CN108009595A - A kind of image-recognizing method of feature based stipulations - Google Patents
A kind of image-recognizing method of feature based stipulations Download PDFInfo
- Publication number
- CN108009595A CN108009595A CN201711421049.4A CN201711421049A CN108009595A CN 108009595 A CN108009595 A CN 108009595A CN 201711421049 A CN201711421049 A CN 201711421049A CN 108009595 A CN108009595 A CN 108009595A
- Authority
- CN
- China
- Prior art keywords
- feature
- mrow
- characteristic
- stipulations
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
Abstract
The present invention relates to a kind of image-recognizing method of feature based stipulations:The problem of big is taken for feature redundancy present in the characteristics of image description based on local feature description's and memory space, using the thinking of feature stipulations, feature division, slip gauge are carried out to image about first and is merged, cluster stipulations are carried out again, form the character representation of image, so as to carry out classification learning and identification using grader, the present invention can effectively improve the compactness of feature, the memory space of feature is reduced, so as to improve performance of the local feature in the problems such as image retrieval, images match.
Description
Technical field
The present invention relates to a kind of image-recognizing method of feature based stipulations, for fields such as video monitoring, image retrievals.
Background technology
Image recognition is a kind of typical case in computer vision.With the development of computer vision technique, increasingly
More carries out image recognition in the case where resource is limited using hope, and since feature becomes increasingly complex, feature is carried out
Necessary stipulations become extremely important.
Feature stipulations generally have two class main methods, and one kind is to carry out dimension in itself to feature about to subtract, and another kind is to more
Kind compound characteristics description carries out redundancy elimination.Pass through feature stipulations so that the feature description to image is compacter, so as to be beneficial to
Stored and accelerate to analyze.
About subtract aspect in intrinsic dimensionality, mainly including two kinds of linear dimensionality reduction and Nonlinear Dimension Reduction.Principal component analysis (PCA) is
A kind of common feature dimension reduction method, its basic thought are that high dimensional data is mapped to a principal component sky by orthogonal transformation
Between in.Linear discriminant analysis (LDA) is also a kind of common dimension reduction method.Different from PCA, the main purpose of LDA is to make dimensionality reduction
Data point afterwards is easily distinguished as far as possible, and PCA is then the data message kept as far as possible before and after dimensionality reduction.Linear dimensionality reduction leads to
Often assume that mapping of the data from higher dimensional space to lower dimensional space is linear, but this cannot be expired sometimes in practical situations
Foot.Nonlinear Dimension Reduction can preferably adapt to the needs of actual task.Dimension reduction method based on geo-nuclear tracin4 (kerneltrick) is
A kind of common Method of Nonlinear Dimensionality Reduction.Core principle component analysis (KPCA) is the nonlinear extensions to linear PCA algorithm, in order to more
Good processing nonlinear data, KPCA introduce nonlinear mapping function, the data in former space are mapped to higher dimensional space.
Compound characteristics are carried out with redundancy elimination, common method is to carry out feature selecting.L1 regularizations feature selecting utilizes
L1 norms have an openness characteristic, so as to become the characteristic for so having and eliminating redundancy.In addition, some are returned based on logarithm probability
The method of core random forest, then carry out redundancy elimination by the method for marking to feature.
Although various methods have a different advantages, above method there are the problem of be not reflect characteristic point in image
In the regularity of distribution geometrically.Different from above method, the method for the present invention take into account several regularities of distribution of characteristic point, and
Calculating speed is faster.
The content of the invention
The technology of the present invention solves the problems, such as:In place of overcome the deficiencies in the prior art, there is provided a kind of feature based stipulations
Image-recognizing method, this method can reduce the dimension of feature and reflect that local feature in the regularity of distribution geometrically, is counted at the same time
Calculate simply, Project Realization is easy.
The present invention technical solution be:A kind of scene recognition method of feature based stipulations, comprises the following steps:
(1) to image zooming-out SIFT feature, division and merging characteristic block region, all characteristic block areas in image are obtained
Domain;
(2) to all characteristic block regions in image, block feature stipulations are carried out;
(3) to the characteristic point after block feature stipulations, hierarchical clustering stipulations are carried out, the joint for generating feature represents;
(4) joint of feature is represented to carry out the Feature Dimension Reduction based on metric matrix;
(5) input using dimensionality reduction union feature as SVM classifier, training grader, obtains point for image recognition
Class device parameter, the image recognition processes of feature based stipulations so as to complete the present invention.
