CN106910180B - A kind of image quality measure method and device - Google Patents
A kind of image quality measure method and device Download PDFInfo
- Publication number
- CN106910180B CN106910180B CN201510970440.4A CN201510970440A CN106910180B CN 106910180 B CN106910180 B CN 106910180B CN 201510970440 A CN201510970440 A CN 201510970440A CN 106910180 B CN106910180 B CN 106910180B
- Authority
- CN
- China
- Prior art keywords
- image
- assessed
- area
- point set
- network
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of image quality measure method and apparatus, by acquiring characteristics of image point set, it is characterized point set building Delaunay triangular net, and according to the uniqueness of Delaunay triangular net, the related data of Delaunay triangular net is calculated, to evaluate picture quality, entire evaluation procedure is simple and efficient, and carried out from computer vision angle, it is suitable for automated graphics identification and augmented reality field.
Description
Technical field
The present invention relates to image procossing calculating field more particularly to a kind of image quality measure method and devices.
Background technique
In the field of image recognition based on content, an image is characterized usually in a manner of feature point set, is known in image
When other, the search result of image is determined according to the matching relationship between characteristic point pair, in extreme circumstances, search result and mesh
There was only a small amount of matching characteristic point pair between logo image, at this point, since feature describes the limitation of algorithm, if retrieved establishing
When database, picture quality it is poor (such as meet condition characteristic point it is seldom, or be unevenly distributed), it will be difficult under extreme conditions
It retrieves correct as a result, the normal work of image identification system can be interfered, influences image recognition effect, and then influence user's body
It tests.
Existing image quality evaluating method is broadly divided into: reference image quality appraisement and non-reference picture quality appraisement.
Reference image quality appraisement method is due to needing to refer to figure, and flexibility is poor when application, is not suitable for field of image recognition.And it is existing
No reference plot quality evaluation method mainly has artificial evaluation method and the subjective vision system founding mathematical models according to human eye, and
The quality of image is calculated by specific formula, the two mode is all referring to human eye subjective vision, and automated graphics identification belongs to
Computer vision field, these image quality evaluating methods cannot all reach promising result.
Summary of the invention
The object of the present invention is to provide a kind of image quality measure method and devices, assess picture quality, solve
When establishing image retrieval database, because lacking image quality measure system, be put into excessive second-rate image and caused by figure
As the problem of recognition effect difference, the recognition accuracy of image identification system can be improved from source, promote user experience.
In order to achieve the above-mentioned object of the invention, the present invention provides a kind of image quality measure methods, comprising:
Feature extraction is carried out to image to be assessed, obtains the feature point set data of image to be assessed, in feature point set data
Location information including each characteristic point in image-region；
Delaunay Triangulation is carried out to the feature point set of the image to be assessed, it is corresponding to obtain image to be assessed
Delaunay triangulation network network；
Calculate the area area [i] of each triangle in the Delaunay triangulation network network, i is to be less than more than or equal to 1 etc.
In the integer of n, n is Delaunay triangulation network network intermediate cam figurate number amount；
Area occupied ratio of the Delaunay triangulation network network in image to be assessed, and root are calculated according to area [i]
Quality evaluation is carried out to image to be assessed according to the area occupied ratio.
Preferably, the method also includes: calculate area [i] distribution smoothness；According to described calculated
The distribution smoothness of area occupied ratio and area [i] of the Delaunay triangulation network network in image to be assessed is to image to be assessed
Carry out quality evaluation.
Wherein, the distribution smoothness of area [i] is calculated specifically: calculate the mean value mean and variance of area [i]
variance；It calculates (area [i]-mean)2In maximum value maxSub；Distribution smoothness=1-sqrt of area [i]
(variance/maxSub)。
Preferably, the feature point set to the image to be assessed carries out Delaunay Triangulation, specifically: it treats
It assesses each characteristic point in the feature point set of image and carries out spatial classification, construct Delaunay triangular net according to ranking results.
Preferably, the spatial classification, which refers to, carries out intermediate value to the characteristic point in feature point set according to the location information of characteristic point
Sequence, specifically: A: using characteristic point in feature point set in x-axis and y-axis diameter maximum/minimum axis as sort axis；B: it calculates
The intermediate value of two characteristic points of the diameter is constituted, changing former feature point set makes the characteristic point being spatially positioned on the left of intermediate value in data
It is located on the left of median point in set, right-hand point is located on the right side of median point；C: and then to the point set and right-hand point structure that left-hand point is constituted
At point set carry out above-mentioned A and step B Recursion process, until intermediate value side characteristic point quantity is less than 2.
Correspondingly, the present invention also proposes a kind of image quality measure device, comprising:
Characteristic extracting module obtains the feature point set number of image to be assessed for carrying out feature extraction to image to be assessed
According to including location information of each characteristic point in image-region in feature point set data；
Triangulation module carries out Delaunay Triangulation for the feature point set to the image to be assessed, obtains
The corresponding Delaunay triangulation network network of image to be assessed；
Computing module, for calculating the area area [i] of each triangle in the Delaunay triangulation network network, and according to
Area [i] calculates area occupied ratio of the Delaunay triangulation network network in image to be assessed, and wherein i is more than or equal to 1
Integer less than or equal to n, n are Delaunay triangulation network network intermediate cam figurate number amount；
Evaluation module carries out quality to image to be assessed according to the calculated area occupied ratio of computing module and comments
Estimate.
Preferably, the computing module is also used to calculate the distribution smoothness of area [i]；The evaluation module is according to calculating
The calculated area occupied ratio of module and the distribution smoothness of area [i] carry out quality evaluation to image to be assessed.
Preferably, the triangle subdivision module cuts open the feature point set progress Delaunay triangle of the image to be assessed
Point, specifically: spatial classification is carried out to characteristic point each in the feature point set of image to be assessed, is constructed according to ranking results
Delaunay triangular net.
Compared with prior art, the invention has the following beneficial effects:
Image quality measure method and apparatus of the present invention are to identify that field is designed for automated graphics, pass through acquisition
Characteristics of image point set is characterized point set building Delaunay triangular net, according to the uniqueness of Delaunay triangular net,
The related data of Delaunay triangular net is calculated, to evaluate picture quality, entire evaluation procedure is simple and efficient, and is stood and counted
Calculation machine visual angle carries out, and is more suitable for automated graphics identification field.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, 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
Some embodiments of invention without any creative labor, may be used also for those of ordinary skill in the art
To obtain other drawings based on these drawings:
Fig. 1 is image quality measure of embodiment of the present invention method flow schematic diagram；
Fig. 2 is a feature point set schematic diagram in one embodiment of the invention；
Fig. 3 is image quality measure of embodiment of the present invention apparatus structure schematic diagram.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Computer vision and human eye vision have natural difference, and the image that some human eyes can readily identify is in computer
It is difficult to identify in the eyes, such as characteristic point is few but gem-pure image.In field of image recognition, and use image recognition
Augmented reality field, image storage are the premises of image recognition, however since most of user does not know computer vision
It is how to identify image, at will places some storage images, when storage picture quality is poor (for example meet the feature of condition
Point seldom, or is unevenly distributed), retrieval is easy to failure.Therefore when image storage, an image quality measure side is needed
Method, informs whether user's figure is easily recognizable to the computer, and search result is made to meet the target of user.
The present invention utilizes the uniqueness of Delaunay triangulation network network, and the feature point set for each storage image constructs one
Delaunay triangulation network network, according to the related data of Delaunay triangulation network network, assessment storage picture quality.
Because the present invention uses Delaunay triangle subdivision, therefore before introducing specific embodiment, first introduce
Delaunay triangular net.
Delaunay triangular net is the network for carrying out Delaunay Triangulation to point set and being formed, and to be met
The definition of Delaunay Triangulation, it is necessary to meet two important criterion:
1) empty circle characteristic: Delaunay triangulation network is unique (any 4 points cannot be concyclic), in Delaunay triangle
Other points are not had in net within the scope of the circumscribed circle of any triangle to exist；
2) minimum angle characteristic is maximized: in the triangulation that scatterplot collection is likely to form, Delaunay Triangulation institute shape
At triangle minimum angle it is maximum.In this sense, Delaunay triangulation network be " closest to regularization " three
Angle net.In particular to the diagonal line in two adjacent triangulars at convex quadrangle, after being exchanged with each other, six interior angles
Minimum angle no longer increase.
Delaunay triangulation network network has following excellent characteristics:
1) closest: with nearest three-point shape at triangle, and each line segment (side of triangle) is all non-intersecting；
2) no matter constructing since the where of region, consistent result finally will all uniqueness: be obtained；
3) optimality: any two adjacent triangle formed convex quadrangle diagonal line if it can be interchanged, that
The smallest angle will not become larger in two triangles, six interior angles；
4) it is most regular: if the minimum angle of each triangle in the triangulation network is carried out ascending order arrangement, Delaunay tri-
The numerical value that the arrangement of angle net obtains is maximum；
5) regional: only to will affect the triangle closed on when newly-increased, deletion, some mobile vertex；
6) with the shell of convex polygon: the outermost boundary of the triangulation network forms the shell of a convex polygon.
In the following, introducing the specific embodiment of the invention in conjunction with attached drawing.
Referring to Fig. 1, it is a kind of image quality measure method flow schematic diagram of the embodiment of the present invention, includes the following steps:
S101: feature extraction is carried out to image to be assessed, obtains the feature point set data of image to be assessed, feature point set number
It include location information of each characteristic point in image-region in, this steps characteristic extracting method can be using based on scale
Constant feature extracting method, such as ORB, SIFT, SURF etc., the characteristic point data extracted may be used also other than location information
To include scale, direction, characterization information etc., only image quality measure of the present invention only uses location information.
S102: Delaunay Triangulation is carried out to the feature point set of the image to be assessed, obtains image pair to be assessed
Answer Delaunay triangulation network network (triangular net have uniqueness, i.e., the same point set is constructed, no matter from which
Point starts all to obtain consistent as a result, carrying out delete operation, the obtained triangulation network to the same subset concentrated simultaneously
It is consistent), this step Delaunay Triangulation concrete mode is described below.
S103: calculating the area area [i] of each triangle in the Delaunay triangulation network network, and i is small more than or equal to 1
In the integer for being equal to n, n is Delaunay triangulation network network intermediate cam figurate number amount, in the area area [i] for calculating each triangle
When, pixel unit can be used and calculated；
S104: area occupied ratio of the Delaunay triangulation network network in image to be assessed is calculated according to area [i].
The area of triangles all in Delaunay triangulation network network is added, Delaunay triangulation network network area is obtained；According to be assessed
The wide height of image, calculates image area to be assessed；The ratio between Delaunay triangulation network network area and image area to be assessed, obtain
Area occupied ratio of the Delaunay triangulation network network in image to be assessed, the ratio between 0.0~1.0, get over by this ratio
Height indicates that image characteristic point to be assessed distribution is wider, and characteristic point distribution is wider, to block adaptability it is higher (in image retrieval,
It is higher that retrieval success rate is completed in the case where blocking), thus we to can be understood as picture quality better.
S105: the distribution smoothness of area [i] is calculated, specific calculation includes following tri- step of ABC:
A: the mean value mean and variance variance of area [i] are calculated:
Mean=sum (area [i])/n；
Variance=sum (area [i] * area [i])/n-mean*mean；
B: it calculates (area [i]-mean)2In maximum value maxSub:
C: calculate: the distribution smoothness of area [i], smoothness are denoted as smoothVal:
SmoothVal=1-sqrt (variance/maxSub), smoothness is bigger, indicates that characteristic point distribution is more uniform, right
It is higher to block adaptability, it is better to be interpreted as picture quality in the present invention.
In above-mentioned calculation formula, sum indicates summation, and Sqrt indicates sqrt.
S106: according to area occupied ratio of the calculated Delaunay triangulation network network in image to be assessed and
The distribution smoothness of area [i] carries out quality evaluation to image to be assessed, when assessment, freely define the two according to actual needs and weighs
Weight, such as the two weight can be respectively to account for 0.5, or 0.3,0.7 or even 0.0,1.I.e. in the present invention when it is implemented,
It can be according to point of area occupied ratio of the calculated Delaunay triangulation network network in image to be assessed and area [i]
Any one parameter in cloth smoothness carries out quality evaluation to image to be assessed, certainly both preferred in conjunction with carrying out picture quality
Assessment.
In step S102, Delaunay Triangulation is carried out to the feature point set of the image to be assessed, specifically:
Spatial classification is carried out to characteristic point each in the feature point set of image to be assessed, constructs Delaunay according to ranking results
Triangular net, the spatial classification can be median-of-three sort, and the median-of-three sort refers to according to the location information of characteristic point to spy
The characteristic point that sign point is concentrated carries out a median-of-three sort, specifically: A: by characteristic point in feature point set in x-axis and y-axis diameter it is maximum/
Minimum axis is as sequence axis；B: calculating the intermediate value for constituting two characteristic points of the diameter, and changing former feature point set keeps space upper
Characteristic point on the left of intermediate value is located on the left of median point in data acquisition system, and right-hand point is located on the right side of median point；Then to left side
The point set that the point set and right-hand point that point is constituted are constituted carries out the Recursion process of above-mentioned A and step B, until intermediate value side feature is counted
Amount is less than 2.Wherein x-axis diameter refers in feature point set, the x coordinate of each characteristic point, the absolute value of the difference of maxima and minima；y
Shaft diameter refers in feature point set that the y-coordinate of each characteristic point, the absolute value of the difference of maxima and minima is referring to fig. 2 one
Point set, including following 7 points: [(- 2,2) (2.5, -5) (2,1) (- 4, -1.5) (- 7.5,2.5) (7,2) (1, -2.5)], this 7
The x-axis diameter of the point set of a point composition is 14, and y-axis diameter is 7.5, it is assumed that is with the greater in xy axis week diameter when median-of-three sort
Sort axis, then when the first minor sort, using x-axis as sequence axis, intermediate value 0, by (- 7.5,2.5), (- 2,2), (- 4, -1.5) three
A point comes on the left of median point, other four points are placed on the right side of median point.Then recurrence is carried out to left side point set and right side point set
Processing, i.e., find left and right sides point set again and be relatively large in diameter axis in xy axis, calculates the intermediate value for constituting two characteristic points of the diameter,
Changing former feature point set is located at the characteristic point being spatially positioned on the left of intermediate value on the left of median point in data acquisition system, right side point
On the right side of median point.
It is a kind of image quality measure device of the embodiment of the present invention referring to Fig. 3, comprising:
Characteristic extracting module 1 obtains the feature point set number of image to be assessed for carrying out feature extraction to image to be assessed
According to including location information of each characteristic point in image-region in feature point set data, feature extracting method can use base
In the feature extracting method of Scale invariant, such as ORB, SIFT, SURF etc..
Triangulation module 2 carries out Delaunay Triangulation for the feature point set to the image to be assessed, obtains
The corresponding Delaunay triangulation network network of image to be assessed, Delaunay Triangulation method are detailed in the implementation of image quality measure method
Detailed narration in example to the part S102, this place does not repeat them here.
Computing module 3, for calculating the area area [i] of each triangle in the Delaunay triangulation network network, and root
Calculate the area occupied ratio of the Delaunay triangulation network network in image to be assessed according to area [i], wherein i be more than or equal to
1 is less than or equal to the integer of n, and n is Delaunay triangulation network network intermediate cam figurate number amount；Each parameter calculation reference in computing module
Previous embodiment step S103, S104 part.
Evaluation module 4 calculates the area occupied ratio that 3 go out according to computing module and comments image to be assessed progress quality
Estimate, for the ratio between 0.0~1.0, this ratio is higher, indicates that image characteristic point distribution to be assessed is wider, characteristic point distribution
Wider, higher to adaptability is blocked, picture quality is better.
In another embodiment, the computing module 3 is also used to calculate the distribution smoothness of area [i], smoothness
It is bigger, indicate that characteristic point distribution is more uniform, it is higher to adaptability is blocked, it is better that it is interpreted as picture quality in the present invention.It is described
Evaluation module 4 is according to the calculated area occupied ratio of computing module 3 and the distribution smoothness of area [i] to figure to be assessed
As carrying out quality evaluation, when assessment, both freely define weight according to actual needs, such as the two weight can be respectively to account for 0.5,
It may be 0.3,0.7 or even 0.0,1.I.e. in the present invention when it is implemented, can be according to the calculated Delaunay tri-
Any one parameter of angle network in the distribution smoothness of area occupied ratio and area [i] in image to be assessed is to be assessed
Image carries out quality evaluation, both certainly preferred in conjunction with carrying out image quality measure.
Image quality measure method and apparatus of the present invention are suitable for field of image recognition, and use the increasing of image recognition
Storage image is assessed using the method for the present invention, can be given in some way in image storage in strong reality technology field
An assessment result prompt, city user know that certain picture quality if appropriate for for the storage image as image retrieval, makes out
Search result meets the target of user.
All features disclosed in this specification or disclosed all methods or in the process the step of, in addition to mutually exclusive
Feature and/or step other than, can combine in any way.
Any feature disclosed in this specification (including any accessory claim, abstract and attached drawing), except non-specifically chatting
It states, can be replaced by other alternative features that are equivalent or have similar purpose.That is, unless specifically stated, each feature is only
It is an example in a series of equivalent or similar characteristics.
The invention is not limited to specific embodiments above-mentioned.The present invention, which expands to, any in the present specification to be disclosed
New feature or any new combination, and disclose any new method or process the step of or any new combination.
Claims (8)
1. a kind of image quality measure method characterized by comprising
Feature extraction is carried out to image to be assessed, the feature point set data of image to be assessed is obtained, includes in feature point set data
Location information of each characteristic point in image-region；
Delaunay Triangulation is carried out to the feature point set of the image to be assessed, it is corresponding to obtain image to be assessed
Delaunay triangulation network network；
The area area [i] of each triangle in the Delaunay triangulation network network is calculated, i is more than or equal to 1 less than or equal to n's
Integer, n are Delaunay triangulation network network intermediate cam figurate number amount；
Area occupied ratio of the Delaunay triangulation network network in image to be assessed is calculated according to area [i], and according to this
Area occupied ratio carries out quality evaluation to image to be assessed.
2. image quality measure method as described in claim 1, which is characterized in that the method also includes: it calculates area [i]
Distribution smoothness；
According to point of area occupied ratio and area [i] of the calculated Delaunay triangulation network network in image to be assessed
Cloth smoothness carries out quality evaluation to image to be assessed.
3. image quality measure method as claimed in claim 2, which is characterized in that calculate the distribution smoothness tool of area [i]
Body are as follows:
Calculate the mean value mean and variance variance of area [i]；
It calculates (area [i]-mean)2In maximum value maxSub；
The distribution smoothness of area [i]=1-sqrt (variance/maxSub).
4. image quality measure method as claimed any one in claims 1 to 3, which is characterized in that described to described to be evaluated
The feature point set for estimating image carries out Delaunay Triangulation, specifically:
Spatial classification is carried out to characteristic point each in the feature point set of image to be assessed, constructs Delaunay triangle according to ranking results
L network.
5. image quality measure method as claimed in claim 4, which is characterized in that the spatial classification refers to according to characteristic point
Location information carries out median-of-three sort to the characteristic point in feature point set, specifically:
A: using the characteristic point in feature point set in x-axis and y-axis diameter maximum/minimum axis as sequence axis；
B: calculating the intermediate value for constituting two characteristic points of the diameter, and changing former feature point set makes the spy being spatially positioned on the left of intermediate value
Sign point is located on the left of median point in data acquisition system, and right-hand point is located on the right side of median point；
C: and then above-mentioned A and step B Recursion process, Zhi Daozhong are carried out to the point set of the left-hand point point set constituted and right-hand point composition
It is worth side characteristic point quantity less than 2.
6. a kind of image quality measure device characterized by comprising
Characteristic extracting module obtains the feature point set data of image to be assessed, spy for carrying out feature extraction to image to be assessed
Levying includes location information of each characteristic point in image-region in point set data；
Triangulation module carries out Delaunay Triangulation for the feature point set to the image to be assessed, obtains to be evaluated
Estimate the corresponding Delaunay triangulation network network of image；
Computing module, for calculating the area area [i] of each triangle in the Delaunay triangulation network network, and according to area
[i] calculates area occupied ratio of the Delaunay triangulation network network in image to be assessed, and wherein i is to be less than more than or equal to 1
Integer equal to n, n are Delaunay triangulation network network intermediate cam figurate number amount；
Evaluation module carries out quality evaluation to image to be assessed according to the calculated area occupied ratio of computing module.
7. image quality measure device as claimed in claim 6, which is characterized in that the computing module is also used to calculate area
The distribution smoothness of [i]；The evaluation module is according to point of the calculated area occupied ratio of computing module and area [i]
Cloth smoothness carries out quality evaluation to image to be assessed.
8. image quality measure device as claimed in claims 6 or 7, which is characterized in that the triangulation module is to described
The feature point set of image to be assessed carries out Delaunay Triangulation, specifically:
Spatial classification is carried out to characteristic point each in the feature point set of image to be assessed, constructs Delaunay triangle according to ranking results
L network.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510970440.4A CN106910180B (en) | 2015-12-22 | 2015-12-22 | A kind of image quality measure method and device |
| PCT/CN2016/110367 WO2017107867A1 (en) | 2015-12-22 | 2016-12-16 | Image quality evaluation method and apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510970440.4A CN106910180B (en) | 2015-12-22 | 2015-12-22 | A kind of image quality measure method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106910180A CN106910180A (en) | 2017-06-30 |
| CN106910180B true CN106910180B (en) | 2019-08-20 |
Family
ID=59089140
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510970440.4A Active CN106910180B (en) | 2015-12-22 | 2015-12-22 | A kind of image quality measure method and device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN106910180B (en) |
| WO (1) | WO2017107867A1 (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107610110B (en) * | 2017-09-08 | 2020-09-25 | 北京工业大学 | Global and local feature combined cross-scale image quality evaluation method |
| CN107993230B (en) * | 2017-12-18 | 2021-11-19 | 辽宁师范大学 | Image tampering detection method based on triangular mesh comprehensive characteristics |
| CN108829595B (en) * | 2018-06-11 | 2022-05-17 | Oppo（重庆）智能科技有限公司 | Test method, test device, storage medium and electronic equipment |
| CN108983233B (en) * | 2018-06-13 | 2022-06-17 | 四川大学 | PS point combination selection method in GB-InSAR data processing |
| CN115249330B (en) * | 2022-09-05 | 2023-04-28 | 中国测绘科学研究院 | Method and system for evaluating vegetation connectivity |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012016242A2 (en) * | 2010-07-30 | 2012-02-02 | Aureon Biosciences, Inc. | Systems and methods for segmentation and processing of tissue images and feature extraction from same for treating, diagnosing, or predicting medical conditions |
| CN102760293A (en) * | 2012-06-14 | 2012-10-31 | 南京信息工程大学 | Image quality evaluation method based on distance matrix |
| CN103366378A (en) * | 2013-07-26 | 2013-10-23 | 深圳大学 | Reference-free type image quality evaluation method based on shape consistency of condition histogram |
| CN103996192A (en) * | 2014-05-12 | 2014-08-20 | 同济大学 | Non-reference image quality evaluation method based on high-quality natural image statistical magnitude model |
| CN104282019A (en) * | 2014-09-16 | 2015-01-14 | 电子科技大学 | Blind image quality evaluation method based on natural scene statistics and perceived quality propagation |
-
2015
- 2015-12-22 CN CN201510970440.4A patent/CN106910180B/en active Active
-
2016
- 2016-12-16 WO PCT/CN2016/110367 patent/WO2017107867A1/en active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012016242A2 (en) * | 2010-07-30 | 2012-02-02 | Aureon Biosciences, Inc. | Systems and methods for segmentation and processing of tissue images and feature extraction from same for treating, diagnosing, or predicting medical conditions |
| CN102760293A (en) * | 2012-06-14 | 2012-10-31 | 南京信息工程大学 | Image quality evaluation method based on distance matrix |
| CN103366378A (en) * | 2013-07-26 | 2013-10-23 | 深圳大学 | Reference-free type image quality evaluation method based on shape consistency of condition histogram |
| CN103996192A (en) * | 2014-05-12 | 2014-08-20 | 同济大学 | Non-reference image quality evaluation method based on high-quality natural image statistical magnitude model |
| CN104282019A (en) * | 2014-09-16 | 2015-01-14 | 电子科技大学 | Blind image quality evaluation method based on natural scene statistics and perceived quality propagation |
Non-Patent Citations (1)
| Title |
|---|
| Quality Assessment of Fingerprints with Minutiae Delaunay;YAO,Z等;《ICISSP 2015-1st International Conference on Information Systems Security and Privacy》;20150211;全文 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106910180A (en) | 2017-06-30 |
| WO2017107867A1 (en) | 2017-06-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106910180B (en) | A kind of image quality measure method and device | |
| CN109409437B (en) | Point cloud segmentation method and device, computer readable storage medium and terminal | |
| CN109196561B (en) | System and method for three-dimensional garment mesh deformation and layering for fitting visualization | |
| CN107111833B (en) | Fast 3D model adaptation and anthropometry | |
| CN105354876B (en) | A kind of real-time volume fitting method based on mobile terminal | |
| CN102236899B (en) | Method and device for detecting objects | |
| US20160249041A1 (en) | Method for 3d scene structure modeling and camera registration from single image | |
| EP3971841A1 (en) | Three-dimensional model generation method and apparatus, and computer device and storage medium | |
| CN109446889A (en) | Object tracking method and device based on twin matching network | |
| CN106952335B (en) | Method and system for establishing human body model library | |
| DE102017208952A1 (en) | Tooth type determining program, tooth type position determining device and method thereof | |
| CN106157372A (en) | A kind of 3D face grid reconstruction method based on video image | |
| CN110889826A (en) | Segmentation method and device for eye OCT image focal region and terminal equipment | |
| CN103913131A (en) | Free curve method vector measurement method based on binocular vision | |
| WO2010004466A1 (en) | Three dimensional mesh modeling | |
| CN105404888A (en) | Saliency object detection method integrated with color and depth information | |
| CN110378914A (en) | Rendering method and device, system, display equipment based on blinkpunkt information | |
| CN109740659B (en) | Image matching method and device, electronic equipment and storage medium | |
| CN113822982A (en) | Human body three-dimensional model construction method and device, electronic equipment and storage medium | |
| CN111754618B (en) | Object-oriented live-action three-dimensional model multi-level interpretation method and system | |
| CN107507188B (en) | Method and device for extracting image information based on machine learning | |
| CN109313802B (en) | Biological object detection | |
| CN106778660B (en) | A kind of human face posture bearing calibration and device | |
| CN114329747A (en) | Building digital twin oriented virtual and real entity coordinate mapping method and system | |
| CN110490829A (en) | A kind of filtering method and system of depth image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |