CN111274924A - Palm vein detection model modeling method, palm vein detection method and palm vein detection device - Google Patents
Palm vein detection model modeling method, palm vein detection method and palm vein detection device Download PDFInfo
- Publication number
- CN111274924A CN111274924A CN202010054103.1A CN202010054103A CN111274924A CN 111274924 A CN111274924 A CN 111274924A CN 202010054103 A CN202010054103 A CN 202010054103A CN 111274924 A CN111274924 A CN 111274924A
- Authority
- CN
- China
- Prior art keywords
- palm vein
- model
- vein detection
- detection
- palm
- 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.)
- Pending
Links
- 210000003462 vein Anatomy 0.000 title claims abstract description 271
- 238000001514 detection method Methods 0.000 title claims abstract description 224
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000012549 training Methods 0.000 claims abstract description 38
- 238000005457 optimization Methods 0.000 claims abstract description 17
- 238000001727 in vivo Methods 0.000 abstract description 5
- 230000006399 behavior Effects 0.000 abstract description 3
- 230000005764 inhibitory process Effects 0.000 abstract description 3
- 238000003062 neural network model Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- 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
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06V40/14—Vascular patterns
Abstract
The application provides a palm vein detection model modeling method, a palm vein detection method and a palm vein detection device, wherein the modeling method comprises the following steps: obtaining a palm vein training image; inputting a palm vein training image into a palm vein detection initial model, and carrying out model training on the palm vein detection initial model, wherein the palm vein detection initial model comprises: a HOA algorithm module; and performing convergence optimization on the palm vein detection initial model based on the error between the predicted value output by the palm vein detection initial model and the preset label value to obtain the palm vein detection model. The HOA module is introduced to the original model structure by adopting a neural network model containing the HOA algorithm module. Through the inhibition of the biased learning behavior of the depth network of the HOA algorithm module, the attention richness of the depth characteristics is enhanced, and the trained model has stronger discrimination capability, so that the anti-counterfeiting accuracy is improved, and the technical problem of poor anti-counterfeiting identification performance of the existing in-vivo detection model is solved.
Description
Technical Field
The application relates to the technical field of palm vein recognition, in particular to a palm vein detection model modeling method, a palm vein detection method and a palm vein detection device.
Background
Palm vein identification is a biological feature identification technology for identifying personal identity by using distribution information of vein blood vessels of palm part of human body. The palm vein is positioned under the skin surface, so that the living body effectiveness is realized, the hand is usually in a half-fist state, the palm vein information is not easy to steal, and the safety is high; meanwhile, the palm vein contains abundant personal information, has high identity identification capability, and is commonly used in occasions with high requirements on security level, such as public security, commercial finance and the like.
The existing palm vein detection model usually adopts a detection model trained by a single neural network to carry out palm vein living body detection, and the detection model trained by the single neural network has a relatively simple structure, so that the technical problem of poor anti-counterfeiting identification performance of the existing living body detection model is caused.
Disclosure of Invention
The application provides a palm vein detection model modeling method, a palm vein detection method and a palm vein detection device, which are used for solving the technical problem that the existing in-vivo detection model is poor in anti-counterfeiting identification performance.
In view of this, the first aspect of the present application provides a palm vein detection model modeling method, including:
obtaining a palm vein training image;
inputting the palm vein training image into a palm vein detection initial model, and performing model training on the palm vein detection initial model, wherein the palm vein detection initial model comprises: a HOA algorithm module;
and performing convergence optimization on the palm vein detection initial model based on the error between the predicted value output by the palm vein detection initial model and a preset label value to obtain the palm vein detection model.
Optionally, the performing convergence optimization on the palm vein detection initial model based on the predicted value output by the palm vein detection initial model and the error of the preset tag value to obtain the palm vein detection model specifically includes:
and updating the model weight of the palm vein detection initial model based on the predicted value output by the palm vein detection initial model and the error of a preset tag value until the predicted value output by the palm vein detection initial model and the error of the tag value are minimum, so as to obtain the palm vein detection model.
Optionally, the HOA algorithm module is specifically a first-order HOA algorithm module or a multi-order HOA algorithm module.
A second aspect of the present application provides a palm vein detection method, including:
obtaining a palm vein sample image;
inputting the palm vein sample image into a palm vein detection model, so that the palm vein detection model detects the palm vein sample image and outputs a detection result;
the palm vein detection model is obtained by the palm vein detection model modeling method according to the first aspect of the application.
Optionally, the inputting the palm vein sample image into a palm vein detection model, so that the detecting the palm vein sample image by the palm vein detection model and outputting the detection result specifically include:
inputting the palm vein sample image into a palm vein detection model, enabling the palm vein detection model to detect the palm vein sample image, if the predicted value output by the palm vein detection model is larger than a preset judgment threshold value, outputting a palm vein detection result as true, and if not, outputting a palm vein detection result as false.
The third aspect of the present application provides a palm vein detection model modeling apparatus, including:
the training image acquisition unit is used for acquiring a palm vein training image;
the model training unit is used for inputting the palm vein training image into a palm vein detection initial model and performing model training on the palm vein detection initial model, wherein the palm vein detection initial model comprises: a HOA algorithm module;
and the model optimization unit is used for carrying out convergence optimization on the palm vein detection initial model based on the error between the predicted value output by the palm vein detection initial model and a preset label value to obtain the palm vein detection model.
Optionally, the model optimization unit is specifically configured to:
and updating the model weight of the palm vein detection initial model based on the predicted value output by the palm vein detection initial model and the error of a preset tag value until the predicted value output by the palm vein detection initial model and the error of the tag value are minimum, so as to obtain the palm vein detection model.
Optionally, the HOA algorithm module is specifically a first-order HOA algorithm module or a multi-order HOA algorithm module.
The present application in a fourth aspect provides a palm vein detection device, comprising:
the sample image acquisition unit is used for acquiring a palm vein sample image;
the palm vein detection unit is used for inputting the palm vein sample image into a palm vein detection model, so that the palm vein detection model detects the palm vein sample image and outputs a detection result;
the palm vein detection model is a model constructed by the palm vein detection model modeling device according to the third aspect of the present application.
Optionally, the palm vein detection unit is specifically configured to:
inputting the palm vein sample image into a palm vein detection model, enabling the palm vein detection model to detect the palm vein sample image, if the predicted value output by the palm vein detection model is larger than a preset judgment threshold value, outputting a palm vein detection result as true, and if not, outputting a palm vein detection result as false.
According to the technical scheme, the method has the following advantages:
the application provides a palm vein detection model modeling method, a palm vein detection method and a palm vein detection device, wherein the modeling method comprises the following steps: obtaining a palm vein training image; inputting a palm vein training image into a palm vein detection initial model, and carrying out model training on the palm vein detection initial model, wherein the palm vein detection initial model comprises: a HOA algorithm module; and performing convergence optimization on the palm vein detection initial model based on the error between the predicted value output by the palm vein detection initial model and the preset label value to obtain the palm vein detection model.
The HOA module is introduced to the original model structure by adopting a neural network model containing the HOA algorithm module. Through the inhibition of the biased learning behavior of the depth network of the HOA algorithm module, the attention richness of the depth characteristics is enhanced, and the trained model has stronger discrimination capability, so that the anti-counterfeiting accuracy is improved, and the technical problem of poor anti-counterfeiting identification performance of the existing in-vivo detection model is solved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
Fig. 1 is a schematic flow chart of an embodiment of a palm vein detection model modeling method provided in the present application;
fig. 2 is a schematic flow chart of an embodiment of a palm vein detection method provided in the present application;
fig. 3 is a schematic structural diagram of an embodiment of a palm vein detection model modeling apparatus provided in the present application;
fig. 4 is a schematic structural diagram of an embodiment of a palm vein detection device provided in the present application;
FIG. 5 is a first-order HOA block diagram of a palm vein detection model modeling method provided by the present application;
fig. 6 is a third-order HOA module diagram of a palm vein detection model modeling method provided by the present application.
Detailed Description
The embodiment of the application provides a palm vein detection model modeling method, a palm vein detection method and a palm vein detection device, which are used for solving the technical problem that the existing in-vivo detection model is poor in anti-counterfeiting identification performance.
In order to make the objects, features and advantages of the present invention more apparent and understandable, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the embodiments described below are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Referring to fig. 1, a first embodiment of the present application provides a palm vein detection model modeling method, including:
101, obtaining a palm vein training image;
it should be noted that, before the modeling method provided in this embodiment, a palm vein training image required for model training is obtained first.
And 102, inputting the palm vein training image into a palm vein detection initial model, and performing model training on the palm vein detection initial model.
Wherein, the palm vein detection initial model comprises: and a HOA algorithm module.
After the palm vein training image is acquired, the palm vein training image is input to the palm vein detection initial model, and model training is performed on the palm vein detection initial model.
And 103, performing convergence optimization on the palm vein detection initial model based on the predicted value output by the palm vein detection initial model and the error of the preset label value to obtain the palm vein detection model.
Further, step 103 of this embodiment specifically includes:
and updating the model weight of the palm vein detection initial model based on the predicted value output by the palm vein detection initial model and the error of a preset tag value until the error of the predicted value output by the palm vein detection initial model and the tag value is minimum, and obtaining the palm vein detection model.
It should be noted that in the process of model training, the model weight of the palm vein detection initial model is updated by calculating the error between the predicted value output by the palm vein detection initial model and the preset tag value, so that convergence optimization is performed on the palm vein detection initial model until the error between the predicted value output by the palm vein detection initial model and the tag value reaches the minimum, that is, the model training is optimal, and then the model training is stopped to obtain the palm vein detection model.
Further, the HOA algorithm module is specifically a first-order HOA algorithm module or a multi-order HOA algorithm module.
Please refer to fig. 5, the HOA algorithm block of the palm vein detection initial model provided in this embodiment may be a first-order HOA module, and specific reference codes of the palm vein detection model are as follows:
the above code is a reference code of a palm vein detection model using a 1 st order HOA module, and on this basis, a multi-order HOA module may be adopted, and specifically, refer to fig. 6.
In this embodiment, taking 3-order HOA workflow as an example, mid-level featuremap (i.e. tensor, dimension is N × C × H × W, corresponding meaning is batch size, channel, width and height) generated by layer2 module is processed by 1 × 1conv to generate 3 groups of 6 branch tensors, Hadamard Product is used between each group to generate 3 new branch tensors (dimension is N × C × H × W), then ReLU and 1 × 1conv are used for the 3 tensors respectively, and then they are summed to become a new tensor (dimension is still N × C × H × W), and then Hadamard Product is made with the original mid-level featuremap. The HOA has the advantages that when the network weight is shared at various spatial positions, excessive parameters cannot be generated, and the operation is simple by using 1 × 1 conv.
According to the method and the device, the HOA module is introduced to an original model structure by adopting a neural network model containing the HOA algorithm module. Through the inhibition of the biased learning behavior of the depth network of the HOA algorithm module, the attention richness of the depth characteristics is enhanced, and the trained model has stronger discrimination capability, so that the anti-counterfeiting accuracy is improved, and the technical problem of poor anti-counterfeiting identification performance of the existing in-vivo detection model is solved.
The above is a detailed description of an embodiment of a palm vein detection model modeling method provided by the present application, and the following is a detailed description of an embodiment of a palm vein detection method provided by the present application.
Referring to fig. 2, a second embodiment of the present application provides a palm vein detection method, including:
First, a palm vein sample image of an object to be recognized needs to be acquired.
The palm vein detection model is obtained by the palm vein detection model modeling method as mentioned in the first embodiment of the present application.
After the palm vein sample image is acquired, the palm vein sample image is input to the trained palm vein detection model, so that the palm vein detection model detects the palm vein sample image, and further obtains a detection result output by the model.
Further, step 202 of this embodiment specifically includes:
inputting the palm vein sample image into a palm vein detection model, enabling the palm vein detection model to detect the palm vein sample image, if the predicted value output by the palm vein detection model is larger than a preset judgment threshold value, outputting a palm vein detection result as true, and if not, outputting a palm vein detection result as false.
It should be noted that, a prediction result output by the palm vein detection model of the present embodiment is a real number between 0 and 1, and if the result is greater than a preset threshold, it is considered as a true palm vein, otherwise it is determined as false.
The above is a detailed description of an embodiment of a palm vein detection method provided by the present application, and the following is a detailed description of an embodiment of a palm vein detection model modeling apparatus provided by the present application.
Referring to fig. 3, a third embodiment of the present application provides a palm vein detection model modeling apparatus, including:
a training image acquisition unit 301 configured to acquire a palm vein training image;
a model training unit 302, configured to input a palm vein training image into a palm vein detection initial model, and perform model training on the palm vein detection initial model, where the palm vein detection initial model includes: a HOA algorithm module;
and the model optimization unit 303 is configured to perform convergence optimization on the palm vein detection initial model based on a predicted value output by the palm vein detection initial model and an error of a preset tag value, so as to obtain the palm vein detection model.
Further, the model optimization unit 303 is specifically configured to:
and updating the model weight of the palm vein detection initial model based on the predicted value output by the palm vein detection initial model and the error of a preset tag value until the error of the predicted value output by the palm vein detection initial model and the tag value is minimum, and obtaining the palm vein detection model.
Further, the HOA algorithm module is specifically a first-order HOA algorithm module or a multi-order HOA algorithm module.
The above is a detailed description of an embodiment of the palm vein detection model modeling device provided by the present application, and the following is a detailed description of an embodiment of the palm vein detection model modeling device provided by the present application.
A fourth embodiment of the present application provides a palm vein detection device, including:
a sample image obtaining unit 401, configured to obtain a palm vein sample image;
a palm vein detection unit 402, configured to input a palm vein sample image to a palm vein detection model, so that the palm vein detection model detects the palm vein sample image, and outputs a detection result;
the palm vein detection model is a model constructed by the palm vein detection model modeling device according to the third aspect of the present application.
Further, the palm vein detection unit 402 is specifically configured to:
inputting the palm vein sample image into a palm vein detection model, enabling the palm vein detection model to detect the palm vein sample image, if the predicted value output by the palm vein detection model is larger than a preset judgment threshold value, outputting a palm vein detection result as true, and if not, outputting a palm vein detection result as false.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The terms "first," "second," "third," "fourth," and the like in the description of the application and the above-described figures, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.
Claims (10)
1. A palm vein detection model modeling method is characterized by comprising the following steps:
obtaining a palm vein training image;
inputting the palm vein training image into a palm vein detection initial model, and performing model training on the palm vein detection initial model, wherein the palm vein detection initial model comprises: a HOA algorithm module;
and performing convergence optimization on the palm vein detection initial model based on the error between the predicted value output by the palm vein detection initial model and a preset label value to obtain the palm vein detection model.
2. The modeling method of the palm vein detection model according to claim 1, wherein the performing convergence optimization on the palm vein detection initial model based on the error between the predicted value output by the palm vein detection initial model and a preset tag value to obtain the palm vein detection model specifically comprises:
and updating the model weight of the palm vein detection initial model based on the predicted value output by the palm vein detection initial model and the error of a preset tag value until the predicted value output by the palm vein detection initial model and the error of the tag value are minimum, so as to obtain the palm vein detection model.
3. The palm vein detection model modeling method according to claim 1, wherein the HOA algorithm module is specifically a first order HOA algorithm module or a multi-order HOA algorithm module.
4. A palm vein detection method is characterized by comprising the following steps:
obtaining a palm vein sample image;
inputting the palm vein sample image into a palm vein detection model, so that the palm vein detection model detects the palm vein sample image and outputs a detection result;
wherein the palm vein detection model is a model obtained by the palm vein detection model modeling method according to any one of claims 1 to 3.
5. The palm vein detection method according to claim 4, wherein the inputting the palm vein sample image into a palm vein detection model to enable the palm vein detection model to detect the palm vein sample image and outputting a detection result specifically comprises:
inputting the palm vein sample image into a palm vein detection model, enabling the palm vein detection model to detect the palm vein sample image, if the predicted value output by the palm vein detection model is larger than a preset judgment threshold value, outputting a palm vein detection result as true, and if not, outputting a palm vein detection result as false.
6. A palm vein detection model modeling device is characterized by comprising:
the training image acquisition unit is used for acquiring a palm vein training image;
the model training unit is used for inputting the palm vein training image into a palm vein detection initial model and performing model training on the palm vein detection initial model, wherein the palm vein detection initial model comprises: a HOA algorithm module;
and the model optimization unit is used for carrying out convergence optimization on the palm vein detection initial model based on the error between the predicted value output by the palm vein detection initial model and a preset label value to obtain the palm vein detection model.
7. The palm vein detection model modeling apparatus according to claim 6, wherein the model optimization unit is specifically configured to:
and updating the model weight of the palm vein detection initial model based on the predicted value output by the palm vein detection initial model and the error of a preset tag value until the predicted value output by the palm vein detection initial model and the error of the tag value are minimum, so as to obtain the palm vein detection model.
8. The device as claimed in claim 6, wherein the HOA algorithm module is a first order HOA algorithm module or a multi-order HOA algorithm module.
9. A palm vein detection device, comprising:
the sample image acquisition unit is used for acquiring a palm vein sample image;
the palm vein detection unit is used for inputting the palm vein sample image into a palm vein detection model, so that the palm vein detection model detects the palm vein sample image and outputs a detection result;
wherein the palm vein detection model is a model constructed by the palm vein detection model modeling apparatus according to any one of claims 6 to 8.
10. The palm vein detection device according to claim 9, wherein the palm vein detection unit is specifically configured to:
inputting the palm vein sample image into a palm vein detection model, enabling the palm vein detection model to detect the palm vein sample image, if the predicted value output by the palm vein detection model is larger than a preset judgment threshold value, outputting a palm vein detection result as true, and if not, outputting a palm vein detection result as false.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010054103.1A CN111274924A (en) | 2020-01-17 | 2020-01-17 | Palm vein detection model modeling method, palm vein detection method and palm vein detection device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010054103.1A CN111274924A (en) | 2020-01-17 | 2020-01-17 | Palm vein detection model modeling method, palm vein detection method and palm vein detection device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111274924A true CN111274924A (en) | 2020-06-12 |
Family
ID=70998769
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010054103.1A Pending CN111274924A (en) | 2020-01-17 | 2020-01-17 | Palm vein detection model modeling method, palm vein detection method and palm vein detection device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111274924A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112200159A (en) * | 2020-12-01 | 2021-01-08 | 四川圣点世纪科技有限公司 | Non-contact palm vein identification method based on improved residual error network |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100045788A1 (en) * | 2008-08-19 | 2010-02-25 | The Hong Kong Polytechnic University | Method and Apparatus for Personal Identification Using Palmprint and Palm Vein |
CN108681708A (en) * | 2018-05-16 | 2018-10-19 | 福州精益精科技有限责任公司 | A kind of vena metacarpea image-recognizing method, device and storage medium based on Inception neural network models |
CN110288597A (en) * | 2019-07-01 | 2019-09-27 | 哈尔滨工业大学 | Wireless capsule endoscope saliency detection method based on attention mechanism |
CN110321870A (en) * | 2019-07-11 | 2019-10-11 | 西北民族大学 | A kind of vena metacarpea recognition methods based on LSTM |
CN110414373A (en) * | 2019-07-08 | 2019-11-05 | 武汉大学 | A kind of deep learning palm vein identification system and method based on cloud side end cooperated computing |
-
2020
- 2020-01-17 CN CN202010054103.1A patent/CN111274924A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100045788A1 (en) * | 2008-08-19 | 2010-02-25 | The Hong Kong Polytechnic University | Method and Apparatus for Personal Identification Using Palmprint and Palm Vein |
CN108681708A (en) * | 2018-05-16 | 2018-10-19 | 福州精益精科技有限责任公司 | A kind of vena metacarpea image-recognizing method, device and storage medium based on Inception neural network models |
CN110288597A (en) * | 2019-07-01 | 2019-09-27 | 哈尔滨工业大学 | Wireless capsule endoscope saliency detection method based on attention mechanism |
CN110414373A (en) * | 2019-07-08 | 2019-11-05 | 武汉大学 | A kind of deep learning palm vein identification system and method based on cloud side end cooperated computing |
CN110321870A (en) * | 2019-07-11 | 2019-10-11 | 西北民族大学 | A kind of vena metacarpea recognition methods based on LSTM |
Non-Patent Citations (1)
Title |
---|
BINGHUI CHEN: ""Mixed High-Order Attention Network for Person Re-Identification"", 《ARXIV.ORG》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112200159A (en) * | 2020-12-01 | 2021-01-08 | 四川圣点世纪科技有限公司 | Non-contact palm vein identification method based on improved residual error network |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107169454B (en) | Face image age estimation method and device and terminal equipment thereof | |
CN107958230B (en) | Facial expression recognition method and device | |
CN107437074B (en) | Identity authentication method and device | |
JP7414901B2 (en) | Living body detection model training method and device, living body detection method and device, electronic equipment, storage medium, and computer program | |
CN110163096B (en) | Person identification method, person identification device, electronic equipment and computer readable medium | |
CN111785366B (en) | Patient treatment scheme determination method and device and computer equipment | |
CN110232318A (en) | Acupuncture point recognition methods, device, electronic equipment and storage medium | |
CN111401339B (en) | Method and device for identifying age of person in face image and electronic equipment | |
WO2019119396A1 (en) | Facial expression recognition method and device | |
CN108614987A (en) | The method, apparatus and robot of data processing | |
CN113143295A (en) | Equipment control method and terminal based on motor imagery electroencephalogram signals | |
CN111860056B (en) | Blink-based living body detection method, blink-based living body detection device, readable storage medium and blink-based living body detection equipment | |
CN113808044B (en) | Encryption mask determining method, device, equipment and storage medium | |
CN111104897A (en) | Training method and device for child face recognition model and storage medium | |
CN111274924A (en) | Palm vein detection model modeling method, palm vein detection method and palm vein detection device | |
CN112861742A (en) | Face recognition method and device, electronic equipment and storage medium | |
CN111104952A (en) | Method, system and device for identifying food types and refrigerator | |
CN112561935B (en) | Intelligent classification method, device and equipment for brain images | |
CN112487903B (en) | Gait data generation method and device based on countermeasure network | |
CN111476775B (en) | DR symptom identification device and method | |
CN114332990A (en) | Emotion recognition method, device, equipment and medium | |
CN111832815A (en) | Scientific research hotspot prediction method and system | |
CN113837930B (en) | Face image synthesis method, device and computer readable storage medium | |
CN115147420B (en) | Inter-slice correlation detection model training method, detection method and electronic equipment | |
CN115381467B (en) | Attention mechanism-based time-frequency information dynamic fusion decoding method and device |
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 | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: Room 1301, No.132, Fengqi Road, phase III, software park, Xiamen City, Fujian Province Applicant after: Xiamen Entropy Technology Co.,Ltd. Address before: 361000, Xiamen three software park, Fujian Province, 8 North Street, room 2001 Applicant before: XIAMEN ZKTECO INFORMATION TECHNOLOGY Co.,Ltd. |
|
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200612 |