CN110175588A - A kind of few sample face expression recognition method and system based on meta learning - Google Patents
A kind of few sample face expression recognition method and system based on meta learning Download PDFInfo
- Publication number
- CN110175588A CN110175588A CN201910465071.1A CN201910465071A CN110175588A CN 110175588 A CN110175588 A CN 110175588A CN 201910465071 A CN201910465071 A CN 201910465071A CN 110175588 A CN110175588 A CN 110175588A
- Authority
- CN
- China
- Prior art keywords
- sample
- expression recognition
- facial
- master cast
- meta learning
- 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
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/174—Facial expression recognition
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The present disclosure proposes a kind of few sample face expression recognition method and system based on meta learning, comprising: receive facial sample set, carry out data prediction；Construct the master cast of Expression Recognition；Facial sample set is divided based on the method for meta learning: for seven class expressions, randomly choosing three classes expression and is used for training set, then random selection three classes expression is used for testing set in remaining four class expressions；Using the method construct C-way K-shot of episode-based, i.e., sample set and query set are constructed using ready-portioned training set；The facial sample set constructed is inputted into master cast, parameter optimization is carried out to master cast；Face data to be identified is received, human facial expression recognition is carried out according to the master cast after optimization.The disclosure mainly considers few sample face Expression Recognition problem based on meta learning, using the Research on Methods training set of episode-based, constructs a convolutional neural networks and extracts the knowledge of transferability to realize the identification to expression.
Description
Technical field
This disclosure relates to the image identification technical field of computer vision, more particularly to a kind of few sample based on meta learning
This human facial expression recognition method and system.
Background technique
With the development of artificial intelligence and depth learning technology, human facial expression recognition is critically important as field of image recognition
Problem is receive more and more attention.Facial expression is that people convey own emotions and are intended to most advantageous, most natural, most universal
One of signal, and human facial expression recognition be based on face seven kinds of expressions (it is angry, detest, fear, it is glad, sad, startled and
It is neutral) determine the emotion of people.Human facial expression recognition has been achieved for very big progress, extensively as one of depth learning technology
It is general to be applied to many fields such as Psychology analysis, medical diagnosis, analysis of advertising results.
Inventor has found under study for action, in recent years depth learning technology computer vision field achieve it is very big into
Step, such as target detection, image segmentation and image classification.Deep neural network can be mentioned automatically from input picture end to end
High-level semantics feature is taken, is considered as most possibly close to one of artificial intelligence technology of human levels.And these supervision are learned
The data and multiple iteration that model needs largely to have label are practised thus a large amount of model parameter of training.Due to label for labelling
It takes time and effort, scalability when which limits in face of new classification.Importantly, due to emerging or rare class
It does not mark sample largely, and limits application.So how preferably to have exemplar training one using a small amount of
The disaggregated model that a accuracy of identification is high, Generalization Capability is good is a meaningful research direction, i.e. the research of sample problem less.
Few sample learning problem typically contains three data sets: training set, support set, query set,
For C class sample is contained in support set, and every class sample contains K sample, referred to as C-way K-shot problem.Phase
Instead, the mankind are good at identifies target in the case where not direct supervision message very much, does not occur previously even
Classification, this is the ability of the congenital meta learning having of the mankind.
Summary of the invention
The purpose of this specification embodiment is to provide a kind of few sample face expression recognition method based on meta learning, benefit
It can use considerably less training sample with the trained model of disclosure this method, reach satisfied accuracy of identification, to solve
Training pattern of having determined needs largely have an exemplar to take time and effort problem.
This specification embodiment provides a kind of few sample face expression recognition method based on meta learning, passes through following skill
Art scheme is realized:
Include:
Facial sample set is received, data prediction is carried out；
Construct the master cast of Expression Recognition；
Method based on meta learning divides data set: for seven class expressions, randomly choosing three classes expression and is used for
Training set, then random selection three classes expression is used for testing set in remaining four class expressions；
Using the method construct C-way K-shot of episode-based, that is, utilize ready-portioned training set structure
Make sample set and query set；
The facial sample set constructed is inputted into master cast, parameter optimization is carried out to master cast；
Face data to be identified is received, human facial expression recognition is carried out according to the master cast after optimization.
