CN106096661A - Zero sample image sorting technique based on relative priority random forest - Google Patents

Zero sample image sorting technique based on relative priority random forest Download PDF

Info

Publication number
CN106096661A
CN106096661A CN201610465880.9A CN201610465880A CN106096661A CN 106096661 A CN106096661 A CN 106096661A CN 201610465880 A CN201610465880 A CN 201610465880A CN 106096661 A CN106096661 A CN 106096661A
Authority
CN
China
Prior art keywords
attribute
image
class
known class
classification
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
Application number
CN201610465880.9A
Other languages
Chinese (zh)
Other versions
CN106096661B (en
Inventor
乔雪
彭晨
段贺
刘久云
胡岩峰
刘振
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Suzhou Research Institute Institute Of Electronics Chinese Academy Of Sciences
Original Assignee
Suzhou Research Institute Institute Of Electronics Chinese Academy Of Sciences
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Suzhou Research Institute Institute Of Electronics Chinese Academy Of Sciences filed Critical Suzhou Research Institute Institute Of Electronics Chinese Academy Of Sciences
Priority to CN201610465880.9A priority Critical patent/CN106096661B/en
Publication of CN106096661A publication Critical patent/CN106096661A/en
Application granted granted Critical
Publication of CN106096661B publication Critical patent/CN106096661B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/24Classification techniques
    • G06F18/241Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2415Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10Character recognition
    • G06V30/19Recognition using electronic means
    • G06V30/192Recognition using electronic means using simultaneous comparisons or correlations of the image signals with a plurality of references
    • G06V30/194References adjustable by an adaptive method, e.g. learning

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Probability & Statistics with Applications (AREA)
  • Databases & Information Systems (AREA)
  • Multimedia (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Image Analysis (AREA)

Abstract

The present invention proposes a kind of zero sample image sorting technique based on relative priority random forest, attribute sequence score model is set up according to the image that the relativeness between image category and image attributes is unknown classification, the score model that sorted by the attribute of all images trains random forest grader as training sample, and the label of test image is predicted by the random forest grader obtained finally according to the attribute sequence score and training testing image.The method of the present invention is capable of zero sample image classification, and has the advantages such as Classification and Identification rate is high, model stability is strong.

