CN103679201B - Calibration method of point set matching for image matching, recognition and retrieval - Google Patents
Calibration method of point set matching for image matching, recognition and retrieval Download PDFInfo
- Publication number
- CN103679201B CN103679201B CN201310688861.9A CN201310688861A CN103679201B CN 103679201 B CN103679201 B CN 103679201B CN 201310688861 A CN201310688861 A CN 201310688861A CN 103679201 B CN103679201 B CN 103679201B
- Authority
- CN
- China
- Prior art keywords
- node
- matching
- image
- point
- recognition
- 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.)
- Expired - Fee Related
Links
Abstract
The invention belongs to the technical field of pattern recognition, image processing and computer vision, and particularly relates to a calibration method of point set matching for image matching, recognition and retrieval. According to the calibration method of the point set matching for the image matching, recognition and retrieval, an adjacent matrix is established according to an initial matching relation of two point sets, and an approximate solving method of a maximum clique problem in a graph theory is proposed to obtain a point set matching relation approximately complying with identical geometric transformation. The similarity degree between the two point sets can be obtained by projecting one point set to the space where the other point set is located through the geometric transformation, and the similarity degree between the two point sets is used as an image similarity degree to achieve the image matching, recognition and retrieval. Experiments show that the calibration method of the point set matching can be combined with any of multiple shape feature extraction methods to obtain good image matching and recognition effects.
Description
Technical field
The invention belongs to pattern recognition, image procossing, technical field of computer vision, be specifically related to a kind of some sets match
Bearing calibration, may be used for images match, identify, retrieve.
Background technology
Image includes shape, texture, colouring information, and wherein, shape is image recognition, retrieves the main information relied on,
Shape facility describes for image recognition, retrieves extremely important, and similarity and the diversity between shape is often reflected in figure
In the characteristic point of picture, therefore a kind of primary solutions of images match is to solve as a sets match.
【S.Belogie,J.Malik,J.Puzicha:“Shape matching and object recognition using
shape contexts,IEEE Transactions on Pattern Analysis and Machine
Intelligence ", Volume 24, pp.509-52,2002] paper proposes a kind of it is referred to as Shape context (Shape
Contexts) shape description method, uses the Bipartite Matching in graph theory on the basis of shape descriptor Similarity Measure
A set is mated by method, but its computation complexity is higher, its solve Bipartite Matching algorithm complexity about
For O (N4)。【David G.Lowe:″Distinctive Image Features from Scale-Invariant
Keypoints″,International Journal of Computer Vision,Volume 60,Issue 2,pp.91-
110,2004] Feature Points Extraction of a kind of DoG and a kind of description being referred to as SIFT are proposed in, and based on describing son
Between similarity characteristic point is mated, but such set matching result without correction containing error hiding,
Can to follow-up images match, identify, retrieve and bring interference.
Summary of the invention
It is an object of the invention to propose a kind of computing cost rationally and can obtain with the collocation of variously-shaped description method
Preferable images match, identify, retrieve the bearing calibration of the some sets match of performance.
A kind of bearing calibration for a sets match that the present invention proposes, concrete calculation procedure is as follows:
(1) adjacency matrix is calculated;
(2) maximal clique problem in approximate solution graph theory;
The step that adjacency matrix in step 1 in the bearing calibration of recited above some sets match calculates is as follows:
A () assumes two some set P={P1,P2,…,PmAnd Q={Q1,Q2,…,QmMatching relationship initial between } is Will abut against matrix initialisation is C={cij=0|i,j=1,2,…,m};B () calculates R
={rij=d(Pi,Pj)/d(Qi,Qj)|i,j=1,2,…,m;I ≠ j}, here d (Pi,Pj) represent some PiWith a PjBetween Europe several
In must be apart from, d (Qi,Qj) represent some QiWith a QjBetween Euclidean distance;
C () is by { rij=d(Pi,Pj)/d(Qi,Qj)|i,j=1,2,…,m;I ≠ j} sorts according to order from small to large,
To R1≤R2≤…≤Rm(m-1);By RkLocation records in R be S [k] ∈ (i, j) | i, j=1,2 ..., m;I ≠ j}, k=1,
2,…,m(m-1);
D () is by R1≤R2≤…≤Rm(m-1)Segmentation, segmentation method is as follows: if there is n-1 section, the subscript that its border is corresponding
For I [1]=1, I [2], I [3] ..., I [n-1], I [n]=m (m-1) and meet condition RI[i]/RI[i+1]>t∧RI[i]/RI[i+1]+1≤
T, here i=1,2 ..., n-1, t be one close to 1 threshold value, then with I [1]=1, I [2], I [3] ..., I [n-1], I [n] are limit
Boundary carries out segmentation;
(e) from above-mentioned steps (d) obtain to R1≤R2≤…≤Rm(m-1)N-1 segmentation in find the longest one section,
Its corresponding order in n-1 segmentation is Extract this section in R
Corresponding subscript S [k] | k=I [i*],I[i*]+1,…,I[i*+1]};
F () makes { cS[k]=1|k=I[i*],I[i*]+1,…,I[i*+1]};
Maximal clique problem approximate solution in the graph theory in step 2 in the bearing calibration of recited above some sets match
Calculation procedure is as follows:
(a) the lower target set of all nodes of a complete graph is initialized as Θ=1,2 ..., m};By noise node
Corresponding lower target set is initialized as null set Ψ=Φ, the set of the residue node outside noise node is initialized as Ω=
Θ;
B () arranges enumeratorHow many nodes are had to be connected with node i for record;
(c) for i=1,2 ..., m: if vi=0, node i is added the set of noise node, i.e. Ψ ∪ { i} → Ψ;With
Time by node from residue node set omega delete, i.e. Ω-{ i} → Ω;
If (d) vi=vjArbitrary i ≠ j is set up, here i ∈ Ω and j ∈ Ω, then willΩ institute it is designated as under in
The Corresponding matching point comprising element is to output and exits;Otherwise forward step (e) to;
E () finds the node in Ω with Smallest connection limit numberMake Ψ ∪ { i ' } → Ψ and
Ω-{i′}→Ω;Find the node being connected with node i ', i.e. Γ=j | ci′j=1;j=1,2,...,m};For j ∈ Γ, make vj-
1→vj;Forward step (d) to.
Accompanying drawing explanation
Fig. 1 is the composition frame chart of image identification system.
Detailed description of the invention
One image identification system is generally made up of following link, image acquisition, pretreatment, feature extraction, similar
Degree calculates, classification, and the target of image identification system is to return the image most like with input picture from image data base, whole
The composition of image identification system is shown in Fig. 1.Here, image acquisition can complete physics by camera, scanner etc. are various
The sensing equipment of picture completes, and pretreatment uses a kind of bianry image skeletal point extracting method that inventor proposes, and feature extraction is adopted
A kind of shape descriptor proposed with inventor.
Embodiment 1:
Step 1: a width input picture is extracted characteristic point, and calculates the shape descriptor of each characteristic point, make P={P1,
P2,…,PKAnd { f (F (Pk)) | k=1,2 ..., K} represents the shape descriptor of obtained characteristic point and correspondence thereof, shape respectively
The calculation procedure that shape describes son is as follows:
(a) optional characteristic point Pk∈ P is as a reference point, adds up the spatial distribution of further feature point, obtains
One corresponding rectangular histogram, is denoted as h (Pk);Here, histogrammic circular is as follows: with reference point PkCentered by, will figure
As the space at minimum circumscribed circle place is divided into the grid of M × Ν, the number calculating the characteristic point falling into each interval of grid obtains
To rectangular histogram, M and N is natural number;As a reference point with each characteristic point respectively, the most corresponding each characteristic point respectively obtains one
Individual rectangular histogram, there are K rectangular histogram { h (Pk)|k=1,2,…,K};
B the rectangular histogram of each Feature point correspondence is sought Fourier transformation by (), if h is (Pk) Fourier transformation be F (Pk), right
Matrix F (PkEach element in) carries out the mathematic(al) manipulation that function f (.) defines, F (Pk) mathematic(al) manipulation f (.) be defined as matrix F
(PkThe W power of the modulus value of each element in), if Fij(Pk) representing matrix F (Pk) the i-th row, jth row element, then f (Fij
(Pk))=|Fij(Pk)|W, W=2;By { f (F (Pk)) | k=1,2 ..., K} is as the shape descriptor of K characteristic point correspondence respectively;;
Step 2: piece image optional in image library is extracted characteristic point, based on the shape descriptor meter described in step 1
Calculation method calculates the shape descriptor of each characteristic point, makes Q={Q1,Q2,…,QLAnd { f (F (Ql)) | l=1,2 ..., L} is respectively
Characteristic point obtained by expression and the shape descriptor of correspondence thereof;
Step 3: the similarity between calculating input image and each shape descriptor of image library image, is denoted as { dkl=d(f
(F(Pk)),f(F(Ql)))|k=1,2,…,K;L=1,2 ..., L}, employing inner product is as measuring similarity here, the most respectively by square
Battle array f (F (Pk)) and f (F (Ql)) stretch as vector, then seek two vectorial inner products;
Step 4: according to nearest neighbouring rule to P={P1,P2,…,PKAnd Q={Q1,Q2,…,QLMate, computational methods
As follows: to carry out m=min{K, L} iteration, the point that each iteration obtains a coupling is right, and the concrete calculation procedure of each iteration is such as
Under: (a) finds set D={dkl|k=1,2,…,K;L=1,2 ..., the greatest member d in L}st;B () willAs one
Coupling is to recorded setIn;C () makes dsl=-∞ and dkt=-∞: k=1,2 ..., K and l=1,2 ..., L;
Step 5: use the initial some set that step 4 is obtained by the bearing calibration of the some sets match of present invention proposition
Join relationIt is corrected, obtains corrected some set matching relationshipn≤m;Order
Represent matching double points Coordinate figure;
Step 6: calculate projective transformation, step based on the matching relationship between the corrected some set that step 5 obtains
As follows:
A () makes Order Order Here, 4 parameters in β are fixed
Justice is: s is scaling ratio, and α is the anglec of rotation, δxAnd δyIt is the translational movement of X and Y-axis respectively;
B () seeks the least square solution of A β=b, obtain β=(ATA)-1ATb;
Step 7: between two width images, similarity is defined as P={P1,P2,…,PKAnd Q={Q1,Q2,…,QLPhase between }
Like degree, calculation procedure is as follows:
A () utilizes formula To { Q1,Q2,…,QLConvert, if QjWarp
Cross the coordinate figure that obtains of conversion and be designated as T (Qj), j=1,2 ..., L;
(b) some set P={P1,P2,…,PKAnd Q={Q1,Q2,…,QLSimilarity between } is defined as
In above formula: function T ' is threshold value, here t '=30 set in advance;d(Pi,T(Qj))
Represent PiWith T (Qj) Euclidean distance between 2, i=1,2 ..., K, j=1,2 ..., L;
Step 8: set the image having S width to prestore in image library, repeated execution of steps 2 to step 7, calculate each image respectively
With the similarity of input picture, according to arest neighbors principle of classification, arrange according in similarity Sequential output image library from big to small
Image in front T position is as identifying or the result of retrieval, T≤S.
Step 1 and step 2 in embodiment 1 have employed a kind of characteristics of image point extracting method realization figure that inventor proposes
As pretreatment, extracting the skeletal point of bianry image here as characteristic point, circular is as follows:
Step 1: use the gaussian kernel wave filter of 7 × 7 that image is smoothed, Gauss kernel parameter selection σ=2 here;
Step 2: the binarization method using inventor to propose turns to 1 and 0,1 and 0 point to by each pixel two-value of image
Biao Shi foreground point and background dot;
Step 3: bianry image carries out endpoint detections, and marginal point is defined as the pixel value not phase of two consecutive points here
Deng point;
Step 4: for each marginal point, finding the pixel value comprising this marginal point is 1 vertical and horizontal straight line continuously
Section, the midpoint making shorter in vertical and horizontal straightway one is skeletal point;
Step 5: other skeletal point comprised in deleting the certain radius of each skeletal point, radius value takes 1 here, if one
Individual skeletal point has been deleted, and will no longer scan it in subsequent step.
The concrete calculation procedure of the binarization method described in the step 2 of characteristics of image point extracting method recited above is such as
Under:
Step 21: assume that image has n pixel, is ranked up obtaining c by the gray value of all for image pixels1≤c2
≤,…,≤cn;
Step 22: make xi=i and yi=ci, i=1 here, 2 ..., n;Make t=c1;
Step 23: for i=1,2 ..., n: calculate point (xi,yi) to distance d of certain straight linei, straight line referred herein by
Point (x1,y1) and point (xI,yI) determine;
Step 24: make j=1;Make I=min{i | ci>0};Make tj=cI;Make rj=(n-I)/n;
Step 25: for j=2,3: ordertj=cI, rj=(n-I)/n;
Step 26: for j=3,2,1: if rjMore than certain threshold value r set in advance, take r=2% here, then make t=tj;
Step 27: for i=1,2 ..., n: if ci>=t, makes bi=1;Otherwise, b is madei=0;Here b1,b2,…,bnRepresent
The pixel value of each point after image binaryzation.
The method described based on embodiment 1 devises Symbol recognition program, and to GREC2003 image library (http:// www.iapr-tc10.org) tested, test 6900 width images altogether, it addition, with other two kinds of feature extracting method generations
Having carried out contrast experiment for the feature extracting method implementing 1 employing, respectively [poplar is long-standing: Yi Zhongtong for both feature extracting methods
The character description method for Symbol recognition, patent of invention, authorize the time: on February 6th, 2008, authorize country origin: China,
Grant number: 200410016733.0] and [S.Belogie, J.Malik, J.Puzicha: " Shape matching and
object recognition using shape contexts,IEEE Transactions on Pattern Analysis
and Machine Intelligence”,Volume 24,pp.509-52,2002】.In experimental result, PLC and SC generation respectively
Table above two feature extracting method, SSC represents the feature extracting method that embodiment 1 uses, and experimental result is as follows:
Table 1: discrimination (%) (50 kinds of models of ideal image;Rank 1:5 kind symbol, 5 width images;Rank 2:20 kind accords with
Number, 20 width images;Rank 3:50 kind symbol, 50 kinds of images)
PLC | SSC | SC | |
Rank 1 | 100 | 100 | 100 |
Rank 2 | 100 | 100 | 100 |
Rank 3 | 100 | 100 | 100 |
Table 2: rotate and discrimination (%) (50 kinds of models of the image that stretches;Rank 1:5 kind symbol, 25 width images;Rank 2:
20 kinds of symbols, 100 width images;Rank 3:50 kind symbol, 250 width images)
Table 3: discrimination (%) (50 kinds of models of deformation pattern;Rank 1:5 kind symbol, 25 width images;Rank 2:15 kind accords with
Number, 75 width images)
Table 4: noise jamming hypograph discrimination (%) (rank 1:5 kind model, 5 kinds of symbols, 25 width images;Rank 2:20 kind
Model, 20 kinds of symbols, 100 width images;Rank 3:50 kind model, 50 kinds of symbols, 250 width images)
Table 5: the image recognition rate (%) (15 kinds of models, 15 kinds of symbols, 75 width images) when noise and deformation occur simultaneously
Claims (1)
1. one kind for images match, the bearing calibration of some sets match that identifies, retrieve, it is characterised in that comprise adjacency matrix
Calculate and two parts of maximal clique problem approximate solution in graph theory;Wherein:
The step that described adjacency matrix calculates is as follows:
A () assumes two some set P={P1,P2,…,PmAnd Q={Q1,Q2,…,QmMatching relationship initial between } is Will abut against matrix initialisation is C={cij=0 | i, j=1,2 ..., m};
B () calculates F={rij=d (Pi,Pj)/d(Qi,Qj) | i, j=1,2 ..., m;i≠j};Here d (Pi,Pj) represent some PiWith
Point PjBetween Euclidean distance, d (Qi,Qj) represent some QiWith a QjBetween Euclidean distance;
C () is by { rij=d (Pi,Pj)/d(Qi,Qj) | i, j=1,2 ..., m;I ≠ j} sorts according to order from small to large and obtains R1
≤R2≤…≤Rm(m-1);By RkLocation records in F be S [k] ∈ (i, j) | i, j=1,2 ..., m;I ≠ j}, k=1,
2,…,m(m-1);Here, Rk=rijTime, k is RkSubscript, (i j) is rijSubscript, it is right that S [k] have recorded between subscript
Should be related to, so available { the R of record1,R2,…,Rm(m-1)And { rij| i, j=1,2 ..., m;Between the member of i ≠ j} one
One corresponding relation;
D () is by R1≤R2≤…≤Rm(m-1)Segmentation, segmentation method is as follows: if there is n-1 section, is designated as I under its border is corresponding
[1]=1, I [2], I [3] ..., I [n-1], I [n]=m (m-1) and meet condition RI[i]/RI[i+1]>t∧RI[i]/RI[i+1]+1≤
T, here i=1,2 ..., n-1, t be one close to 1 threshold value, then with I [1]=1, I [2], I [3] ..., I [n-1], I [n] are
Border carries out segmentation;
(e) from above-mentioned steps obtain to R1≤R2≤…≤Rm(m-1)N-1 segmentation in find the longest one section, it is at n-1
Corresponding order in individual segmentation isExtract this section corresponding subscript in F
S [k] | k=I [i*],I[i*]+1,…,I[i*+1]};
F () makes the value of adjacency matrix in step (a) be { cS[k]=1 | k=I [i*],I[i*]+1,…,I[i*+1]};Here, S
Step (c) is shown in the definition of [k];
In described graph theory, the calculation procedure of maximal clique problem approximate solution is as follows:
(A) the lower target set of all nodes of a complete graph is initialized as Θ=1,2 ..., m};By noise node pair
The lower target set answered is initialized as null set Ψ=Φ, by outside noise node residue node set be initialized as Ω=
Θ;
(B) enumerator is setHow many nodes are had to be connected with node i for record;
(C) for i=1,2 ..., m: if vi=0, node i is added the set of noise node, i.e. Ψ ∪ { i} → Ψ;Simultaneously
Node is deleted from the set omega of residue node, i.e. Ω-{ i} → Ω;
(D) if vi=vjArbitrary i ≠ j is set up, here i ∈ Ω and j ∈ Ω, then willIt is designated as Ω under in be comprised
The Corresponding matching point of element is to output and exits;Otherwise forward step (E) to;
(E) node with Smallest connection limit number is found in ΩMake Ψ ∪ { i ' } → Ψ and Ω-
{i′}→Ω;Find the node being connected with node i ', i.e. Γ=j | ci′j=1;J=1,2 ..., m};For j ∈ Γ, make vj-
1→vj;Forward step (D) to.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310688861.9A CN103679201B (en) | 2013-12-14 | 2013-12-14 | Calibration method of point set matching for image matching, recognition and retrieval |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310688861.9A CN103679201B (en) | 2013-12-14 | 2013-12-14 | Calibration method of point set matching for image matching, recognition and retrieval |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103679201A CN103679201A (en) | 2014-03-26 |
CN103679201B true CN103679201B (en) | 2017-01-11 |
Family
ID=50316689
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310688861.9A Expired - Fee Related CN103679201B (en) | 2013-12-14 | 2013-12-14 | Calibration method of point set matching for image matching, recognition and retrieval |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103679201B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109117854B (en) * | 2018-07-25 | 2021-01-29 | 北京达佳互联信息技术有限公司 | Key point matching method and device, electronic equipment and storage medium |
CN113343017B (en) * | 2021-06-10 | 2022-12-02 | 浙江大华技术股份有限公司 | Method and device for determining similarity of image feature points |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6526170B1 (en) * | 1993-12-14 | 2003-02-25 | Nec Corporation | Character recognition system |
CN1506903A (en) * | 2002-12-06 | 2004-06-23 | 中国科学院自动化研究所 | Automatic fingerprint distinguishing system and method based on template learning |
-
2013
- 2013-12-14 CN CN201310688861.9A patent/CN103679201B/en not_active Expired - Fee Related
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6526170B1 (en) * | 1993-12-14 | 2003-02-25 | Nec Corporation | Character recognition system |
CN1506903A (en) * | 2002-12-06 | 2004-06-23 | 中国科学院自动化研究所 | Automatic fingerprint distinguishing system and method based on template learning |
Non-Patent Citations (1)
Title |
---|
基于二维近邻保持嵌入的图像识别;张大明;《模式识别与人工智能》;20111231;第24卷(第6期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN103679201A (en) | 2014-03-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Yuan et al. | Dual-clustering-based hyperspectral band selection by contextual analysis | |
Aldoma et al. | Multimodal cue integration through hypotheses verification for rgb-d object recognition and 6dof pose estimation | |
Wang et al. | Motionlets: Mid-level 3d parts for human motion recognition | |
Raviv et al. | Full and partial symmetries of non-rigid shapes | |
CN103679200A (en) | Frequency domain shape description method for image matching, recognition and retrieval | |
Yang et al. | Dual-geometric neighbor embedding for image super resolution with sparse tensor | |
Wu et al. | DSN: A new deformable subnetwork for object detection | |
Lei et al. | Orthogonal locally discriminant spline embedding for plant leaf recognition | |
Pickup et al. | Euclidean-distance-based canonical forms for non-rigid 3D shape retrieval | |
Liao et al. | Feature matching and position matching between optical and SAR with local deep feature descriptor | |
Liu et al. | Motion consistency-based correspondence growing for remote sensing image matching | |
Tortorici et al. | Convolution operations for relief-pattern retrieval, segmentation and classification on mesh manifolds | |
Haque et al. | Plant recognition system using leaf shape features and Minimum Euclidean distance. | |
CN103679201B (en) | Calibration method of point set matching for image matching, recognition and retrieval | |
Haindl et al. | Model-based texture segmentation | |
CN112381144A (en) | Heterogeneous deep network method for non-European and European domain space spectrum feature learning | |
Tu et al. | Texture pattern separation for hyperspectral image classification | |
Versteegen et al. | Texture modelling with nested high-order Markov–Gibbs random fields | |
Wang et al. | Unified detection of skewed rotation, reflection and translation symmetries from affine invariant contour features | |
Ahmad et al. | Robust detection and affine rectification of planar homogeneous texture for scene understanding | |
Santellani et al. | Md-net: Multi-detector for local feature extraction | |
He et al. | Beyond ${\chi^ 2} $ Difference: Learning Optimal Metric for Boundary Detection | |
Akagündüz et al. | 3D object recognition from range images using transform invariant object representation | |
CN104573727A (en) | Dimension reduction method of handwritten digital image | |
Astono et al. | [Regular Paper] Adjacent Network for Semantic Segmentation of Liver CT Scans |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20190704 Address after: Room 1103, Building 21, 39 Jibang Road, Zhongming Town, Shanghai 202163 Patentee after: SHANGHAI JILIAN NETWORK TECHNOLOGY Co.,Ltd. Address before: 200433 No. 220, Handan Road, Shanghai, Yangpu District Patentee before: Fudan University |
|
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170111 Termination date: 20211214 |