This specification embodiment provides a kind of few sample face Expression Recognition system based on meta learning, passes through following skill
Art scheme is realized:
Include:
Data preprocessing module is configured as: being received facial sample set, is carried out data prediction；
Master cast constructs module, is configured as: constructing the master cast of Expression Recognition；
Dataset construction module, is configured as: the method based on meta learning divides data set: for seven class tables
Feelings, random selection three classes expression is used for training set, then random selection three classes expression is used in remaining four class expressions
testing set；
Using the method construct C-way K-shot of episode-based, that is, utilize ready-portioned training set structure
Make sample set and query set；
Master cast optimization module, is configured as: the facial sample set constructed being inputted master cast, is joined to master cast
Number optimization；
Human facial expression recognition module, is configured as: receiving face data to be identified, carries out face according to the master cast after optimization
Portion's Expression Recognition.
Compared with prior art, the beneficial effect of the disclosure is:
The disclosure mainly considers few sample face Expression Recognition problem based on meta learning, utilizes episode-based's
Research on Methods training set, one convolutional neural networks of construction extract the knowledge of transferability to realize the identification to expression.
The present disclosure contemplates that original human facial expression recognition needs largely have label data, and the mark of label was both time-consuming
Effort again, how significantly more efficient using a small amount of label data, for the research of few sample Expression Recognition, the disclosure learns member
The Training strategy of habit is introduced into human facial expression recognition, can use a small amount of facial expression sample, to go identification not in training
The sample type occurred in the process；Using the heuristic approach to training set based on episode, instruction is more effectively made full use of
Practice collection, the knowledge with transitivity is more efficiently extracted, to perform better than in support set, to preferably divide
Class testing set.
Detailed description of the invention
The Figure of description for constituting a part of this disclosure is used to provide further understanding of the disclosure, and the disclosure is shown
Meaning property embodiment and its explanation do not constitute the improper restriction to the disclosure for explaining the disclosure.
Fig. 1 is a kind of few sample face expression recognition method process based on meta learning according to one or more embodiments
Figure；
Fig. 2 (a)-Fig. 2 (b) is the Expression Recognition network master cast schematic diagram according to one or more embodiments；
Fig. 3 is the human facial expression recognition method frame schematic diagram according to one or more embodiments.
Specific embodiment
It is noted that following detailed description is all illustrative, it is intended to provide further instruction to the disclosure.Unless another
It indicates, all technical and scientific terms used herein has usual with disclosure person of an ordinary skill in the technical field
The identical meanings of understanding.
It should be noted that term used herein above is merely to describe specific embodiment, and be not intended to restricted root
According to the illustrative embodiments of the disclosure.As used herein, unless the context clearly indicates otherwise, otherwise singular
Also it is intended to include plural form, additionally, it should be understood that, when in the present specification using term "comprising" and/or " packet
Include " when, indicate existing characteristics, step, operation, device, component and/or their combination.
Examples of implementation one
As shown in Figure 1, according to the one aspect of one or more other embodiments of the present disclosure, provide a kind of based on meta learning
Few sample face expression recognition method flow chart.
A kind of few sample face expression recognition method based on meta learning, this method comprises:
S101: facial sample set is received, data prediction is carried out；
S102: building Expression Recognition network master cast；
S103: the method based on meta learning divides data set and forms training and support/query set, utilizes
The method construct of episode-based meets sample set and the query set of C-way K-shot；
S104: pretreated sample is inputted into network master cast, model is optimized；
S105: receiving face data to be identified, carries out human facial expression recognition according to the model after optimization.
In the step S101 of the present embodiment, the facial sample data in the face sample set is facial samples pictures,
Carrying out the data prediction to facial samples pictures includes every breadth portion samples pictures being normalized and to facial sample
Each pixel in this picture is normalized.The concrete operation step of data prediction is carried out in the present embodiment:
S1011 normalizes each width picture: subtracting average value from every picture, then sets 3.125 for standard deviation；
S1012 normalizes each pixel: calculating a mean value pixel value picture first, then each width picture is subtracted
Go the mean value pixel of corresponding position；Then 1 is set by the standard deviation of each pixel of all training set pictures.