In the step (1), original image is subjected to initial division as the characteristic block area of m 5 × 5 according to network style
Domain, counts the average characteristics dot density in m characteristic block region, is denoted as
Wherein, niIt is the quantity of characteristic point in ith feature block region.Since the upper left position of image, according to from
Left-to-right direction from top to bottom scans for, and is less than for characteristic point quantityCharacteristic block region, according to from the right side under
Order merges itself and adjacent characteristic block region, and the characteristic block region after merging is equal to or more thanThen jump to
Next characteristic block region do not searched for carries out same operation, until all characteristic block regions are complete merging behaviour
Make.
In the step (2), for multiple characteristic points present in a characteristic block, the purpose of block provincial characteristics stipulations is
Most representational characteristic point in current block is found, block feature stipulations method is, for all in the i of any one region
SIFT feature, finds a characteristic point x of SIFT feature direction amplitude maximumi, as the major feature point of this block, if deposited
In multiple identical maximum amplitude characteristic points, then one is randomly choosed, for all characteristic points in block i, count direction amplitude
With xiDifference is less thanCharacteristic point quantity, be denoted asCharacteristic direction parameter of consistency σ in the i of zoningi, computational methods
It is defined as follows:
After this step, for each characteristic block region i, a major feature point x is obtainedi, and a characteristic direction
Uniformity degree parameter σi, just complete block feature stipulations process;
In the step (3), to a major feature points of all m ', according to characteristic direction parameter of consistency σiCarry out from greatly to
Small sequence, takes σiMaximum a major feature points of n ' as cluster centre,It is nearest to find Euclidean distance around cluster centre
Characteristic point be added in cluster, update cluster centre, then find the characteristic point closest with current cluster centre and be added to
In current cluster, and so on, untill all characteristic points are all assigned in a cluster, a clusters of n ' are obtained at this time
Center vector is that the joint being characterized represents, a cluster centre vector constitutive characteristic matrix Ns of n ';
In the step (4), dimensionality reduction is carried out to eigenmatrix N, first construction random metric Matrix C, it is any in Matrix C
One element c(i,j)Generated according to such as lower probability:
Wherein, p is the probability for generating number;
Dimensionality reduction is carried out to matrix N by crossing random metric matrix again:
Nc=N*C
Wherein, N is the eigenmatrix of a × n ', and a is intrinsic dimensionality, and C is the random measurement matrix of n ' × 64, NcIt is a × 64
Dimensionality reduction joint representing matrix.Obtained NcMatrix is the character representation matrix after dimensionality reduction.
In the step (5), aggregation features vector c as described above is extracted to all training images, is instructed using SVM
Practice, the grader obtained using training carries out image recognition.
The present invention compared with prior art the advantages of be:
(1) present invention takes for feature redundancy present in the characteristics of image description based on local feature and memory space
The problem of big, using thinking of the slip gauge about with level stipulations, improve the compactness of feature, reduce the memory space of feature.
(2) present invention to local feature when stipulations are carried out, it is contemplated that on the space geometry of feature in the picture
The regularity of distribution, and common feature stipulations method does not use space geometry relation then.Compare and other methods, the present invention
Feature stipulations method calculate cost it is relatively low, it is not necessary to carry out extra training process, it is easy to accomplish.
Brief description of the drawings
Fig. 1 is the image recognition flow chart of feature based stipulations of the present invention;
Fig. 2 is the characteristic point distribution map using (right figure) after (left figure) before feature stipulations and feature stipulations.
Embodiment
The present invention is described in detail with reference to the accompanying drawings and embodiments.
As shown in Figure 1, the specific implementation step of the present invention is as follows:
(1) original image is subjected to initial division as the characteristic block region of m 5 × 5 according to according to network style, counts m
The average characteristics dot density in a characteristic block region, is denoted as
Wherein, niIt is the quantity of characteristic point in ith feature block region.Since the upper left position of image, according to from
Left-to-right direction from top to bottom scans for, and is less than for characteristic point quantityCharacteristic block region, according to suitable under from the right side
Sequence merges itself and adjacent characteristic block region, and the characteristic block region after merging is equal to or more thanThen jump to down
One characteristic block region do not searched for carries out same operation, until all characteristic block regions are complete union operation.
Finally obtain the characteristic block region after a merging of m '.
