CN110378425A - A kind of method and its system that intelligent image compares - Google Patents
A kind of method and its system that intelligent image compares Download PDFInfo
- Publication number
- CN110378425A CN110378425A CN201910665589.XA CN201910665589A CN110378425A CN 110378425 A CN110378425 A CN 110378425A CN 201910665589 A CN201910665589 A CN 201910665589A CN 110378425 A CN110378425 A CN 110378425A
- Authority
- CN
- China
- Prior art keywords
- image
- rate
- feature vector
- texture feature
- target 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/5862—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using texture
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Image Analysis (AREA)
Abstract
This application discloses method and its system that a kind of intelligent image compares, the method that wherein intelligent image compares, specifically includes the following steps: obtaining target image；Calculate the texture feature vector of target image；The texture feature vector of target image is compared with the texture feature vector of the multiple images in comparison data library, obtains comparing rate；Comparing rate is higher than the image in the comparison data library of specified threshold and forms alternate image set；Compare the spatial relation characteristics vector of each image and target image in alternate image set and obtains relative rate；Relative rate and comparing rate are combined, image comparison rate is obtained.The application can accurately compare the similarity between each image for needing to store in the image and database that authenticate, improve the accuracy rate of comparison.
Description
Technical field
This application involves image domains, and in particular, to a kind of method and its system that intelligent image compares.
Background technique
In the prior art, multiple images are usually stored in the database in advance, the image and database that needs are authenticated
In image be compared, to complete the comparison of image.Further, usually simple during the comparison process in the prior art
The characteristic quantity of image authenticated will be needed to be compared with the characteristic quantity of image in database, if the result compared unanimously if authenticate
Pass through, but this rough control methods easily lead to result occur only part in mistake, such as image it is similar but
A possibility that certification passes through.Therefore a kind of more accurate intelligent image comparison method is needed, the image for accurately authenticating needs
It is compared with the image stored in database, reduces and a possibility that comparison mistake occur.
Summary of the invention
The application's is designed to provide a kind of method and its system that intelligent image compares, and can accurately compare needs
The similarity between each image stored in the image and database of certification, improves the accuracy rate of comparison.
In order to achieve the above objectives, this application provides a kind of methods that intelligent image compares, specifically includes the following steps: obtaining
Obtain target image；Calculate the texture feature vector of target image；It will be in the texture feature vector of target image and comparison data library
The texture feature vectors of multiple images be compared, obtain comparing rate；Comparing rate is higher than in the comparison data library of specified threshold
Image formed alternate image set；Compare the spatial relation characteristics vector of each image and target image in alternate image set
Obtain relative rate；Relative rate and comparing rate are combined, image comparison rate is obtained,
As above, wherein it further include analysis target image before the texture feature vector for calculating target image.
It is as above, wherein according to the luminance information of target object, frequency characteristic information and by each position of target object
Shape, position, size information analyzed.
As above, wherein the texture feature vector of target image is calculated specifically includes the following steps: determining trial zone；It will
Trial zone is set as high-resolution；Texture feature vector is calculated in trial zone；Wherein texture feature vector indicates are as follows:
Wherein L indicates the gray level of image；I, j respectively indicate the gray scale of pixel；D indicates the spatial position between two pixels
Relationship, p2 d(i, j) indicates pixel grey scale i from spatial relation d to square of the probability of pixel grey scale j.
As above, wherein texture feature vector indicates are as follows:
Wherein L indicates the gray level of image；I, j respectively indicate the gray scale of pixel；D indicates the spatial position between two pixels
Relationship, pd(i, j) indicates pixel grey scale i from spatial relation d to the probability of pixel grey scale j, lg expression common logarithm.
As above, wherein carry out the texture feature vector of target image and the texture of the multiple images in comparison data library
Before feature vector compares, multiple images are registered.
As above, wherein include the registration information for collecting multiple images in registration process, includes people in the registration information
The name of object or the code name of object identify or transfer the name of the personage in the registration information or the code name of object.
As above, wherein comparing rate indicates are as follows:Wherein a=1,2,3,4；faIndicate the textural characteristics of target image
Vector, faThe texture feature vector of image in ' expression database.
A kind of intelligent image Compare System, including acquiring unit, vector calculation unit, comparing unit, combining unit；It obtains
Unit, for obtaining target image；Vector calculation unit, for calculating the texture feature vector of target image；Comparing unit is used
It is compared, determines with the texture feature vector of the multiple images in comparison data library in the texture feature vector to target image
Comparing rate, and alternate image set is ultimately formed according to comparing rate；Combining unit, for obtaining relative rate, and by relative rate with
Comparing rate merges to form image comparison rate.
As above, wherein comparing unit specifically includes following submodule: registration module, judgment module, collection modules；Note
Volume module, the registration information for collecting multiple images in advance are registered in the database；Judgment module, for comparing in database
Multiple images and target image similarity degree, judge whether similarity degree is higher than threshold value；Collection modules, if being used for similar journey
Degree is higher than threshold value, then forms alternate image set higher than the image in the database of threshold value.
The application has the advantages that
(1) method and its system that intelligent image provided by the present application compares can accurately compare the image for needing to authenticate
Similarity between each image for storing in database, improves the accuracy rate of comparison.
(2) method and its system that intelligent image provided by the present application compares can not only compare merely target image with
The similarity of image is in database to obtain comparison result, but finally obtains comparison result according to calculating layer by layer, makes to compare
Or authentication result is more accurate.
Detailed description of the invention
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The some embodiments recorded in application can also be obtained according to these attached drawings other for those of ordinary skill in the art
Attached drawing.
Fig. 1 is the method flow diagram compared according to intelligent image provided by the embodiments of the present application；
Fig. 2 is the internal structure chart according to intelligent image Compare System provided by the embodiments of the present application；
Fig. 3 is the inside sub-modular structure figure according to intelligent image Compare System provided by the embodiments of the present application；
Fig. 4 is the another internal sub-modular structure figure according to intelligent image Compare System provided by the embodiments of the present application.
Specific embodiment
Below with reference to the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Ground description, it is clear that described embodiment is some embodiments of the present application, instead of all the embodiments.Based on the application
In embodiment, those skilled in the art's every other embodiment obtained without making creative work, all
Belong to the range of the application protection.
This application involves a kind of intelligent image comparison method and systems.According to the application, it can accurately compare needs and recognize
The similarity between each image stored in the image and database of card, improves the accuracy rate of comparison.
The method flow diagram compared as shown in Figure 1 for intelligent image provided by the present application.
Step S110: target image is obtained.
Specifically, which is the image that the needs inputted are compared or authenticate, and the target image can be
A part in object or person or object, personage.
Step S120: the texture feature vector of target image is calculated.
It specifically, further include analysis target image, such as basis wherein before the texture feature vector of calculating target image
Target object carries out luminance information, frequency characteristic information and carries out shape, position, the size at each position of target object etc.
The information of numeralization is analyzed.Finally judge whether target image is completely able to carry out the calculating of texture feature vector.
Further, if luminance information, frequency characteristic information and by the shape at each position of target object, position, big
The information to quantize such as small reaches normal number value or range, then it is assumed that the target image can further calculate texture spy
Levy vector.Wherein analysis method specifically refers to the prior art.
Specifically, texture feature vector indicates the characteristic of target object.Texture feature vector can be with energy feature, letter
Cease the representations such as entropy, contrast, correlation.The above-mentioned form of expression can represent texture feature vector, wherein target can be calculated
One or more texture feature vectors of image.
Calculate target image texture feature vector specifically includes the following steps:
Step D1: trial zone is determined.
Wherein before determining trial zone, the reception window for receiving target image is divided.
Specifically, window will be received and is divided into several lattices, wherein it is real for choosing target image and its periphery grid
Test area.
Step D2: high-resolution is set by trial zone.
Specifically, the extraction of texture sign is carried out in the data of high-definition picture can make subsequent calculated result more quasi-
Really.
Step D3: texture feature vector is calculated in trial zone.
Specifically, it if calculating energy feature as texture feature vector, can be expressed as:
Wherein, f1Indicate that texture feature vector, L indicate the gray level of image；I, j respectively indicate the gray scale of pixel；D is indicated
Spatial relation between two pixels, pd(i, j) indicates pixel grey scale i from spatial relation d to the general of pixel grey scale j
Rate, lg indicate common logarithm.
If calculating Information Entropy Features as texture feature vector, can be expressed as:
Wherein, f2Indicate that texture feature vector, L indicate the gray level of image；I, j respectively indicate the gray scale of pixel；D is indicated
Spatial relation between two pixels, pd(i, j) indicates pixel grey scale i from spatial relation d to the general of pixel grey scale j
Rate, lg indicate common logarithm.
If calculating contrast metric as texture feature vector, can be expressed as:
Wherein f3Indicate that texture feature vector, n indicate the quantity of the grid divided, L indicates the gray level of image；I, j points
Not Biao Shi pixel gray scale；D indicates the spatial relation between two pixels, pd(i, j) indicates pixel grey scale i from spatial position
Probability of the relationship d to pixel grey scale j.
If calculating correlation as texture feature vector, can be expressed as:
Wherein in formula four, f4Indicate texture feature vector,
Specifically, one or more of formula one, two, three, four can be used as texture feature vector, can distinguish table
Show, uniformity, complexity, clarity and the linear relationship of target image.
Step S130: by the textural characteristics of the multiple images in the texture feature vector of target image and comparison data library to
Amount is compared, and obtains comparing rate；
Wherein carry out the texture feature vector of target image and the texture feature vector of the multiple images in comparison data library
It before comparing, further include collecting the registration information of multiple images, being registered and stored in the database.Wherein by target figure
As comparing to be authenticated with the image in database.
Specifically, in the registration information, the name of personage or the code name of object can be enclosed so as to identified or tune
It takes.In addition, further including registering at least one registered images in registration information.It equally can be according to the name of personage or the code name of object
Carry out transferring for registered images.
Further, registered images be include image for the image of certification and its associated information, specifically include
The structure of identification information, shooting image and texture feature vector.
Specifically, if by the textural characteristics of the multiple images in the texture feature vector of target image and comparison data library to
Before amount is compared, it is also necessary to determine the selection classification of the texture feature vector of target image in step S120.In database
The classification of the texture feature vector of image should be consistent with the selection classification of the texture feature vector of target image.
In order to facilitate differentiation, the texture feature vector of target image is defined as " target texture feature vector ", by data
The texture feature vector of multiple images is defined as " former texture feature vector " in library.
Illustratively, if having chosen energy feature f in step S1201With comentropy f2As target texture feature vector, then
Still it needs to be determined that in database multiple images corresponding energy feature f1' and comentropy f2' as former texture feature vector.
Preferably, the method that the selection of former feature vector can refer to formula one, two, three, four in step D1-D3.
Specifically, similarity degree of the comparing rate for multiple images and target image in database of descriptions.It is represented byWherein a=1,2,3,4.Image if the comparing rate the high in database of descriptions is more similar to target image.
Step S140: comparing rate is higher than the image in the comparison data library of specified threshold and forms alternate image set.
Preferably, the specified threshold mentioned in the present embodiment is the fixed range being arranged according to actual conditions, by artificial
It is arranged and can be modified.
Illustratively, if the comparing rate of image A and image B in database are higher than specified threshold, more with target image
Similar, then image A and image B forms alternate image set, for being further compared with target image.
Step S150: the spatial relation characteristics vector for comparing each image and target image in alternate image set obtains phase
To rate.
Specifically, relative rate be alternate image set in image with respect to other images, to what extent with target figure
As approximate score.Relative rate can be from which further followed that by comparing spatial relation characteristics.
Wherein obtain relative rate specifically includes the following steps:
Step P1: in alternate image set, the shared region of alternate image and target image is determined.
Illustratively, with image A citing, it is preferable that image A and target image are still divided into several lattices, gone forward side by side
The division and determination in the shared region of row.
Illustratively, image A and target image are divided into the grid of 16*16, choose 2* in image A and target image
Compared one by one 2 target area.It determines and whether there is approximate region in the target area of the two 2*2.
If it exists, then the approximate region is defined as shared region in alternate image and target image, executes step P2.
Otherwise the 2*2 lattice for replacing with other numerical value is continued to compare.
Preferably, the determination for sharing region can refer to the method being compared between image in the prior art.
Specifically, wherein alternate image is one-to-one relationship with the shared region in target image.Such as spare figure
As the region of upper left 2*2 is consistent with the region of the upper left 2*2 of target image, then two regions are shared region, are existed
Corresponding relationship.
Step P2: the spatial relationship that target image shares region is calculated.
Illustratively, region is shared at 5 if existing in image A and target image, choose any in shared region at 3
The calculating that region carries out spatial relationship is shared at two.
Wherein spatial relationship available range size is determined, specifically shared distance DCDIt may be expressed as:
Wherein θCDFor share at any two region C, D-shaped at correspondence directed line segment folder
Angle.
Step P3: the spatial relationship that region is shared in alternate image is calculated.
Specifically, calculating the shared region in the alternate image of spatial relationship need to be corresponding close with the region in target image
System, is represented by C ', D '.The range formula that spatial relationship in alternate image can refer in step P2 is calculated, and specifically may be used
It is expressed as
If in alternate image share region distance and target image share region at a distance from it is identical or be no more than specify threshold
Value, then it is assumed that the two matches, and spatial relationship is identical.
Step P4: relative rate is calculated.
Illustratively, if it is approximate with target area there are region is shared at 5 in image A, it therefrom has chosen and target image
Corresponding 2 pairs of shared regions shared region corresponding with target area is compared, check share it is interregional whether to matching (value
It obtains it is noted that since shared region is approximation, it is therefore desirable to further compare the similarity between shared region, that is, be
It is no to match).
Such as C ', D ' are had chosen, the 2 pairs of shared regions C ", D ".If there was only C ', the shared distance of D ' and target figure in image A
Shared apart from identical as in, then matched shared number of regions is 2.Other alternate images determine the side for matching shared region
Method is identical as the determination method in shared region matched in image A.
Specifically, relative rate S is represented by, S=N/N ', and wherein N indicates matched shared number of regions, N ' expression target
Number of regions is approximately shared in image and alternate image.
Step S160: relative rate and comparing rate are combined, and obtain image comparison rate.
Specifically, the merging of relative rate and comparing rate can be carried out by following formula, image comparison rate is embodied as:
X=δ * A+ (1- δ) * B, wherein δ indicates weight, if correlation ratio and the range differences of comparing rate away from larger, can lead to
Weight is crossed to adjust the gap between the two to achieve the effect that result is more accurate.
Wherein image comparison rate is the result of final comparison.Preferably, if image comparison rate is higher, illustrate target image
It is more similar to a certain image in alternate image set.
The application further include provide intelligent image Compare System, as shown in Fig. 2, intelligent image Compare System which includes
Acquiring unit 201, vector calculation unit 202, comparing unit 203, combining unit 204.
Wherein acquiring unit 201 is for obtaining target image.
Vector calculation unit 202 is connect with acquiring unit 201, for calculating the texture feature vector of target image.
Comparing unit 203 is connect with vector calculation unit 202, for the texture feature vector to target image and than logarithm
It is compared according to the texture feature vector of the multiple images in library, determines comparing rate, and spare figure is ultimately formed according to comparing rate
Image set closes.