In the step S102 of the present embodiment, as shown in Fig. 2 (a)-Fig. 2 (b), the Expression Recognition network master cast includes
4 concatenated Convolution Block blocks and the last one Flatten layers；
The Convolution Block block specifically includes that convolutional layer, batch normalization layer, Relu activation primitive, Chi Hua
Layer.The parameter setting of convolutional layer: convolution kernel 3*3, padding=SAME mode；Pond layer uses maximum value pond.
The Flatten layer is used for the feature one-dimensional for extracting training pattern, obtains the feature of n=64 dimension.
Fig. 3 gives few sample face expression recognition method frame diagram based on meta learning: main innovation in entire method
It is the research to few sample face Expression Recognition, be largely divided into three parts: construction, feature extraction, the model of data set are excellent
Change.
It is divided into three data sets: training, support, test in few sample learning.Wherein training is for instructing
Practice, for support for verifying, test is used for last model measurement.And during training, it is constructed and is instructed using training
Sample set and query set during white silk, the expansion for following algorithm.
The construction of S103 data set comprises the concrete steps that:
Using raw data set, according to the thought of meta learning, (i.e. training and support/test have different S1031
The space label, and support/test has the identical space label) construction training/support/testing.In line with most
Bigization utilizes the standard of data set, is divided as follows to data set: randomly choosing three classes expression in seven class expressions and is used for
Training set randomly chooses three classes for support/query set again in remaining four classes expression, then program is every
Sample class of the operation once for training and test is not identical.
In the embodiment of the present application, slash unified representation "and".
It is selection C class in seven class expressions, in every one kind using the method construct C-way K-shot of episode-based
K sample of selection is used to construct the sample set in training process, selects q sample for constructing query in the C class
set。
When it is implemented, the method that S1032 utilizes episode-based, construction meets the sample of C-way K-shot
Set and query set.In the three classes expression picture of C=3, select K picture, K=1 or K > 1 for constructing sample
set；In the remaining picture of the three classes, select q picture for constructing query set, q=5,15,20 etc..
Feature extraction is to export to obtain the spy of 64 dimensions of input sample by the Flattern number of plies by network master cast
Sign.
S104 model optimization is joined using the method for stochastic gradient descent SGD to model using designed loss function
Number optimizes, so that total losses is minimum, detailed process is as follows:
S1041 calculates the prototype of every a kind of sample in sample set according to the feature of extraction.3-wayK-shot's
In sample set: if K=1, then the prototype of such sample is the feature p of 64 dimension of samplek=f (xi)；If K > 1, according to
The principle of Bregman divergence, then the prototype of kth class sample beWherein NsIt is that every a kind of expression is chosen
Sample number, SkIt is the set of such sample in sample set, (xi,yi) it is the exemplar that has in the set, f (xi) be
The feature extracted by master cast.
S1042 successively calculates the sample x in query setqWith every a kind of prototype pkDistance d (xq,pk), then basis
Far and near to such prototype distance calculates a possibility that belonging to suchThe calculating of distance can herein
To use Euclidean distance or COS distance.
S1043 uses loss function L (xq)=- logp (xq,pk), it is optimized using stochastic gradient descent method SGD.
Table 1 gives the pseudocode of dataset construction and model optimization.
Table 1
Examples of implementation two
According to the one aspect of one or more other embodiments of the present disclosure, a kind of few sample face based on meta learning is provided
Expression recognition apparatus.
A kind of few sample face expression recognition apparatus based on meta learning, few sample face based on a kind of meta learning
Portion's expression recognition method, comprising: sequentially connected data preprocessing module, master cast construct module, dataset construction module, mould
Type optimization module and human facial expression recognition module.