(2) for multiple characteristic points present in a characteristic block, the purpose of block provincial characteristics stipulations is to find current block
In most representational characteristic point, block feature stipulations method is, for all SIFT features in the i of any one region,
Find a characteristic point x of SIFT feature direction amplitude maximumi, as the major feature point of this block, if there is multiple identical
Maximum amplitude characteristic point, then randomly choose one, for all characteristic points in block i, count direction amplitude and xiDiffer small
InCharacteristic point quantity, be denoted asCharacteristic direction parameter of consistency σ in the i of zoningi, computational methods are defined as follows
After this step, for each characteristic block region i, a major feature point x is obtainedi, and a characteristic direction
Uniformity degree parameter σi, just complete block feature stipulations process;
(3) to a major feature points of all m ', according to characteristic direction parameter of consistency σiSorted from big to small, take σi
Maximum a major feature points of n ' as cluster centre,The nearest characteristic point of Euclidean distance around cluster centre is found to add
Enter into cluster, update cluster centre, then find the characteristic point closest with current cluster centre and be added in current cluster,
The rest may be inferred, untill all characteristic points are all assigned in a cluster, obtains a cluster centre vectors of n ' at this time i.e.
The joint expression being characterized, a cluster centre vector constitutive characteristic matrix Ns of n '.Carry out the local feature distribution before and after feature stipulations
As shown in Fig. 2, characteristic point than comparatively dense, with the presence of redundancy feature point, passes through feature in right figure in image local area in left figure
Than sparse, redundancy feature point is reduced characteristic point after stipulations.
(4) dimensionality reduction is carried out to the eigenmatrix N that a feature vectors of n ' are formed, constructs random metric Matrix C, Matrix C first
In any one element c(i,j)Generated according to such as lower probability:
Wherein, p is the probability for generating number.For example, if intrinsic dimensionality is 3, the number of feature vector is 4, then one
As above the Matrix C of the condition of satisfaction is:
Dimensionality reduction is carried out to matrix N by random metric matrix again:
Nc=N*C
Wherein, N is the eigenmatrix of a × n ', and a is intrinsic dimensionality, and C is the random measurement matrix of n ' × 64, NcIt is a × 64
Dimensionality reduction joint representing matrix.Obtained NcMatrix is the character representation matrix after dimensionality reduction.
(5) all training images extract aggregation features vector c as described above, are trained using SVM, using trained
The grader arrived carries out image recognition.
Experimental verification is carried out on Caltech data sets, contrasts the method without using feature stipulations, the results show uses this
Method after the feature stipulations of invention than it is unused when obtained characteristic point it is less, recognition effect is more preferable.
Method | Average every frame characteristic point quantity | Accuracy of identification |
SIFT+SVM | 289 | 52.1% |
SIFT+ block feature stipulations+SVM | 162 | 53.5% |
SIFT+ block features stipulations+cluster feature stipulations+SVM | 129 | 53.8% |
The content not being described in detail in description of the invention belongs to the prior art known to professional and technical personnel in the field.
Above example is provided just for the sake of the description purpose of the present invention, and is not intended to limit the scope of the present invention.This
The scope of invention is defined by the following claims.The various equivalent substitutions that do not depart from spirit and principles of the present invention and make and repair
Change, should all cover within the scope of the present invention.
Claims (5)
1. a kind of image-recognizing method of feature based stipulations, it is characterised in that comprise the following steps:
The first step, to image zooming-out SIFT feature, division and merging characteristic block region, obtain all characteristic block areas in image
Domain;
Second step, to all characteristic block regions in image, carries out block feature stipulations;
3rd step, to the characteristic point after block feature stipulations, carries out cluster stipulations, and the joint for generating feature represents;
4th step, represents to carry out the Feature Dimension Reduction based on metric matrix to the joint of feature;
5th step, the input using dimensionality reduction union feature as SVM classifier, training grader, obtains point for image recognition
Class device, the image recognition processes of feature based stipulations so as to complete the present invention.
2. the image-recognizing method of feature based stipulations according to claim 1, it is characterised in that:In the first step,
The method in division and merging characteristic block region is as follows:
(1) original image is subjected to initial division as the characteristic block region of m 5 × 5 according to network style, counts m characteristic block
The average characteristics dot density in region, is denoted as
<mrow>
<mover>
<mi>d</mi>
<mo>&OverBar;</mo>
</mover>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<mi>m</mi>
</mfrac>
<msubsup>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>m</mi>
</msubsup>
<msub>
<mi>n</mi>
<mi>i</mi>
</msub>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
Wherein, niIt is the quantity of characteristic point in ith feature block region;
(2) since the upper left position of image, scan for according to direction from left to right from top to bottom, count for feature
Amount is less thanCharacteristic block region, itself and adjacent characteristic block region are merged according to the order from the right side under, until merge
Characteristic block region afterwards is equal to or more thanThen jump to next characteristic block region do not searched for and carry out same operation, directly
Union operation is complete to all characteristic block regions.
3. the image-recognizing method of feature based stipulations according to claim 1, it is characterised in that:In the second step,
Carrying out block feature stipulations process to all characteristic block regions in image is:
(1) for all SIFT features in the i of any one region, a characteristic point x of direction amplitude maximum is foundi, as
The major feature point in this characteristic block region, if there is multiple identical maximum amplitude characteristic points, then randomly chooses one, for
All SIFT features in the i of characteristic block region, count direction amplitude and xiDifference is less thanCharacteristic point quantity, be denoted as
Calculate the characteristic direction parameter of consistency σ in characteristic block region ii, computational methods are as follows:
<mrow>
<msub>
<mi>&sigma;</mi>
<mi>i</mi>
</msub>
<mo>=</mo>
<mfrac>
<mover>
<msub>
<mi>n</mi>
<mi>&iota;</mi>
</msub>
<mo>^</mo>
</mover>
<msub>
<mi>n</mi>
<mi>i</mi>
</msub>
</mfrac>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>2</mn>
<mo>)</mo>
</mrow>
</mrow>
After this step, for each characteristic block region i, a major feature point x is obtainedi, and a characteristic direction uniformity
Spend parameter σi, just complete block feature stipulations process.
4. the image-recognizing method of feature based stipulations according to claim 1, it is characterised in that:In 3rd step,
To the characteristic point after block feature stipulations, the process for carrying out cluster stipulations is as follows:
To a major feature points of all m ', according to characteristic direction parameter of consistency σiSorted from big to small, take σiMaximum n ' is a
Major feature point as cluster centre,Find the nearest characteristic point of Euclidean distance around cluster centre and be added to cluster
In, cluster centre is updated, then find the characteristic point closest with current cluster centre and be added in current cluster, until all
Characteristic point be all assigned in a cluster untill, obtain the joint expression that a cluster centres of n ' vector is characterized at this time,
A cluster centre vector constitutive characteristic matrix Ns of n '.
5. the image-recognizing method of feature based stipulations according to claim 1, it is characterised in that:4th step is right
The joint of feature represents that carrying out the Feature Dimension Reduction process based on metric matrix is:
(1) dimensionality reduction is carried out to eigenmatrix N, first construction random metric Matrix C, any one element c in Matrix C(i,j)Press
Generated according to such as lower probability:
<mrow>
<msub>
<mi>c</mi>
<mrow>
<mo>(</mo>
<mi>i</mi>
<mo>,</mo>
<mi>j</mi>
<mo>)</mo>
</mrow>
</msub>
<mo>=</mo>
<msqrt>
<mn>3</mn>
</msqrt>
<mo>*</mo>
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<mn>0</mn>
<mo>,</mo>
</mrow>
</mtd>
<mtd>
<mrow>
<mi>p</mi>
<mo>=</mo>
<mfrac>
<mn>2</mn>
<mn>3</mn>
</mfrac>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mn>1</mn>
<mo>,</mo>
</mrow>
</mtd>
<mtd>
<mrow>
<mi>p</mi>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<mn>6</mn>
</mfrac>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mo>-</mo>
<mn>1</mn>
<mo>,</mo>
</mrow>
</mtd>
<mtd>
<mrow>
<mi>p</mi>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<mn>6</mn>
</mfrac>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>3</mn>
<mo>)</mo>
</mrow>
</mrow>
Wherein, p is the probability for generating number;
(2) dimensionality reduction is carried out to matrix N by crossing random metric matrix again:
Nc=N*C
Wherein, N is the eigenmatrix of a × n ', and a is intrinsic dimensionality, and C is the random measurement matrix of n ' × 64, NcIt is the drop of a × 64
Tie up joint representing matrix, obtained NcMatrix is the character representation matrix after dimensionality reduction.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711421049.4A CN108009595B (en) | 2017-12-25 | 2017-12-25 | A kind of image-recognizing method of feature based stipulations |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711421049.4A CN108009595B (en) | 2017-12-25 | 2017-12-25 | A kind of image-recognizing method of feature based stipulations |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108009595A true CN108009595A (en) | 2018-05-08 |
CN108009595B CN108009595B (en) | 2018-10-12 |
Family
ID=62061117
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711421049.4A Active CN108009595B (en) | 2017-12-25 | 2017-12-25 | A kind of image-recognizing method of feature based stipulations |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108009595B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111968127A (en) * | 2020-07-06 | 2020-11-20 | 中国科学院计算技术研究所 | Cancer focus area identification method and system based on full-section pathological image |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101197045A (en) * | 2007-12-17 | 2008-06-11 | 电子科技大学 | Image solid matching method and device thereof |
CN103617217A (en) * | 2013-11-20 | 2014-03-05 | 中国科学院信息工程研究所 | Hierarchical index based image retrieval method and system |
CN105427298A (en) * | 2015-11-12 | 2016-03-23 | 西安电子科技大学 | Remote sensing image registration method based on anisotropic gradient dimension space |
CN106156374A (en) * | 2016-09-13 | 2016-11-23 | 华侨大学 | A kind of view-based access control model dictionary optimizes and the image search method of query expansion |
US20160357840A1 (en) * | 2015-06-03 | 2016-12-08 | Fujitsu Limited | Apparatus and method for clustering data in streaming clustering without reducing precision |
-
2017
- 2017-12-25 CN CN201711421049.4A patent/CN108009595B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101197045A (en) * | 2007-12-17 | 2008-06-11 | 电子科技大学 | Image solid matching method and device thereof |
CN103617217A (en) * | 2013-11-20 | 2014-03-05 | 中国科学院信息工程研究所 | Hierarchical index based image retrieval method and system |
US20160357840A1 (en) * | 2015-06-03 | 2016-12-08 | Fujitsu Limited | Apparatus and method for clustering data in streaming clustering without reducing precision |
CN105427298A (en) * | 2015-11-12 | 2016-03-23 | 西安电子科技大学 | Remote sensing image registration method based on anisotropic gradient dimension space |
CN106156374A (en) * | 2016-09-13 | 2016-11-23 | 华侨大学 | A kind of view-based access control model dictionary optimizes and the image search method of query expansion |
Non-Patent Citations (2)
Title |
---|
YAN KE 等: ""PCA-SIFT: A More Distinctive Representation for Local Image Descriptors"", 《COMPUTER VISION AND PATTERN RECOGNITION,CVPR 2004》 * |
夏东 等: ""基于粗糙集近似约简和SIFT特征图像匹配算法"", 《信号处理》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111968127A (en) * | 2020-07-06 | 2020-11-20 | 中国科学院计算技术研究所 | Cancer focus area identification method and system based on full-section pathological image |
Also Published As
Publication number | Publication date |
---|---|
CN108009595B (en) | 2018-10-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11062123B2 (en) | Method, terminal, and storage medium for tracking facial critical area | |
Gilani et al. | Learning from millions of 3D scans for large-scale 3D face recognition | |
US11416710B2 (en) | Feature representation device, feature representation method, and program | |
Kumar et al. | Extraction of informative regions of a face for facial expression recognition | |
CN109118519A (en) | Target Re-ID method, system, terminal and the storage medium of Case-based Reasoning segmentation | |
CN110825899A (en) | Clothing image retrieval method integrating color features and residual network depth features | |
CN110837836A (en) | Semi-supervised semantic segmentation method based on maximized confidence | |
CN105930402A (en) | Convolutional neural network based video retrieval method and system | |
CN104679863A (en) | Method and system for searching images by images based on deep learning | |
CN106778852A (en) | A kind of picture material recognition methods for correcting erroneous judgement | |
CN111310800B (en) | Image classification model generation method, device, computer equipment and storage medium | |
CN105243139A (en) | Deep learning based three-dimensional model retrieval method and retrieval device thereof | |
CN106339719A (en) | Image identification method and image identification device | |
Niu et al. | Fitting‐based optimisation for image visual salient object detection | |
CN113378710A (en) | Layout analysis method and device for image file, computer equipment and storage medium | |
CN111754396A (en) | Face image processing method and device, computer equipment and storage medium | |
CN110751027B (en) | Pedestrian re-identification method based on deep multi-instance learning | |
CN111311702B (en) | Image generation and identification module and method based on BlockGAN | |
CN109657715A (en) | A kind of semantic segmentation method, apparatus, equipment and medium | |
CN114821249A (en) | Vehicle weight recognition method based on grouping aggregation attention and local relation | |
CN110188864B (en) | Small sample learning method based on distribution representation and distribution measurement | |
CN115131803A (en) | Document word size identification method and device, computer equipment and storage medium | |
CN112597399B (en) | Graph data processing method and device, computer equipment and storage medium | |
CN113762041A (en) | Video classification method and device, computer equipment and storage medium | |
CN108009595A (en) | A kind of image-recognizing method of feature based stipulations |
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 |