Combining unit 204 is connect with comparing unit 203 respectively, is closed for obtaining relative rate, and by relative rate and comparing rate
And form image comparison rate.
Further, as shown in figure 3, including registration module 301, judgment module 302, collection modules in comparing unit 203
303。
Wherein registration module 301 is registered in the database for collecting the registration information of multiple images in advance.
Judgment module 302 is connect with registration module 301, for comparing the phase of the multiple images in database with target image
Like degree, judge whether similarity degree is higher than threshold value.
Collection modules 303 are connect with judgment module 302, if being higher than threshold value for similarity degree, are higher than the data of threshold value
Image in library forms alternate image set.
Still further, as shown in figure 4, combining unit 204 specifically includes following submodule: shared area determination module
401, spatial relationship computing module 402, relative rate computing module 403, image comparison rate computing module 404.
Shared area determination module 401 is used to determine the shared region of alternate image and target image.
Spatial relationship computing module 402 is connect with shared area determination module 401, shares region for calculating target image
The spatial relationship in region is shared with alternate image.
Relative rate computing module 403 is connect with spatial relationship computing module 402, for calculating relative rate.
Image comparison rate computing module 404 is connect with relative rate computing module 403, based on according to comparing rate and relative rate
Nomogram is as comparison rate.
The application has the advantages that
(1) method and its system that intelligent image provided by the present application compares can accurately compare the image for needing to authenticate
Similarity between each image for storing in database, improves the accuracy rate of comparison.
(2) method and its system that intelligent image provided by the present application compares can not only compare merely target image with
The similarity of image is in database to obtain comparison result, but finally obtains comparison result according to calculating layer by layer, makes to compare
Or authentication result is more accurate.
Although the example of present application reference is described, it is intended merely to the purpose explained rather than the limit to the application
System, the change to embodiment, increase and/or deletion can be made without departing from scope of the present application.
The above, the only specific embodiment of the application, but the protection scope of the application is not limited thereto, it is any
Those familiar with the art within the technical scope of the present application, can easily think of the change or the replacement, and should all contain
Lid is within the scope of protection of this application.Therefore, the protection scope of the application should be based on the protection scope of the described claims.
Claims (10)
1. a kind of method that intelligent image compares, which is characterized in that specifically includes the following steps:
Obtain target image；
Calculate the texture feature vector of target image；
The texture feature vector of target image is compared with the texture feature vector of the multiple images in comparison data library, is obtained
Obtain comparing rate；
Comparing rate is higher than the image in the comparison data library of specified threshold and forms alternate image set；
Compare the spatial relation characteristics vector of each image and target image in alternate image set and obtains relative rate；
Relative rate and comparing rate are combined, image comparison rate is obtained.
2. the method that intelligent image as described in claim 1 compares, which is characterized in that calculate the textural characteristics of target image to
It further include analysis target image before amount.
3. the method that intelligent image as claimed in claim 2 compares, which is characterized in that according to the luminance information of target object,
Frequency characteristic information and shape, position, the size information at each position of target object are analyzed.
4. the method that intelligent image as described in claim 1 compares, which is characterized in that calculate the textural characteristics of target image to
Amount specifically includes the following steps:
Determine trial zone；
High-resolution is set by trial zone；
Texture feature vector is calculated in trial zone；
Wherein texture feature vector indicates are as follows:
Wherein L indicates the gray level of image；I, j respectively indicate the gray scale of pixel；D indicates that the spatial position between two pixels is closed
System, p2 d(i, j) indicates pixel grey scale i from spatial relation d to square of the probability of pixel grey scale j.
5. the method that intelligent image as described in claim 1 compares, which is characterized in that texture feature vector indicates are as follows:
Wherein L indicates the gray level of image；I, j respectively indicate the gray scale of pixel；D indicates that the spatial position between two pixels is closed
System, pd(i, j) indicates pixel grey scale i from spatial relation d to the probability of pixel grey scale j, lg expression common logarithm.
6. the method that intelligent image as described in claim 1 compares, which is characterized in that carry out the textural characteristics of target image to
Before amount is compared with the texture feature vector of the multiple images in comparison data library, multiple images are registered.
7. the method that intelligent image as claimed in claim 6 compares, which is characterized in that include collecting multiple figures in registration process
The registration information of picture includes the name of personage or the code name of object in the registration information, identifies or transfer the registration information
On personage name or object code name.
8. the method that intelligent image as described in claim 1 compares, which is characterized in that comparing rate indicates are as follows:
Wherein a=1,2,3,4；faIndicate the texture feature vector of target image, faThe textural characteristics of image in ' expression database
Vector.
9. a kind of intelligent image Compare System, which is characterized in that including acquiring unit, vector calculation unit, comparing unit, merging
Unit；
Acquiring unit, for obtaining target image；
Vector calculation unit, for calculating the texture feature vector of target image；
Comparing unit, for target image texture feature vector and comparison data library in multiple images textural characteristics to
Amount is compared, and determines comparing rate, and ultimately form alternate image set according to comparing rate；
Combining unit merges to form image comparison rate with comparing rate for obtaining relative rate, and by relative rate.
10. intelligent image Compare System as claimed in claim 9, which is characterized in that comparing unit specifically includes following submodule
Block: registration module, judgment module, collection modules；
Registration module, the registration information for collecting multiple images in advance are registered in the database；
Whether judgment module judges similarity degree for comparing the similarity degree of multiple images and target image in database
Higher than threshold value；
Collection modules, if being higher than threshold value for similarity degree, the image being higher than in the database of threshold value forms alternate image collection
It closes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910665589.XA CN110378425B (en) | 2019-07-23 | 2019-07-23 | Intelligent image comparison method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910665589.XA CN110378425B (en) | 2019-07-23 | 2019-07-23 | Intelligent image comparison method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110378425A true CN110378425A (en) | 2019-10-25 |
| CN110378425B CN110378425B (en) | 2021-10-22 |
Family
ID=68255051
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910665589.XA Active CN110378425B (en) | 2019-07-23 | 2019-07-23 | Intelligent image comparison method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110378425B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111368932A (en) * | 2020-03-16 | 2020-07-03 | 北京伟杰东博信息科技有限公司 | Image comparison method and system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101075868A (en) * | 2006-05-19 | 2007-11-21 | 华为技术有限公司 | Long-distance identity-certifying system, terminal, servo and method |
| CN102866871A (en) * | 2012-08-03 | 2013-01-09 | 甲壳虫（上海）网络科技有限公司 | Method for dynamically displaying image |
| CN104572971A (en) * | 2014-12-31 | 2015-04-29 | 安科智慧城市技术（中国）有限公司 | Image retrieval method and device |
| CN106067172A (en) * | 2016-05-27 | 2016-11-02 | 哈尔滨工程大学 | A kind of underwater topography image based on suitability analysis slightly mates and mates, with essence, the method combined |
| CN106991419A (en) * | 2017-03-13 | 2017-07-28 | 特维轮网络科技（杭州）有限公司 | Method for anti-counterfeit based on tire inner wall random grain |
| US9767348B2 (en) * | 2014-11-07 | 2017-09-19 | Noblis, Inc. | Vector-based face recognition algorithm and image search system |
| CN109543535A (en) * | 2018-10-23 | 2019-03-29 | 华南理工大学 | Three-dimensional refers to vena characteristic extracting method and its matching process |
-
2019
- 2019-07-23 CN CN201910665589.XA patent/CN110378425B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101075868A (en) * | 2006-05-19 | 2007-11-21 | 华为技术有限公司 | Long-distance identity-certifying system, terminal, servo and method |
| CN102866871A (en) * | 2012-08-03 | 2013-01-09 | 甲壳虫（上海）网络科技有限公司 | Method for dynamically displaying image |
| US9767348B2 (en) * | 2014-11-07 | 2017-09-19 | Noblis, Inc. | Vector-based face recognition algorithm and image search system |
| CN104572971A (en) * | 2014-12-31 | 2015-04-29 | 安科智慧城市技术（中国）有限公司 | Image retrieval method and device |
| CN106067172A (en) * | 2016-05-27 | 2016-11-02 | 哈尔滨工程大学 | A kind of underwater topography image based on suitability analysis slightly mates and mates, with essence, the method combined |
| CN106991419A (en) * | 2017-03-13 | 2017-07-28 | 特维轮网络科技（杭州）有限公司 | Method for anti-counterfeit based on tire inner wall random grain |
| CN109543535A (en) * | 2018-10-23 | 2019-03-29 | 华南理工大学 | Three-dimensional refers to vena characteristic extracting method and its matching process |
Non-Patent Citations (1)
| Title |
|---|
| 杨帆: "《数字图像处理与分析 第4版》", 31 January 2019 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111368932A (en) * | 2020-03-16 | 2020-07-03 | 北京伟杰东博信息科技有限公司 | Image comparison method and system |
| CN111368932B (en) * | 2020-03-16 | 2021-05-28 | 赢技科技发展(杭州)有限公司 | Image comparison method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110378425B (en) | 2021-10-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111832605B (en) | Training method and device for unsupervised image classification model and electronic equipment | |
| CN105913040B (en) | The real-time pedestrian detecting system of dual camera under the conditions of noctovision | |
| CN101539990B (en) | Method for selecting and rapidly comparing robust features of iris images | |
| CN110490158B (en) | Robust face alignment method based on multistage model | |
| US20150363670A1 (en) | Image recognition method and camera system | |
| CN105469359B (en) | Face super-resolution reconstruction method based on local restriction low-rank representation | |
| CN111539247B (en) | Hyper-spectrum face recognition method and device, electronic equipment and storage medium thereof | |
| CN105138993A (en) | Method and device for building face recognition model | |
| US9117145B2 (en) | Finger biometric sensor providing coarse matching of ridge flow data using histograms and related methods | |
| US20150371077A1 (en) | Fingerprint recognition for low computing power applications | |
| CN106415594A (en) | A method and a system for face verification | |
| CN110189294B (en) | RGB-D image significance detection method based on depth reliability analysis | |
| CN104050448B (en) | A kind of human eye positioning, human eye area localization method and device | |
| CN102509138A (en) | Authentication system based on second-generation ID card and human face feature recognition and working method therefor | |
| CN108197669B (en) | Feature training method and device of convolutional neural network | |
| CN105760898A (en) | Vision mapping method based on mixed group regression method | |
| CN112686191B (en) | Living body anti-counterfeiting method, system, terminal and medium based on three-dimensional information of human face | |
| CN106600613A (en) | Embedded GPU-based improved LBP infrared target detection method | |
| CN110363250A (en) | A kind of method and its system of 3-D image intelligent Matching | |
| CN110909582B (en) | Face recognition method and equipment | |
| CN110378425A (en) | A kind of method and its system that intelligent image compares | |
| CN114882537A (en) | Finger new visual angle image generation method based on nerve radiation field | |
| CN117372515B (en) | Self-adaptive deviation rectifying control system | |
| CN116596428B (en) | Rural logistics intelligent distribution system based on unmanned aerial vehicle | |
| CN110223264B (en) | Image difference characteristic attribute fusion validity distribution structure based on intuition possibility set and synthesis method |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210923 Address after: 430000 C1-10, room 02, floor 5, building 2, international enterprise center, No. 1, Guanshan Second Road, East Lake New Technology Development Zone, Wuhan, Hubei Province (Wuhan area of free trade zone) (one site with multiple photos) Applicant after: Wuhan luosiyashi Technology Co.,Ltd. Address before: 101300 Beijing Shunyi District Airport Street, No. 1 Anhua Street, 1st Building, 1st Floor, No. 2159 Applicant before: BEIJING LONGPU INTELLIGENT TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |