value 0, then the pixel is shown as black
Color, pixel point value 1, then the pixel be shown as white.
S5：Connected domain detection is carried out to the figure after binary conversion treatment, the connected domain of area maximum is corresponded to as finger tip
Candidate region；
Point traversal binary image B pixel-by-pixeli+1(i >=0), if if its pixel value of adjacent two pixels is all 1,
Then the two pixels are included in into same connected domain, can finally obtain multiple connected domains.Two pixels are adjacent to be defined as follows
Shown in table, for pixel x, pixel 1-8 is its adjacent pixel.
| 1 | 2 | 3 |
| 4 | x | 5 |
| 6 | 7 | 8 |
Area detecting is carried out for the multiple connected domains obtained in upper step, area is less than 10 pixels (empirical value)
Connected domain filtered out.Since the connected domain area that these are filtered out is too small, then it will not be fingertip area, be noise region.
All connected domains are traversed, by the connected domain of area maximum, as the corresponding candidate region of finger tip, are denoted as Hi+1(i≥0)。
S6：Candidate area size and shape are analyzed, complete fingertip location screening；
Although obtain region Hi+1(i >=0), but it not necessarily represents finger tip, then also needs to carry out size and shape to it
Shape is analyzed, so as to obtain further analysis result；
Analysis for size：Calculate candidate region Hi+1The extraneous rectangle of (i >=0), if the length and width of extraneous rectangle are big
In threshold value (20 pixels), then it is assumed that be not fingertip area (fingertip area can not possibly be excessive).Otherwise, continue next step
Judge.
Shape analysis：The length-width ratio of fingertip area is to meet certain proportion requirement, therefore, if candidate region Hi+1(i
>=0) length-width ratio of boundary rectangle is more than 1.5, then can filter out.If less than 1.5, then retain.For present frame Si+1(i
>=0) for, if there is no the candidate region met the requirements, then it is assumed that finger has been moved off touching medium, and finger tip disappears.
S7：By front and rear two frames similarity-rough set, fingertip area is determined；
After the analysis of shape and size size is completed, if there is satisfactory candidate region, it is also necessary to candidate
The picture material in region is compared, and by analyzing its similarity, could finally determine that finger tip detection is completed, by using brightness
The form of histogram is compared, specific as follows：
S71：Extract SiIn (i >=0) frame image, the region parts of images of finger tip is denoted as Ti(i≥0)；
S72：Extract Si+1In (i >=0) frame image, candidate region Hi+1(i >=0) institute to corresponding region parts of images,
It is denoted as Ti+1(i≥0)；
S73：For Ti(i >=0) calculates its Luminance Distribution histogram, is denoted as H1, and brightness histogram is set as 16
Grade, wherein, H1(i) it represents for TiAll pixels point in (i >=0), pixel value size is in [(i-1) * 16, i*16-1]
All pixels point number, 0≤i≤15；
S74：For Ti+1(i >=0) equally calculates its Luminance Distribution histogram, is denoted as H2, and brightness histogram is set as
16 grades, wherein, H2(i) it represents for Ti+1All pixels point in (i >=0), pixel value size is in [(i-1) * 16, i*
16-1] in all pixels point number, 0≤i≤15；
S75：The similarity dist of two histograms is calculated, as shown in formula (1).
S76：If Euclidean distance dist is less than threshold value 30 (empirical value), then it is assumed that Ti(i >=0) and Ti+1(i >=0) is phase
As, i.e. Ti+1It is fingertip area that (i >=0) is really, otherwise, Ti(i >=0) and Ti+1(i >=0) is dissimilar, then the finger of present frame
Point detection failure.
S8：The average value of fingertip area frame image respective coordinates point is calculated, obtains finger tip center.
In Si+1In (i >=0) frame infrared image, zoning Ti+1In (i >=0), the average value of all coordinate points is asked for,
Then the average value can be as the center (x, y) of finger tip, and formula is such as shown in (2)-(3).Wherein, n represents region Ti+1In (i >=0),
The number of all coordinate pairs, XiRepresent the abscissa of each of which coordinate pair, YiRepresent the ordinate of each of which coordinate pair.Finally, originally
Patent just completes the Overall Steps of entire finger tip positioning.
Embodiment described above is only that the preferred embodiment of the present invention is described, not to the model of the present invention
It encloses and is defined, under the premise of design spirit of the present invention is not departed from, those of ordinary skill in the art are to the technical side of the present invention
The various modifications and improvement that case is made should all be fallen into the protection domain that claims of the present invention determines.
Claims (4)
1. a kind of finger tip point rapid detection method based on infrared video, which is characterized in that include the following steps：
（1）Current infrared image is obtained, and binary conversion treatment is carried out to the image, obtains fingertip location；
（2）Fingertip location is stored, search range is determined according to fingertip location；
（3）According to the search range of present frame, in next frame image, corresponding region parts of images is intercepted, obtains subgraph；
（4）Binary conversion treatment is carried out to subgraph；
（5）Connected domain detection is carried out to the figure after binary conversion treatment, by the connected domain of area maximum, as the corresponding time of finger tip
Favored area；
（6）Candidate area size and shape are analyzed, complete fingertip location screening；
（7）By front and rear two frames similarity-rough set, fingertip area is determined；
（8）The average value of fingertip area frame image respective coordinates point is calculated, obtains finger tip center.
2. the finger tip point rapid detection method according to claim 1 based on infrared video, it is characterised in that：The two-value
Change is handled, using following steps：
（11）The search range according to determined by former frame, the corresponding position interception area areal map in a later frame infrared image
Picture；
（12）Each pixel of traversal interception range image, if the gray value corresponding to the coordinate of pixel is less than threshold values,
The pixel value 0, otherwise pixel value is 1.
3. the finger tip point rapid detection method according to claim 2 based on infrared video, it is characterised in that：Step（5）
In, the connected domain detection specifically comprises the following steps：
（51）If the pixel value of two adjacent pixels is 1, which is drawn for point traversal binary image pixel-by-pixel
Enter in same connected domain；
（52）Area detecting is carried out to the connected domain of acquisition, if area is less than threshold values, as noise filtering, if area is more than valve
Value, then as the corresponding candidate region of finger tip.
4. the finger tip point rapid detection method according to claim 1 based on infrared video, it is characterised in that：Step（7）
In, it is described by front and rear two frames similarity-rough set, fingertip area is determined, using following steps：
（71）Current frame image is extracted, calculates the Luminance Distribution histogram per frame image；
（72）The similarity of the corresponding Luminance Distribution histogram of two field pictures before and after calculating, if similarity is more than threshold values, to refer to
Sharp region, otherwise, the finger tip detection failure of present frame.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810040023.3A CN108196729A (en) | 2018-01-16 | 2018-01-16 | A kind of finger tip point rapid detection method based on infrared video |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810040023.3A CN108196729A (en) | 2018-01-16 | 2018-01-16 | A kind of finger tip point rapid detection method based on infrared video |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108196729A true CN108196729A (en) | 2018-06-22 |
Family
ID=62589361
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810040023.3A Pending CN108196729A (en) | 2018-01-16 | 2018-01-16 | A kind of finger tip point rapid detection method based on infrared video |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108196729A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113052148A (en) * | 2021-05-10 | 2021-06-29 | 读书郎教育科技有限公司 | Method for improving positioning jitter of flat fingertip |
| CN113362390A (en) * | 2021-06-21 | 2021-09-07 | 武汉理工大学 | Rapid circular target positioning video processing method based on ellipse detection |
| CN113676654A (en) * | 2020-05-14 | 2021-11-19 | 武汉Tcl集团工业研究院有限公司 | Image interception method, device and equipment and computer readable storage medium |
| WO2022222188A1 (en) * | 2021-04-19 | 2022-10-27 | 深圳市华星光电半导体显示技术有限公司 | Display panel and photosensitive display device |
| CN115345854A (en) * | 2022-08-16 | 2022-11-15 | 中国水利水电科学研究院 | Water level identification method based on multi-region search |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101621615A (en) * | 2009-07-24 | 2010-01-06 | 南京邮电大学 | Self-adaptive background modeling and moving target detecting method |
| CN102339390A (en) * | 2011-09-16 | 2012-02-01 | 天津市亚安科技股份有限公司 | Method and system for updating target template of video monitoring system |
| US20130101170A1 (en) * | 2011-10-21 | 2013-04-25 | Industry-University Cooperation Foundation Hanyang University | Method of image processing and device therefore |
| CN103077384A (en) * | 2013-01-10 | 2013-05-01 | 北京万集科技股份有限公司 | Method and system for positioning and recognizing vehicle logo |
| CN103200394A (en) * | 2013-04-07 | 2013-07-10 | 南京理工大学 | Target image real time transmission and tracking method based on digital signal processor (DSP) and target image real time transmission and tracking device based on digital signal processor (DSP) |
| CN103413138A (en) * | 2013-07-18 | 2013-11-27 | 航天恒星科技有限公司 | Method for detecting point target in infrared image sequence |
| CN103544472A (en) * | 2013-08-30 | 2014-01-29 | Tcl集团股份有限公司 | Processing method and processing device based on gesture images |
| CN103778786A (en) * | 2013-12-17 | 2014-05-07 | 东莞中国科学院云计算产业技术创新与育成中心 | Traffic violation detection method based on significant vehicle part model |
| CN103942542A (en) * | 2014-04-18 | 2014-07-23 | 重庆卓美华视光电有限公司 | Human eye tracking method and device |
| CN105049670A (en) * | 2015-07-03 | 2015-11-11 | 西安理工大学 | Method for hiding and extracting false-proof information in halftoning printing images |
| CN107563985A (en) * | 2017-08-31 | 2018-01-09 | 成都空御科技有限公司 | A kind of detection method of infrared image moving air target |
-
2018
- 2018-01-16 CN CN201810040023.3A patent/CN108196729A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101621615A (en) * | 2009-07-24 | 2010-01-06 | 南京邮电大学 | Self-adaptive background modeling and moving target detecting method |
| CN102339390A (en) * | 2011-09-16 | 2012-02-01 | 天津市亚安科技股份有限公司 | Method and system for updating target template of video monitoring system |
| US20130101170A1 (en) * | 2011-10-21 | 2013-04-25 | Industry-University Cooperation Foundation Hanyang University | Method of image processing and device therefore |
| CN103077384A (en) * | 2013-01-10 | 2013-05-01 | 北京万集科技股份有限公司 | Method and system for positioning and recognizing vehicle logo |
| CN103200394A (en) * | 2013-04-07 | 2013-07-10 | 南京理工大学 | Target image real time transmission and tracking method based on digital signal processor (DSP) and target image real time transmission and tracking device based on digital signal processor (DSP) |
| CN103413138A (en) * | 2013-07-18 | 2013-11-27 | 航天恒星科技有限公司 | Method for detecting point target in infrared image sequence |
| CN103544472A (en) * | 2013-08-30 | 2014-01-29 | Tcl集团股份有限公司 | Processing method and processing device based on gesture images |
| CN103778786A (en) * | 2013-12-17 | 2014-05-07 | 东莞中国科学院云计算产业技术创新与育成中心 | Traffic violation detection method based on significant vehicle part model |
| CN103942542A (en) * | 2014-04-18 | 2014-07-23 | 重庆卓美华视光电有限公司 | Human eye tracking method and device |
| CN105049670A (en) * | 2015-07-03 | 2015-11-11 | 西安理工大学 | Method for hiding and extracting false-proof information in halftoning printing images |
| CN107563985A (en) * | 2017-08-31 | 2018-01-09 | 成都空御科技有限公司 | A kind of detection method of infrared image moving air target |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113676654A (en) * | 2020-05-14 | 2021-11-19 | 武汉Tcl集团工业研究院有限公司 | Image interception method, device and equipment and computer readable storage medium |
| WO2022222188A1 (en) * | 2021-04-19 | 2022-10-27 | 深圳市华星光电半导体显示技术有限公司 | Display panel and photosensitive display device |
| US11895899B2 (en) | 2021-04-19 | 2024-02-06 | Shenzhen China Star Optoelectronics Semiconductor Display Technology Co., Ltd. | Display panel and photosensitive display device |
| CN113052148A (en) * | 2021-05-10 | 2021-06-29 | 读书郎教育科技有限公司 | Method for improving positioning jitter of flat fingertip |
| CN113052148B (en) * | 2021-05-10 | 2023-09-29 | 读书郎教育科技有限公司 | Method for improving positioning shake of flat fingertip |
| CN113362390A (en) * | 2021-06-21 | 2021-09-07 | 武汉理工大学 | Rapid circular target positioning video processing method based on ellipse detection |
| CN115345854A (en) * | 2022-08-16 | 2022-11-15 | 中国水利水电科学研究院 | Water level identification method based on multi-region search |
| CN115345854B (en) * | 2022-08-16 | 2023-04-18 | 中国水利水电科学研究院 | Water level identification method based on multi-region search |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108196729A (en) | A kind of finger tip point rapid detection method based on infrared video | |
| CN109409366B (en) | Distorted image correction method and device based on angular point detection | |
| CN107705288B (en) | Infrared video detection method for dangerous gas leakage under strong interference of pseudo-target motion | |
| CN105205488B (en) | Word area detection method based on Harris angle points and stroke width | |
| CN102236784A (en) | Screen area detection method and system | |
| CN110598610A (en) | Target significance detection method based on neural selection attention | |
| CN104598907B (en) | Lteral data extracting method in a kind of image based on stroke width figure | |
| CN104794479B (en) | This Chinese detection method of natural scene picture based on the transformation of local stroke width | |
| CN107589850A (en) | A kind of recognition methods of gesture moving direction and system | |
| CN111161313B (en) | Multi-target tracking method and device in video stream | |
| WO2018233205A1 (en) | Method for detecting pedestrians in image by using gaussian penalty | |
| CN106530310B (en) | A kind of pedestrian count method and device based on the identification of human body overhead | |
| KR20130105952A (en) | Method and apparatus for vehicle license plate recognition | |
| CN111160291B (en) | Human eye detection method based on depth information and CNN | |
| CN101515325A (en) | Character extracting method in digital video based on character segmentation and color cluster | |
| CN104463138B (en) | The text positioning method and system of view-based access control model structure attribute | |
| CN103218605A (en) | Quick eye locating method based on integral projection and edge detection | |
| CN108537787B (en) | Quality judgment method for face image | |
| CN110321769A (en) | A kind of more size commodity on shelf detection methods | |
| CN106663322A (en) | Identifying features | |
| CN103903256B (en) | Depth estimation method based on relative height-depth clue | |
| CN108921813A (en) | Unmanned aerial vehicle detection bridge structure crack identification method based on machine vision | |
| CN109409356A (en) | A kind of multi-direction Chinese print hand writing detection method based on SWT | |
| KR20110128529A (en) | Apparatus and method for tracking non-rigid object based on shape and feature information | |
| CN103866551B (en) | Based on the fabric skew quick detecting method of machine vision |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 230000 Yafu Park, Juchao Economic Development Zone, Chaohu City, Hefei City, Anhui Province Applicant after: ANHUI HUISHI JINTONG TECHNOLOGY Co.,Ltd. Address before: 102, room 602, C District, Hefei National University, Mount Huangshan Road, 230000 Hefei Road, Anhui, China Applicant before: ANHUI HUISHI JINTONG TECHNOLOGY Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180622 |