The data preprocessing module carries out data prediction for receiving facial sample set；
The master cast building module is for constructing Expression Recognition network master cast；
The dataset construction module will be for that will construct training set and the support set/ based on meta learning
Testing set, so that training set and support set/test set has the different spaces label；For structure
Build sample set and the query set for meeting C-way K-shot of episode-based；
The model optimization module is used for according to the data set constructed, according under determining loss function and stochastic gradient
The method of drop optimizes model.
The human facial expression recognition module carries out facial table for receiving face data to be identified, according to the model after optimization
Feelings identification.
It should be noted that although being referred to several modules or submodule of equipment in the detailed description above, it is this
Division is only exemplary rather than enforceable.In fact, in accordance with an embodiment of the present disclosure, two or more above-described moulds
The feature and function of block can embody in a module.Conversely, the feature and function of an above-described module can be with
Further division is to be embodied by multiple modules.
Examples of implementation three
A kind of computer equipment can be run on a memory and on a processor including memory, processor and storage
Computer program, which is characterized in that the processor realizes a kind of few sample face based on meta learning when executing described program
Expression recognition method step.
One of the examples of implementation based on meta learning few sample face expression recognition method the step of referring to embodiment
Particular technique content in son one, is no longer described in detail herein.
Examples of implementation four
A kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
A kind of few sample face expression recognition method step based on meta learning is realized when execution.
One of the examples of implementation based on meta learning few sample face expression recognition method the step of referring to embodiment
Particular technique content in son one, is no longer described in detail herein.
It is understood that in the description of this specification, reference term " embodiment ", " another embodiment ", " other
The description of embodiment " or " first embodiment~N embodiment " etc. means specific spy described in conjunction with this embodiment or example
Sign, structure, material or feature are included at least one embodiment or example of the invention.In the present specification, to above-mentioned
The schematic representation of term may not refer to the same embodiment or example.Moreover, the specific features of description, structure, material
Person's feature can be combined in any suitable manner in any one or more of the embodiments or examples.
The foregoing is merely preferred embodiment of the present disclosure, are not limited to the disclosure, for the skill of this field
For art personnel, the disclosure can have various modifications and variations.It is all within the spirit and principle of the disclosure, it is made any to repair
Change, equivalent replacement, improvement etc., should be included within the protection scope of the disclosure.
Claims (10)
1. a kind of few sample face expression recognition method based on meta learning, characterized in that include:
Facial sample set is received, data prediction is carried out；
Construct the master cast of Expression Recognition；
Facial sample set is divided based on the method for meta learning: for seven class expressions, randomly choosing three classes expression and is used for
Training set, then random selection three classes expression is used for testing set in remaining four class expressions；
Using the method construct C-way K-shot of episode-based, i.e., constructed using ready-portioned training set
Sample set and query set；
The facial sample set constructed is inputted into master cast, parameter optimization is carried out to master cast；
Face data to be identified is received, human facial expression recognition is carried out according to the master cast after optimization.
2. a kind of few sample face expression recognition method based on meta learning as described in claim 1, characterized in that the face
Facial sample data in portion's sample set is facial samples pictures, and carrying out data prediction to facial samples pictures includes to every width
Facial samples pictures are normalized and each pixel in facial samples pictures are normalized.
3. a kind of few sample face expression recognition method based on meta learning as claimed in claim 2, characterized in that every width
Facial samples pictures are normalized: subtracting average value from every picture, standard deviation is then arranged.
4. a kind of few sample face expression recognition method based on meta learning as claimed in claim 2, characterized in that face
Each pixel in samples pictures is normalized: a mean value pixel value picture is calculated first, then for each width picture
Subtract the mean value pixel of corresponding position；Then the standard deviation of each pixel of all training set pictures is set.
5. a kind of few sample face expression recognition method based on meta learning as described in claim 1, characterized in that the table
The master cast of feelings identification includes 4 concatenated Convolution Block blocks and the last one Flatten layers；
The Convolution Block block specifically includes that convolutional layer, batch normalization layer, Relu activation primitive, pond layer；
The parameter setting of convolutional layer: convolution kernel 3*3, padding=SAME mode；Pond layer uses maximum value pond；
The Flatten layer is used for the feature one-dimensional for extracting training pattern, obtains the feature of n=64 dimension.
6. a kind of few sample face expression recognition method based on meta learning as described in claim 1, characterized in that utilize
The method of episode-based, construction meets sample set and the query set of C-way K-shot, in the three classes of C=3
In expression picture, select K picture, K=1 or K > 1 for constructing sample set；In the remaining picture of the three classes, q is selected
Picture is for constructing query set.
7. a kind of few sample face expression recognition method based on meta learning as described in claim 1, characterized in that expression is known
Other master cast exports to obtain the feature of 64 dimensions of input sample by the Flattern number of plies；
According to the feature of extraction, the prototype of every a kind of sample in sample set is calculated, in the sample of 3-way K-shot
In set: if K=1, then the prototype of such sample is the feature p of 64 dimension of samplek=f (xi)；If K > 1, according to Bregman
The principle of divergence, then the prototype of kth class sample beWherein K is the sample that every a kind of expression is chosen
Number, SkIt is sample set, f (xi) it is the feature extracted by master cast；
Successively calculate the sample x in query setqWith every a kind of prototype pkDistance d (xq,pk), then basis arrives such prototype
The far and near of distance calculates a possibility that belonging to such, and the calculating of distance herein can use Euclidean distance or COS distance.
Using loss function L (xq)=- logp (xq,pk), it is optimized using stochastic gradient descent method SGD.
8. a kind of few sample face Expression Recognition system based on meta learning, characterized in that include:
Data preprocessing module is configured as: being received facial sample set, is carried out data prediction；
Master cast constructs module, is configured as: constructing the master cast of Expression Recognition；
Dataset construction module, is configured as: the method based on meta learning divides data set: for seven class expressions, with
Machine selects three classes expression to be used for training set, then random selection three classes expression is used for testing in remaining four class expressions
set；
Using the method construct C-way K-shot of episode-based, i.e., constructed using ready-portioned training set
Sample set and query set；
Master cast optimization module, is configured as: the facial sample set constructed being inputted master cast, it is excellent to carry out parameter to master cast
Change；
Human facial expression recognition module, is configured as: receiving face data to be identified, carries out facial table according to the master cast after optimization
Feelings identification.
9. a kind of computer equipment including memory, processor and stores the meter that can be run on a memory and on a processor
Calculation machine program, which is characterized in that the processor realizes that one kind as claimed in claim 1 to 7 is based on when executing described program
Few sample face expression recognition method step of meta learning.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
A kind of few sample face expression recognition method step based on meta learning as claimed in claim 1 to 7 is realized when execution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910465071.1A CN110175588B (en) | 2019-05-30 | 2019-05-30 | Meta learning-based few-sample facial expression recognition method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910465071.1A CN110175588B (en) | 2019-05-30 | 2019-05-30 | Meta learning-based few-sample facial expression recognition method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110175588A true CN110175588A (en) | 2019-08-27 |
| CN110175588B CN110175588B (en) | 2020-12-29 |
Family
ID=67696889
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910465071.1A Active CN110175588B (en) | 2019-05-30 | 2019-05-30 | Meta learning-based few-sample facial expression recognition method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110175588B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111737426A (en) * | 2020-05-09 | 2020-10-02 | 中国科学院深圳先进技术研究院 | Method for training question-answering model, computer equipment and readable storage medium |
| CN113591660A (en) * | 2021-07-24 | 2021-11-02 | 中国石油大学(华东) | Micro-expression recognition method based on meta-learning |
| WO2022011493A1 (en) * | 2020-07-13 | 2022-01-20 | 广东石油化工学院 | Neural semantic memory storage method |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109376625A (en) * | 2018-10-10 | 2019-02-22 | 东北大学 | A kind of human facial expression recognition method based on convolutional neural networks |
| CN109685135A (en) * | 2018-12-21 | 2019-04-26 | 电子科技大学 | A kind of few sample image classification method based on modified metric learning |
-
2019
- 2019-05-30 CN CN201910465071.1A patent/CN110175588B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109376625A (en) * | 2018-10-10 | 2019-02-22 | 东北大学 | A kind of human facial expression recognition method based on convolutional neural networks |
| CN109685135A (en) * | 2018-12-21 | 2019-04-26 | 电子科技大学 | A kind of few sample image classification method based on modified metric learning |
Non-Patent Citations (5)
| Title |
|---|
| FLOOD SUNG等: "Learning to Compare: Relation Network for Few-Shot Learning", 《HTTPS://ARXIV.ORG/ABS/1711.06025V2》 * |
| JAKE SNELL等: "Prototypical Networks for Few-shot Learning", 《31ST CONFERENCE ON NEURAL INFORMATION PROCESSING SYSTEMS (NIPS 2017)》 * |
| ORIOL VINYALS等: "Matching Networks for One Shot Learning", 《30TH CONFERENCE ON NEURAL INFORMATION PROCESSING SYSTEMS (NIPS 2016)》 * |
| YONG WANG等: "Large Margin Meta-Learning for Few-Shot Classification", 《2ND WORKSHOP ON META-LEARNING AT NEURIPS 2018》 * |
| 闫雷鸣 等: "基于句式元学习的Twitter分类", 《北京大学学报(自然科学版)》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111737426A (en) * | 2020-05-09 | 2020-10-02 | 中国科学院深圳先进技术研究院 | Method for training question-answering model, computer equipment and readable storage medium |
| CN111737426B (en) * | 2020-05-09 | 2021-06-01 | 中国科学院深圳先进技术研究院 | Method for training question-answering model, computer equipment and readable storage medium |
| WO2022011493A1 (en) * | 2020-07-13 | 2022-01-20 | 广东石油化工学院 | Neural semantic memory storage method |
| CN113591660A (en) * | 2021-07-24 | 2021-11-02 | 中国石油大学(华东) | Micro-expression recognition method based on meta-learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110175588B (en) | 2020-12-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020215985A1 (en) | Medical image segmentation method and device, electronic device and storage medium | |
| CN108596882B (en) | The recognition methods of pathological picture and device | |
| CN107341805B (en) | Background segment and network model training, image processing method and device before image | |
| Hou et al. | Classification of tongue color based on CNN | |
| CN104933428B (en) | A kind of face identification method and device based on tensor description | |
| CN110232383A (en) | A kind of lesion image recognition methods and lesion image identifying system based on deep learning model | |
| CN109117744A (en) | A kind of twin neural network training method for face verification | |
| CN108182441A (en) | Parallel multichannel convolutive neural network, construction method and image characteristic extracting method | |
| CN110175588A (en) | A kind of few sample face expression recognition method and system based on meta learning | |
| CN108229379A (en) | Image-recognizing method, device, computer equipment and storage medium | |
| CN109346159A (en) | Case image classification method, device, computer equipment and storage medium | |
| CN108198625B (en) | Deep learning method and device for analyzing high-dimensional medical data | |
| CN108416327A (en) | A kind of object detection method, device, computer equipment and readable storage medium storing program for executing | |
| WO2022247005A1 (en) | Method and apparatus for identifying target object in image, electronic device and storage medium | |
| CN110363131A (en) | Anomaly detection method, system and medium based on human skeleton | |
| CN104484886B (en) | A kind of dividing method and device of MR images | |
| CN110992351A (en) | sMRI image classification method and device based on multi-input convolutional neural network | |
| CN109783624A (en) | Answer generation method, device and the intelligent conversational system in knowledge based library | |
| CN109978074A (en) | Image aesthetic feeling and emotion joint classification method and system based on depth multi-task learning | |
| CN110490239A (en) | Training method, the quality classification method, device and equipment of image quality control network | |
| CN108287857A (en) | Expression picture recommends method and device | |
| CN110472495B (en) | Deep learning face recognition method based on graphic reasoning global features | |
| CN110175505A (en) | Determination method, apparatus, storage medium and the electronic device of micro- expression type | |
| CN108345889A (en) | A kind of application process carrying out registration identification to communication cabinet using Raspberry Pi | |
| CN115374189B (en) | Block chain-based food safety tracing method, device and equipment |
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 |