Description

Zero sample image sorting technique based on relative priority random forest
Technology zero territory
The invention belongs to pattern recognition zero territory, a kind of zero sample image classification based on relative priority random forest Method.
Background technology
1.1 0 sample image classification
Zero sample image classification is one of study hotspot of current area of pattern recognition, with traditional image classification problem not It is sorted in, with, zero sample image, the image that test phase classifies and identify and has neither part nor lot in the training of sorter model.Such as Fig. 1 institute Showing, the training stage, marked image covered " Lion ", and " Athletic shoes " and " Polar bear " three classifications are (the most Know classification), and the image of test phase occurs in that " Stiletto " classification (i.e. unknown classification), due to " Stiletto " class Bing Meiyou not participate in the training of grader, therefore grader will be unable to predict its label.Training data and the distribution of test data Difference makes zero sample image classification become extremely difficult learning tasks, but this problem scenes is widely present in calculating The fields such as the classification of machine vision, image, face and speech recognition.In zero sample image classification problem, in order to realize from known class Being clipped to the knowledge migration of unknown classification, disaggregated model is accomplished by building one from low-level image feature to classification mark by perceptual property The bridge signed.
1.2 relative priority study
Perceptual property (also referred to as attribute) refers to can be by artificial mark and the characteristic (example that can observe in the picture As, have wing, dark hair), attribute is broadly divided into two-value property and relative priority, wherein relative priority represent certain piece image with Other images compare the number containing a certain attribute.Owing to from the angle of cognition of the mankind, being often appreciated and understood by things It is to go to treat in the way of comparing, can more accurately express semantic attribute information hence with relative priority.Such as, from figure Can visually see in 2, (a) shows the attribute of significantly " young ", and (c) does not has " young " this attribute, for For (b), then can not describe with " young " or " not young " simply, and can be with the mode accurate description compared For: " (b) is more young than (c) and less young than (a) ".Therefore, relative priority can be more accurate Semantic information is expressed on ground, has stronger iamge description ability and interactive capability, it is possible to effectively downscaled images low-level image feature And the semantic gap between high-level semantics features.
Relative priority is in addition to the above-mentioned size that can be applied to description attribute intensity, additionally it is possible to by manually having Supervise and provide a feedback to grader[And interactively choose the result of image retrieval, thus improve of Active Learning Habit ability.There is research to be mixed with relative priority by two-value property and propose one Spoken attributive classification device so that attribute can be with One more naturally mode describes image.Research is also had to be tied mutually with relative priority learning framework by degree of depth nerve convolutional network Close, to increase the precision of attribute sequence.In nearest research, relative priority is used for solving text and describes and zero sample learning Etc. problem, such as: first, Gaussian distribution model is set up for all of known class;Then, built by artificial selection's known class The Gaussian distribution model of vertical unknown classification;Finally, the method utilizing maximal possibility estimation carries out Tag Estimation to test image.So And, there is certain shortcoming in this method: (1) assumes that all known class images and the unknown equal Gaussian distributed of class image are not Reasonably;(2) owing to needing to select with manually having supervision classification in modeling process, therefore can artificially be led The impact of sight factor thus cause the accuracy of model the highest;(3) there is bigger error in maximum Likelihood, and this also will The accuracy of image classification is impacted.
Summary of the invention
Technical problem solved by the invention is to provide a kind of zero sample image based on relative priority random forest to divide Class method, sets up attribute sequence score mould according to the image that the relativeness between image category and image attributes is unknown classification Type, the score model that sorted by the attribute of all images trains random forest grader as training sample, finally according to test The label of test image is predicted by the random forest grader that the attribute sequence score of image and training obtain.This method It is capable of zero sample image classification, and Classification and Identification rate is high, model stability is strong.
The technical solution realizing the object of the invention is:
Zero sample image sorting technique based on relative priority random forest, comprises the following steps:
Step 1: the low-level image feature of given known class image and class label collection { x1,x2,...,xS;y1,y2,...,yS}、 Low-level image feature collection { the z of unknown class image1,z2,...,zU, the orderly attribute of known class image is to collection { O1,...,OM, known class The like attribute of image is to collection { S1,...,SM, a number T of random tree and sampling percentage rate η, set up majorized function, wherein, S, U, M, T are positive integer, η ∈ (0,1);
Step 2: utilize low-level image feature and the class label collection { x of known class image1,x2,...,xS;y1,y2,...,yS}、 Attribute is to collection { O in order1,...,OMAnd like attribute to collection { S1,...,SMSolving-optimizing function, obtain M attribute sequence letter NumberWherein wmFor projection vector,For wmTransposition, i=1,2 ..., s, m=1,2 ..., M;
Step 3: set up the attribute sequence score model of known class imageAttribute row with unknown class image Sequence score modelAnd form training sample set Ω, all images are positioned in attribute space, wherein,Represent known class image correspondence low-level image feature x respectively1,x2,...,xSAttribute sequence score,Represent unknown class image correspondence low-level image feature z respectively1,z2,...,zUAttribute sequence point;
Step 4: training sample set Ω is carried out T the Bootstrap stochastical sampling that percentage rate is η of sampling, is sampled Sample set Ωt=BootstrapSampling (Ω), t=1,2 ..., T;
Step 5: generation random tree classification device:
Step 5-1: if ΩtIn the classification of all samples identical, then present node is returned as leaf node, and according to sample This class label carrys out this node classification of labelling;Otherwise, step 5-2 is forwarded to;
Step 5-2: randomly choose parameter space subset:Γ(Ωt) it is complete parameter space, Γsubt) it is Γ (Ωt) subset, for each parameter space subset Γsubt), calculate information gain IG (θjt), Optimized parameter to Weak Classifier:J=1,2 ..., | Γsub|, θjRepresent subset Γsubt) In jth classification;
Step 5-3: the current data set making left and right child node is sky:
Step 5-4: according to optimized parameter θ*Calculate Weak Classifier h (ri*) value, if h (ri*)=1, then by (ri, yi) add the data set of left child node: Ω toleftleft∪{(ri,yi)};If h is (ri*)=0, then by (ri,yi) add Data set to right child node: Ωrightright∪{(ri,yi), wherein, riRepresent attribute sequence score, yiRepresent classification Label;
Step 5-5: data set ΩleftAnd ΩrightBecome the child node of this node, these child nodes are repeated respectively to step Rapid 5-1 to 5-4, obtains the t random tree classification device;
Step 6: repetition step 4, to step 5, obtains zero sample image grader based on relative priority random forest TreeRoot1,...,TreeRootT
Step 7: utilize attribute ranking functionsCalculate attribute sequence score r of test image(u)
Step 8: by r(u)Substitute into grader TreeRoot1,...,TreeRootTIn, obtain r(u)Belong to the probability of classification C, Calculate and export the class label of test image.
Further, the zero sample image sorting technique based on relative priority random forest of the present invention, excellent in step 1 Changing function is:
f m i n = 1 2 || w m || 2 2 + C ( Σ i , j ξ i j 2 + Σ i , j γ i j 2 )
s . t . w m T x i ≥ w m T x j + 1 - ξ i j ∀ ( i , j ) ∈ { O 1 , ... , O M } | w m T x i - w m T x j | ≤ γ i j ∀ ( i , j ) ∈ { S 1 , ... , S M } ξ i j ≥ 0 γ i j ≥ 0
Wherein, ξijIt is ordered into attribute to { O1,...,OMNon-negative relaxation factor, γijIt is that like attribute is to { S1,..., SMNon-negative relaxation factor, parameter C is used for weighing maximization Edge Distance and meets attribute to relativeness.
Further, the zero sample image sorting technique based on relative priority random forest of the present invention, step 2 solves Majorized function uses the edge 1/ that will sort | | wm| | maximization, non-negative relaxation factor ξijAnd γijMinimize, thus obtain optimum throwing Shadow vector.
Further, the zero sample image sorting technique based on relative priority random forest of the present invention, step 3 is set up The attribute sequence score model of known class image comprises the following steps:
Step 3-1: by known class of all categories between relation object compare the relation between the image attributes belonging to such;
Step 3-2: calculate the attribute sequence score of all known class images ri (s)The sequence score of every dimensional table diagram picture correspondence attribute;
Step 3-3: the attribute of all known class images sort to be grouped into attribute sequence score model
Further, the zero sample image sorting technique based on relative priority random forest of the present invention is unknown in step 3 Class image sets up relativeness by the relation between attribute and known class, sorts with the attribute that this sets up unknown class image Sub-model, specifically includes following three kinds of situations:
(1) if there is known classM-th attributeWith unknown classM-th attributeSimultaneously Meet:And known classWithIt is and unknown classTwo known class that relative priority sequence is nearest, then scheme As the m-th attribute of model sorts to be divided into:
r m , j ( u ) = 1 2 ( r m , i ( s ) + r m , k ( s ) )
Wherein, i=1,2 ..., I, k=1,2 ..., K, j=1,2 ..., I K, I and K are known class respectivelyWithTotal number of images,It is respectively known classM-th attribute sequence score;
(2) if unknown classIt is in border and there is known classM-th attribute meetThen iconic model M-th attribute sort to be divided into:
r m , j ( u ) = r m , i ( s ) - d m , i ( s )
Wherein, i=1,2 ..., I, j=1,2 ..., I,Represent between the attribute sequence score of training class image Mean difference, Represent the average of m-th attribute,
(3) if unknown classIt is in border and there is known classM-th attribute meetThen iconic model M-th attribute sort to be divided into:
r m , j ( u ) = r m , k ( s ) + d m , k ( s )
Wherein, k=1,2 ..., K, j=1,2 ..., K,
Further, the zero sample image sorting technique based on relative priority random forest of the present invention, r in step 8(u) The probability belonging to classification c is:
p ( c | r ( u ) ) = 1 T Σ t = 1 T p t ( c | r ( u ) )
Wherein, T is a number of random tree, p in forestt(c|r(u)) it is the categorical distribution of leaf node.
Further, the zero sample image sorting technique based on relative priority random forest of the present invention, step 8 is tested The class label of image is:
c ^ = arg max c ∈ { 1 , ... , U } p ( c | r ( u ) ) .
The present invention uses above technical scheme compared with prior art, has following technical effect that
1, the zero sample image sorting technique based on relative priority random forest of the present invention is that each image is individually built Vertical attribute sequence score model so that the model participating in classifier training is the most reasonable and accurate;
2, the zero sample image sorting technique based on relative priority random forest of the present invention automatically selects known class Model is set up, it is to avoid the subjective impact that artificial selection's known class is brought for unknown classification;
3, the zero sample image sorting technique based on relative priority random forest of the present invention uses random forest grader Reduce error in classification, thus improve the accuracy of zero sample image classification;
4, the zero sample image sorting technique Classification and Identification rate based on relative priority random forest of the present invention is high, model is steady Qualitative by force.
Accompanying drawing explanation
Fig. 1 is zero sample image classification schematic diagram;
Fig. 2 is relative priority schematic diagram;
Fig. 3 is zero sample image sorting technique structured flowchart based on relative priority random forest;
Fig. 4 is the flow chart of study attribute ranking functions;
Fig. 5 be ordered into attribute to and like attribute to schematic diagram;
Fig. 6 is attribute ranking functions schematic diagram;
Fig. 7 is the flow chart setting up AR model;
Fig. 8 is the flow chart of training random forest grader;
Fig. 9 is the flow chart of prediction test image category label.
Detailed description of the invention
Embodiments of the present invention are described below in detail, and the example of described embodiment is shown in the drawings, the most ad initio Represent same or similar element to same or similar label eventually or there is the element of same or like function.Below by ginseng The embodiment examining accompanying drawing description is exemplary, is only used for explaining the present invention, and is not construed as limiting the claims.
Zero sample image sorting technique based on relative priority random forest, as it is shown on figure 3, comprise the following steps:
Step 1: such as (1) in Fig. 4, the low-level image feature of given known class image and class label collection { x1,x2,...,xS;y1, y2,...,yS, the low-level image feature collection { z of unknown class image1,z2,...,zU, the orderly attribute of known class image is to collection {O1,...,OM, the like attribute of known class image is to collection { S1,...,SM, a number T of random tree and sampling percentage rate η, its In, S, U, M, T are positive integer, η ∈ (0,1), set up following majorized function:
f m i n = 1 2 || w m || 2 2 + C ( Σ i , j ξ i j 2 + Σ i , j γ i j 2 )
s . t . w m T x i ≥ w m T x j + 1 - ξ i j ∀ ( i , j ) ∈ { O 1 , ... , O M } | w m T x i - w m T x j | ≤ γ i j ∀ ( i , j ) ∈ { S 1 , ... , S M } ξ i j ≥ 0 γ i j ≥ 0
Wherein, ξijIt is ordered into attribute to { O1,...,OMNon-negative relaxation factor, γijIt is that like attribute is to { S1,..., SMNon-negative relaxation factor, parameter C is used for weighing maximization Edge Distance and meets attribute to relativeness.
Concrete principle is as follows:
Given training image collection I={i}, each image characteristic vector xi∈RdRepresent;The given genus with M attribute Property collectionFor each attribute am, given a series of orderly attributes are to Om={ (i, j) } and like attribute are to Sm= (i, j) }, wherein,Represent that image i contains attribute more than image j;Represent image i Similar to image j containing attribute.Fig. 5 be orderly attribute as a example by " laughing at " this attribute to and like attribute to schematic diagram, its In the image attributes intensity of orderly attribute centering in different size, there is certain strong or weak relation, and the figure of like attribute centering As attribute intensity difference is few, there is not attribute strong or weak relation.The purpose of study attribute ranking functions is to obtain M attribute row Order function:
r m ( x i ) = w m T x i
For m=1 ..., M, meet following restriction most possibly:
∀ ( i , j ) ∈ O m : w m T x i > w m T x j
∀ ( i , j ) ∈ S m : w m T x i = w m T x j
Wherein, wmBeing projection vector, therefore, study attribute ranking functions is intended in low-level image feature space find the throwing of optimum Shadow direction so that the projection in the direction of all images has correct sequence.For solving the problems referred to above, introduce non-negative and relax Variable ξijAnd γij, obtain following majorized function:
f m i n = 1 2 || w m || 2 2 + C ( Σ i , j ξ i j 2 + Σ i , j γ i j 2 )
s . t . w m T x i ≥ w m T x j + 1 - ξ i j ∀ ( i , j ) ∈ { O 1 , ... , O M } | w m T x i - w m T x j | ≤ γ i j ∀ ( i , j ) ∈ { S 1 , ... , S M } ξ i j ≥ 0 γ i j ≥ 0
Wherein, ξijIt is ordered into attribute to OmThe non-negative relaxation factor of={ (i, j) }, γijIt is that like attribute is to Sm=(i, J) non-negative relaxation factor }, parameter C is used for weighing maximization Edge Distance and meeting attribute to relativeness.
Step 2: utilize low-level image feature and the class label collection { x of known class image1,x2,...,xS;y1,y2,...,yS}、 Attribute is to collection { O in order1,...,OMAnd like attribute to collection { S1,...,SMSolving-optimizing function, will sort edge 1/ | | wm|| Maximization, non-negative relaxation factor ξijAnd γijMinimize, obtain optimum projection vector, thus obtain M attribute ranking functionsWherein wmFor projection vector,For wmTransposition, i=1,2 ..., s, m=1,2 ..., M.Set up attribute row Order function is actually the function that training image can be sorted by study one exactly, such as Fig. 4 (2), the edge limit of sequence System allows the distance between two images nearest in whole sequence maximum exactly.As shown in Figure 6, the purpose of sequence is by data point (representing with 1,2,3,4,5,6 respectively) preferably sorts, and allows in queue the edge between two nearest data points (2,3) Greatly, therefore ranking functions can preferably represent the relativeness of attribute intensity.
Step 3: set up the attribute sequence score model of known class imageAttribute row with unknown class image Sequence score modelAnd form training sample set Ω, all images are positioned in attribute space, wherein,Represent known class image correspondence low-level image feature x respectively1,x2,...,xSAttribute sequence score,Represent unknown class image correspondence low-level image feature z respectively1,z2,...,zUAttribute sequence point, such as Fig. 7 (3) institute Show.
Assuming that having S class image is known class, having U class image is unknown classification, general by zero sample image classification Reading and understand, the image of S class known class can directly participate in the training of grader, and the image of U class the unknown classification can not be direct Participate in the training of grader, can only appear on the test phase of zero sample image classification, therefore sort at the attribute setting up image During score model, it is known that the method that the image of the image of classification and unknown classification is used is different, and the present invention proposes to adopt Set up using the following method image attribute sequence score model:
Initially set up the attribute sequence score model of known class image, comprise the following steps, such as Fig. 7 (1):
Step 3-1: by known class of all categories between relation object compare the relation between the image attributes belonging to such, That is: for arbitrary attribute amAnd known classWith
Step 3-2: calculate the attribute sequence score of all known class images The sequence score of every dimensional table diagram picture correspondence attribute;
Step 3-3: the attribute of all known class images sort to be grouped into attribute sequence score model
The known class image x thus script d dimensional feature vector representediBy attribute sequence score r of M dimensioniRepresent: xi∈Rd→ri∈RM, wherein,riThe sequence of every dimensional table diagram picture correspondence attribute Score.
Owing to unknown classification can not directly participate in the training process of grader, therefore can not be by same method to unknown class Image be modeled, but, unknown class image sets up relativeness by the relation between attribute and known class, such as " Bears " (unknown classification) is more than " giraffe " (known class) hair, but be not as many as " rabbit " (known class) hair.Such as Fig. 7 (2), specifically come Say, for attribute am, unknown classKnown class can be usedWithPoint following three kinds of situations carry out associated description:
(1) if there is known classM-th attributeWith unknown classM-th attributeSimultaneously Meet:And known classWithIt is and unknown classTwo known class that relative priority sequence is nearest, then scheme As the m-th attribute of model sorts to be divided into:
r m , j ( u ) = 1 2 ( r m , i ( s ) + r m , k ( s ) )
Wherein, i=1,2 ..., I, k=1,2 ..., K, j=1,2 ..., I K, I and K are known class respectivelyWithTotal number of images,It is respectively known classM-th attribute sequence score;
(2) if unknown classIt is in border and there is known classM-th attribute meetThen iconic model M-th attribute sort to be divided into:
r m , j ( u ) = r m , i ( s ) - d m , i ( s )
Wherein, i=1,2 ..., I, j=1,2 ..., I,Represent between the attribute sequence score of training class image Mean difference, Represent the average of m-th attribute,
(3) if unknown classIt is in border and there is known classM-th attribute meetThen iconic model M-th attribute sort to be divided into:
r m , j ( u ) = r m , k ( s ) + d m , k ( s )
Wherein, k=1,2 ..., K, j=1,2 ..., K,
The present invention uses following strategy to automatically select suitable known class and sets up the attribute sequence score mould of unknown class Type: prioritizing selection meetsKnown classWithAndWithIt is and unknown classRelative priority sorts Two near classes;IfIt is in border, does not meetKnown classWithThen select relative priority sequence The highestOr it is minimumTo unknown class modeling.
Step 4: training sample set Ω is carried out T the Bootstrap stochastical sampling that percentage rate is η of sampling, is sampled Sample set Ωt=BootstrapSampling (Ω), t=1,2 ..., T.
Step 5: generate random tree classification device, each joint as shown in Figure 8, in random forest grader, in each tree Point can be regarded as a Weak Classifier, and (the training sample set Ω arriving this node is included known class sample setWith unknown class sample set) it is calculated a sorting criterion h (r | θ) ={ 0,1}, r ∈ RMRepresenting a training sample, θ={ φ, ψ } is the parameter of this Weak Classifier, and wherein φ () is screening Function, ψ is a parameter matrix.
Step 5-1: if ΩtIn the classification of all samples identical, then present node is returned as leaf node, and according to sample This class label carrys out this node classification of labelling;Otherwise, step 5-2 is forwarded to;
Step 5-2: randomly choose parameter space subset:Γ(Ωt) it is complete parameter space, Γsubt) it is Γ (Ωt) subset, for each node ΓsubAll randomly choosing from Γ, this embodies in node split mistake Randomness in journey, to each parameter space subset Γsubt), calculate information gain IG (θjt), information gain is weighed The fall of training sample impurity level after division, can be defined as:
I G ( θ | Ω ) = H ( Ω ) - Σ i ∈ { l e f t , r i g h t } | Ω i ( θ ) | | Ω | H ( Ω i ( θ ) )
H ( Ω ) = - Σ c = 1 N c p ( c | Ω ) l o g p ( c | Ω )
Wherein, NcThe classification number of expression training sample, and p (c | Ω) represent the ratio shared by classification c in training sample set Ω Example,Represent the set of all training samples falling into this node, yiRepresent the label of i-th sample, Ωleft (θ) and Ωright(θ) it is illustrated respectively in parameter θ and falls into the sample set of left and right child node,Represent the unit in set omega Element number, H (Ω) represents the impurity level of the sample set falling into a node, describes by comentropy.
Then the optimized parameter of Weak Classifier is obtained:J=1,2 ..., | Γsub|, θjTable Show subset ΓsubtJth classification in).
It follows that " optimum " parameter θ of each node*Node impurity level fall after cleaving should be made maximum.
Step 5-3: the current data set making left and right child node is sky:
Step 5-4: according to optimized parameter θ*Calculate Weak Classifier h (ri*) value, if h (ri*)=1, then by (ri, yi) add the data set of left child node: Ω toleftleft∪{(ri,yi)};If h is (ri*)=0, then by (ri,yi) add Data set to right child node: Ωrightright∪{(ri,yi), wherein, riRepresent attribute sequence score, yiRepresent classification Label;
Step 5-5: data set ΩleftAnd ΩrightBecome the child node of this node, these child nodes are repeated respectively to step Rapid 5-1 to 5-5, obtains the t random tree classification device, it may be assumed that at each leaf node, is concentrated by statistics training sample and arrives this The rectangular histogram of the tag along sort of leaf node, can estimate the class distribution on this leaf node.Such repetitive exercise process is held always Row is to can not obtaining bigger information gain by continuing division.
Step 6: repetition step 4, to step 5, obtains zero sample image grader based on relative priority random forest TreeRoot1,...,TreeRootT
Step 7: such as Fig. 9, utilize attribute ranking functionsCalculate attribute sequence score r of test image(u), The most all test images are all the images of unknown classification, are not engaged in the training of random forest grader..
Step 8: such as Fig. 9, by r(u)Substitute into grader TreeRoot1,...,TreeRootTIn, random at each iteratively Tree is carried out or the branch of left or right, until arrive each random tree leaf node, on each leaf node classification distribution namely It it is the classification results made of this tree.Classification in each leaf nodes is distributed and is averaged, i.e. can get r(u)Belong to classification The probability of c:Wherein, T is a number of random tree, p in forestt(c|r(u)) it is the class of leaf node It is not distributed.Then calculate and export test image class label:
The above is only the some embodiments of the present invention, it is noted that for the ordinary skill people in this technology zero territory For Yuan, under the premise without departing from the principles of the invention, it is also possible to make some improvement, these improve the guarantor that should be regarded as the present invention Protect scope.

Claims (7)

1. zero sample image sorting technique based on relative priority random forest, it is characterised in that comprise the following steps:
Step 1: the low-level image feature of given known class image and class label collection { x1, x2..., xS;y1, y2..., yS, unknown Low-level image feature collection { the z of class image1, z2..., zU, the orderly attribute of known class image is to collection { O1..., OM, known class image Like attribute to collection { S1..., SM, a number T of random tree and sampling percentage rate η, set up majorized function, wherein, S, U, M, T It is positive integer, η ∈ (0,1);
Step 2: utilize low-level image feature and the class label collection { x of known class image1, x2..., xS;y1, y2..., yS, in order Attribute is to collection { O1..., OMAnd like attribute to collection { S1..., SMSolving-optimizing function, obtain M attribute ranking functionsWherein wmFor projection vector,For wmTransposition, i=1,2 ..., s, m=1,2 ..., M;
Step 3: set up the attribute sequence score model of known class imageSort with the attribute of unknown class image Sub-modelAnd form training sample set Ω, all images are positioned in attribute space, wherein,Represent known class image correspondence low-level image feature x respectively1, x2..., xSAttribute sequence score,Represent unknown class image correspondence low-level image feature z respectively1, z2..., zUAttribute sequence point;
Step 4: training sample set Ω is carried out T the Bootstrap stochastical sampling that percentage rate is η of sampling, obtains sample Collection Ωt=BootstrapSampling (Ω), t=1,2 ..., T;
Step 5: generation random tree classification device:
Step 5-1: if ΩtIn the classification of all samples identical, then present node is returned as leaf node, and according to sample Class label carrys out this node classification of labelling;Otherwise, step 5-2 is forwarded to;
Step 5-2: randomly choose parameter space subset:Γ(Ωt) it is complete parameter space, Γsubt) For Γ (Ωt) subset, for each parameter space subset Γsubt), calculate information gain/G (θjt), obtain weak The optimized parameter of grader:J=1,2 ..., | Γsub|, θjRepresent subset ΓsubtIn) Jth classification;
Step 5-3: the current data set making left and right child node is sky:
Step 5-4: according to optimized parameter θ*Calculate Weak Classifier h (ri*) value, if h (ri*)=1, then by (ri, yi) add Data set to left child node: Ωleftleft∪{(ri, yi)};If h is (ri*)=0, then by (ri, yi) add right sub-joint to The data set of point: Ωrightright∪{(ri, yi), wherein, riRepresent attribute sequence score, yiRepresent class label;
Step 5-5: data set ΩleftAnd ΩrightBecome the child node of this node, 5-is respectively repeated steps for these child nodes 1 to 5-4, obtains the t random tree classification device;
Step 6: repetition step 4, to step 5, obtains zero sample image grader based on relative priority random forest TreeRoot1..., TreeRootT
Step 7: utilize attribute ranking functionsCalculate attribute sequence score r of test image(u)
Step 8: by r(u)Substitute into grader TreeRoot1..., TreeRootTIn, obtain r(u)Belong to the probability of classification C, calculate And export the class label of test image.
Zero sample image sorting technique based on relative priority random forest the most according to claim 1, it is characterised in that Majorized function in step 1 is:
f m i n = 1 2 || w m || 2 2 + C ( Σ i , j ξ i j 2 + Σ i , j γ i j 2 )
s . t . w m T x i ≥ w m T x j + 1 - ξ i j ∀ ( i , j ) ∈ { O 1 , ... , O M } | w m T x i - w m T x j | ≤ γ i j ∀ ( i , j ) ∈ { S 1 , ... , S M } ξ i j ≥ 0 γ i j ≥ 0
Wherein, ξijIt is ordered into attribute to { O1..., OMNon-negative relaxation factor, γijIt is that like attribute is to { S1..., SM? Non-negative relaxation factor, parameter C is used for weighing maximization Edge Distance and meeting attribute to relativeness.
Zero sample image sorting technique based on relative priority random forest the most according to claim 1, it is characterised in that In step 2, solving-optimizing function uses the edge 1/ that will sort | | wm| | maximization, non-negative relaxation factor ξijAnd γijMinimize, from And obtain optimum projection vector.
Zero sample image sorting technique based on relative priority random forest the most according to claim 1, it is characterised in that The attribute sequence score model setting up known class image in step 3 comprises the following steps:
Step 3-1: by known class of all categories between relation object compare the relation between the image attributes belonging to such;
Step 3-2: calculate the attribute sequence score of all known class images 's The sequence score of every dimensional table diagram picture correspondence attribute;
Step 3-3: the attribute of all known class images sort to be grouped into attribute sequence score model
Zero sample image sorting technique based on relative priority random forest the most according to claim 1, it is characterised in that In step 3, unknown class image sets up relativeness by the relation between attribute and known class, sets up unknown class image with this Attribute sequence score model, specifically include following three kinds of situations:
(1) if there is known classM-th attributeWith unknown classM-th attributeMeet simultaneously:And known classWithIt is and unknown classTwo known class that relative priority sequence is nearest, then image mould The m-th attribute of type sorts to be divided into:
r m , j ( u ) = 1 2 ( r m , i ( s ) + r m , k ( s ) )
Wherein, i=1,2 ..., I, k=1,2 ..., K, j=1,2 ..., I K, I and K are known class respectivelyWithFigure As sum,It is respectively known classM-th attribute sequence score;
(2) if unknown classIt is in border and there is known classM-th attribute meetThen the of iconic model M attribute sorts to be divided into:
r m , j ( u ) = r m , i ( s ) - d m , i ( s )
Wherein, i=1,2 ..., I, j=1,2 ..., I,Represent training class image attribute sequence score between average Difference, Represent the average of m-th attribute,
(3) if unknown classIt is in border and there is known classM-th attribute meetThen the of iconic model M attribute sorts to be divided into:
r m , j ( u ) = r m , k ( s ) + d m , k ( s )
Wherein, k=1,2 ..., K, j=1,2 ..., K,
Zero sample image sorting technique based on relative priority random forest the most according to claim 1, it is characterised in that R in step 8(u)The probability belonging to classification c is:
p ( c | r ( u ) ) = 1 T Σ t = 1 T p t ( c | r ( u ) )
Wherein, T is a number of random tree, p in forestt(c|r(u)) it is the categorical distribution of leaf node.
Zero sample image sorting technique based on relative priority random forest the most according to claim 6, it is characterised in that The class label testing image in step 8 is:
c ^ = arg max c ∈ { 1 , ... , U } p ( c | r ( u ) ) .
CN201610465880.9A 2016-06-24 2016-06-24 The zero sample image classification method based on relative priority random forest Active CN106096661B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610465880.9A CN106096661B (en) 2016-06-24 2016-06-24 The zero sample image classification method based on relative priority random forest

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610465880.9A CN106096661B (en) 2016-06-24 2016-06-24 The zero sample image classification method based on relative priority random forest

Publications (2)

Publication Number Publication Date
CN106096661A true CN106096661A (en) 2016-11-09
CN106096661B CN106096661B (en) 2019-03-01

Family

ID=57252659

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610465880.9A Active CN106096661B (en) 2016-06-24 2016-06-24 The zero sample image classification method based on relative priority random forest

Country Status (1)

Country Link
CN (1) CN106096661B (en)

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107563444A (en) * 2017-09-05 2018-01-09 浙江大学 A kind of zero sample image sorting technique and system
WO2018161217A1 (en) * 2017-03-06 2018-09-13 Nokia Technologies Oy A transductive and/or adaptive max margin zero-shot learning method and system
CN109886289A (en) * 2019-01-08 2019-06-14 深圳禾思众成科技有限公司 A kind of deep learning method, equipment and computer readable storage medium
CN110704662A (en) * 2019-10-17 2020-01-17 广东工业大学 Image classification method and system
CN111079468A (en) * 2018-10-18 2020-04-28 珠海格力电器股份有限公司 Method and device for robot to recognize object
CN111126049A (en) * 2019-12-14 2020-05-08 中国科学院深圳先进技术研究院 Object relation prediction method and device, terminal equipment and readable storage medium
CN111612047A (en) * 2020-04-29 2020-09-01 杭州电子科技大学 Zero sample image identification method based on attribute feature vector and reversible generation model
CN111783531A (en) * 2020-05-27 2020-10-16 福建亿华源能源管理有限公司 Water turbine set fault diagnosis method based on SDAE-IELM
CN112257765A (en) * 2020-10-16 2021-01-22 济南大学 Zero sample image classification method and system based on unknown similarity class set
CN112990161A (en) * 2021-05-17 2021-06-18 江苏数兑科技有限公司 Electronic certificate identification method and device

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101923650A (en) * 2010-08-27 2010-12-22 北京大学 Random forest classification method and classifiers based on comparison mode
CN103473231A (en) * 2012-06-06 2013-12-25 深圳先进技术研究院 Classifier building method and system
CN105512679A (en) * 2015-12-02 2016-04-20 天津大学 Zero sample classification method based on extreme learning machine

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101923650A (en) * 2010-08-27 2010-12-22 北京大学 Random forest classification method and classifiers based on comparison mode
CN103473231A (en) * 2012-06-06 2013-12-25 深圳先进技术研究院 Classifier building method and system
CN105512679A (en) * 2015-12-02 2016-04-20 天津大学 Zero sample classification method based on extreme learning machine

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
DINESH JAYARAMAN ET AL.: "Zero-Shot Recognition with Unreliable Attributes", 《PROCEEDINGS OF ADVANCES IN NEURAL PROCESSING SYSTEMS》 *
MINGXIA LIU ET AL.: "Attributerelationlearningforzero-shotclassification", 《NEUROCOMPUTING》 *

Cited By (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018161217A1 (en) * 2017-03-06 2018-09-13 Nokia Technologies Oy A transductive and/or adaptive max margin zero-shot learning method and system
CN107563444A (en) * 2017-09-05 2018-01-09 浙江大学 A kind of zero sample image sorting technique and system
CN111079468A (en) * 2018-10-18 2020-04-28 珠海格力电器股份有限公司 Method and device for robot to recognize object
CN111079468B (en) * 2018-10-18 2024-05-07 珠海格力电器股份有限公司 Method and device for identifying object by robot
CN109886289A (en) * 2019-01-08 2019-06-14 深圳禾思众成科技有限公司 A kind of deep learning method, equipment and computer readable storage medium
CN110704662A (en) * 2019-10-17 2020-01-17 广东工业大学 Image classification method and system
CN111126049B (en) * 2019-12-14 2023-11-24 中国科学院深圳先进技术研究院 Object relation prediction method, device, terminal equipment and readable storage medium
CN111126049A (en) * 2019-12-14 2020-05-08 中国科学院深圳先进技术研究院 Object relation prediction method and device, terminal equipment and readable storage medium
CN111612047A (en) * 2020-04-29 2020-09-01 杭州电子科技大学 Zero sample image identification method based on attribute feature vector and reversible generation model
CN111612047B (en) * 2020-04-29 2023-06-02 杭州电子科技大学 Zero sample image recognition method based on attribute feature vector and reversible generation model
CN111783531B (en) * 2020-05-27 2024-03-19 福建亿华源能源管理有限公司 Water turbine set fault diagnosis method based on SDAE-IELM
CN111783531A (en) * 2020-05-27 2020-10-16 福建亿华源能源管理有限公司 Water turbine set fault diagnosis method based on SDAE-IELM
CN112257765B (en) * 2020-10-16 2022-09-23 济南大学 Zero sample image classification method and system based on unknown similarity class set
CN112257765A (en) * 2020-10-16 2021-01-22 济南大学 Zero sample image classification method and system based on unknown similarity class set
CN112990161A (en) * 2021-05-17 2021-06-18 江苏数兑科技有限公司 Electronic certificate identification method and device

Also Published As

Publication number Publication date
CN106096661B (en) 2019-03-01

Similar Documents

Publication Publication Date Title
CN106096661B (en) The zero sample image classification method based on relative priority random forest
CN108154134B (en) Pornographic image detection method is broadcast live in internet based on depth convolutional neural networks
CN106897738B (en) A kind of pedestrian detection method based on semi-supervised learning
Pandey et al. A decision tree algorithm pertaining to the student performance analysis and prediction
CN108388927A (en) Small sample polarization SAR terrain classification method based on the twin network of depth convolution
CN109635668B (en) Facial expression recognition method and system based on soft label integrated convolutional neural network
CN110533606B (en) Security inspection X-ray contraband image data enhancement method based on generative countermeasure network
CN108875816A (en) Merge the Active Learning samples selection strategy of Reliability Code and diversity criterion
CN108961245A (en) Picture quality classification method based on binary channels depth parallel-convolution network
CN102314614B (en) Image semantics classification method based on class-shared multiple kernel learning (MKL)
CN106228183A (en) A kind of semi-supervised learning sorting technique and device
CN101667245B (en) Human face detection method by cascading novel detection classifiers based on support vectors
CN106203487A (en) A kind of image classification method based on Multiple Kernel Learning Multiple Classifier Fusion and device
CN104657718A (en) Face recognition method based on face image feature extreme learning machine
CN109816032A (en) Zero sample classification method and apparatus of unbiased mapping based on production confrontation network
CN104702465B (en) A kind of parallel network flow sorting technique
CN110132263A (en) A kind of method for recognising star map based on expression study
CN107729312A (en) More granularity segmenting methods and system based on sequence labelling modeling
CN114998220B (en) Tongue image detection and positioning method based on improved Tiny-YOLO v4 natural environment
CN106127247A (en) Image classification method based on multitask many examples support vector machine
CN110688888B (en) Pedestrian attribute identification method and system based on deep learning
CN112487290B (en) Internet accurate teaching method and system based on big data and artificial intelligence
CN111709477A (en) Method and tool for garbage classification based on improved MobileNet network
CN106227836B (en) Unsupervised joint visual concept learning system and unsupervised joint visual concept learning method based on images and characters
CN108595558A (en) A kind of image labeling method of data balancing strategy and multiple features fusion

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant