CN114140424A - Palm vein data enhancement method and device, electronic equipment and medium - Google Patents
Palm vein data enhancement method and device, electronic equipment and medium Download PDFInfo
- Publication number
- CN114140424A CN114140424A CN202111435301.3A CN202111435301A CN114140424A CN 114140424 A CN114140424 A CN 114140424A CN 202111435301 A CN202111435301 A CN 202111435301A CN 114140424 A CN114140424 A CN 114140424A
- Authority
- CN
- China
- Prior art keywords
- sample data
- data
- enhancement
- palm vein
- original
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20092—Interactive image processing based on input by user
- G06T2207/20104—Interactive definition of region of interest [ROI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
- G06T2207/20132—Image cropping
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The embodiment of the invention discloses a palm vein data enhancement method, a palm vein data enhancement device, electronic equipment and a storage medium, and initial palm vein image data are obtained; performing image detection on the initial palm vein image data, extracting a corresponding ROI (region of interest) region as original sample data, and marking the direction attribute of the original sample data according to the result of the image detection; performing data enhancement on the original sample data based on the direction attribute to obtain enhanced sample data; and adding the original sample data and the enhanced sample data into a sample data set, wherein the sample data set is used for training a palm vein feature extraction model. The ROI area is extracted from the initial palm vein image to serve as original sample data, data enhancement based on the characteristics of the palm vein image is performed on the basis of the original sample data, a sample data set which is as rich as possible is constructed under the condition that fewer original samples are available, and the feature extraction accuracy of the palm vein feature extraction model is improved as much as possible based on the sample data set.
Description
Technical Field
The embodiment of the invention relates to the technical field of image processing, in particular to a palm vein data enhancement method and device, electronic equipment and a storage medium.
Background
The veins are the vessels that lead blood back to the heart, originating in the capillaries, ending in the atrium, and the superficial veins are visible subcutaneously. The palm vein is the internal palm vein, because everyone's palm vein is different, and along with the development of technique, the palm vein can more and more clear accurate detection, and the daily application of palm vein detection and discernment is more and more extensive. Palm vein recognition is also brought into a biological recognition loop at present, and palm vein recognition technology is gradually applied to security authentication systems, such as cash dispenser systems and access control systems, by people and is developed towards payment systems.
The palm vein recognition method is divided into a traditional method and a deep learning-based method, and features are mainly extracted through traditional image processing methods such as a filter and morphology in the traditional palm vein recognition method; the palm vein recognition method based on deep learning mainly trains a deep learning network based on sample data to obtain a feature extraction model, but the palm vein data in the conventional open source database are generally less, and the number of training samples is insufficient, so that the extraction accuracy of the trained feature extraction model is insufficient.
Disclosure of Invention
The invention provides a palm vein data enhancement method, a palm vein data enhancement device, electronic equipment and a storage medium, and aims to solve the technical problem that the feature extraction precision of an existing palm vein feature extraction model is insufficient.
In a first aspect, an embodiment of the present invention provides a palm vein data enhancement method, including:
acquiring initial palm vein image data;
performing image detection on the initial palm vein image data, extracting a corresponding ROI (region of interest) region as original sample data, and marking the direction attribute of the original sample data according to the result of the image detection;
performing data enhancement on the original sample data based on the direction attribute to obtain enhanced sample data;
and adding the original sample data and the enhanced sample data into a sample data set, wherein the sample data set is used for training a palm vein feature extraction model.
On the basis of the above embodiment, the performing data enhancement on the original sample data based on the direction attribute to obtain enhanced sample data specifically includes:
randomly selecting target sample data from the original sample data according to a preset proportion;
obtaining the direction attribute of the target sample data, and confirming at least one enhancement mode corresponding to the target sample data;
and maintaining the direction attribute of the target sample data, and enhancing the corresponding target sample data according to the corresponding enhancement mode to obtain enhanced sample data.
On the basis of the above embodiment, the target sample data is respectively enhanced by the corresponding enhancement modes to obtain a plurality of enhancement sample data, or is comprehensively enhanced by the corresponding enhancement modes to obtain one enhancement sample data.
On the basis of the above embodiment, the enhancement mode includes: shading, center clipping, aspect ratio clipping, brightness adjustment, contrast adjustment and saturation adjustment.
On the basis of the above embodiment, the ROI region is a square region.
In a second aspect, an embodiment of the present invention further provides a palm vein data enhancement device, including:
the data acquisition unit is used for acquiring initial palm vein image data;
the region extraction unit is used for carrying out image detection on the initial palm vein image data, extracting a corresponding ROI (region of interest) region as original sample data, and marking the direction attribute of the original sample data according to the image detection result;
the enhancement processing unit is used for carrying out data enhancement on the original sample data based on the direction attribute to obtain enhanced sample data;
and the data adding unit is used for adding the original sample data and the enhanced sample data into a sample data set, and the sample data set is used for training a palm vein feature extraction model.
On the basis of the above embodiment, the enhancement processing unit includes:
the data selection module is used for randomly selecting target sample data from the original sample data according to a preset proportion;
the mode confirming module is used for acquiring the direction attribute of the target sample data and confirming at least one enhancement mode corresponding to the target sample data;
and the enhancement processing module is used for maintaining the direction attribute of the target sample data and enhancing the corresponding target sample data according to the corresponding enhancement mode to obtain the enhancement sample data.
On the basis of the above embodiment, the target sample data is respectively enhanced by corresponding enhancement modes to obtain a plurality of enhancement sample data; or carrying out comprehensive enhancement through a corresponding enhancement mode to obtain enhancement sample data.
On the basis of the above embodiment, the enhancement mode includes: shading, center clipping, aspect ratio clipping, brightness adjustment, contrast adjustment and saturation adjustment.
On the basis of the above embodiment, the ROI region is a square region.
In a third aspect, an embodiment of the present invention further provides an electronic device, including:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, cause the electronic device to implement a palm vein data enhancement method as described in the first aspect.
In a fourth aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the palm vein data enhancement method according to the first aspect.
According to the palm vein data enhancement method, the palm vein data enhancement device, the electronic equipment and the storage medium, initial palm vein image data are obtained; performing image detection on the initial palm vein image data, extracting a corresponding ROI (region of interest) region as original sample data, and marking the direction attribute of the original sample data according to the result of the image detection; performing data enhancement on the original sample data based on the direction attribute to obtain enhanced sample data; and adding the original sample data and the enhanced sample data into a sample data set, wherein the sample data set is used for training a palm vein feature extraction model. The ROI area is extracted from the initial palm vein image to serve as original sample data, data enhancement based on the characteristics of the palm vein image is performed on the basis of the original sample data, a sample data set which is as rich as possible is constructed under the condition that fewer original samples are available, and the feature extraction accuracy of the palm vein feature extraction model is improved as much as possible based on the sample data set.
Drawings
Fig. 1 is a flowchart of a method for enhancing palm vein data according to an embodiment of the present invention;
fig. 2 is a schematic diagram of palm vein ROI region extraction according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a palm vein data enhancement device according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are for purposes of illustration and not limitation. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
It should be noted that, for the sake of brevity, this description does not exhaust all alternative embodiments, and it should be understood by those skilled in the art after reading this description that any combination of features may constitute an alternative embodiment as long as the features are not mutually inconsistent.
The following examples are described in detail.
Fig. 1 is a flowchart of a method for enhancing palm vein data, where the method is used in an electronic device, and as shown in the figure, the method includes:
step S110: initial palm vein image data is acquired.
In the existing palm vein recognition scheme, the traditional palm vein feature extraction is mainly realized by traditional image processing such as a filter and morphology. The feature extraction precision mainly depends on the structural design of a network model and the richness degree of a training sample based on the palm vein recognition of deep learning. In the field of palm vein recognition, the number of open data sets is small, so that the number of samples is insufficient, and the feature extraction accuracy of the trained palm vein feature extraction model is insufficient.
In the scheme, in order to preliminarily solve the problem of insufficient sample quantity, data enhancement is performed on the basis of the existing samples, so that more available sample data are obtained. The initial palm vein image data may be data acquired from an open data set or may be self-acquired image data. But regardless of the source of the initial palm vein image data, it should be raw image data that has not yet been processed.
Step S120: and carrying out image detection on the initial palm vein image data, extracting a corresponding ROI (region of interest) region as original sample data, and marking the direction attribute of the original sample data according to the image detection result.
Generally speaking, there is much information irrelevant to the palm veins in the initial palm vein image data, and unnecessary data processing burden may be caused by performing model training and subsequent feature extraction directly based on the palm vein image data. In the scheme, invalid information is filtered out through image detection, the proportion of the valid information is improved, and then the efficiency of model training and subsequent feature extraction is improved. The image detection may be implemented by an existing detection method, such as point detection.
In the specific implementation manner shown in fig. 2, before feature extraction, the midpoint of the two finger roots of the index finger and the tail finger is obtained by a point detection method, so as to form a square ROI (region of interest) of the palm, and the ROI regions input to the next step are input according to the sequence of the index finger, the tail finger, and the other two points, and based on the sequence, the direction attribute of the original sample data can be confirmed, and the direction attribute is mainly used for distinguishing the left hand from the right hand. The conventional palm vein feature extraction method is generally to directly extract features of collected palm information, which is easily interfered by non-palm information, such as background environment, finger rings and the like. Through the scheme, the area where the effective palm vein information is located can be confirmed, and interference is reduced. In a specific implementation process, the palm region may also be confirmed by detecting other key points of the hand, for example, detecting the positions of the third joints of the index finger and the tail finger, and further confirming the ROI region.
Step S130: and performing data enhancement on the original sample data based on the direction attribute to obtain enhanced sample data.
When data enhancement is performed on original sample data, data preprocessing is performed on the original sample data, namely, histogram equalization is mainly used for enhancing vein information, so that veins in a palm vein image are clearer, and then a size of an ROI (region of interest) is reset, so that the palm vein image with the consistent size is obtained.
Because palm vein data is generally small and the ROI region is directional, the index finger, the tail finger, and the other two points are input in the order of the index finger, the tail finger, and the other two points in the processed image regardless of the left hand and the right hand. For the palm vein image having directional characteristics, in a specific implementation process, the step S130 may be implemented by the steps S131 to S133:
step S131: and randomly selecting target sample data from the original sample data according to a preset proportion.
In the specific processing process, not every original sample data is subjected to data enhancement, but target sample data is randomly selected from the original sample data according to a preset proportion to perform data enhancement.
Step S132: and acquiring the direction attribute of the target sample data, and confirming at least one enhancement mode corresponding to the target sample data.
In a specific enhancement processing procedure, there may be a plurality of different enhancement modes, and in this scheme, the enhancement modes include: shading, center clipping, aspect ratio clipping, brightness adjustment, contrast adjustment and saturation adjustment.
Regarding occlusion, the probability value of occlusion can be 0.1, namely 10% of original sample data is randomly selected for occlusion; the shielded area is 0.02 to 0.1 times of the original image, namely 0.02 to 0.1 times of the original image; the width-to-height ratio of the shielded area is [0.3,1.2], namely 0.3-1.2 times of the width-to-height ratio of the original image, and the shielding value is a random value. The setting is mainly to add certain noise and enrich the diversity of data, but the area and probability value of the occlusion should not be too large so as not to lose too many features.
For center clipping, the center clipping is performed with a probability of 0.3, that is, 30% of the original sample data is randomly selected for center clipping, the width and height of the center clipping region are all 0.7 of the original image, and the center of the clipping region coincides with the center of the original sample data. This scale-centric cropping ensures that the main features of the image can be preserved, while increasing the diversity of the data.
Regarding aspect ratio clipping, random aspect ratio clipping is performed with a probability of 0.2, that is, 20% of original sample data is randomly selected for aspect ratio clipping. The area after cutting is 0.3 to 1.0 times of the original area of the original image, namely 0.3 to 1.0 time of the original image area, and the height-to-width ratio after cutting is 3/4 to 4/3, namely 3/4 to 4/3 times of the original image width-to-height ratio. The area of random cutting is not too small, 3/4-4/3 can ensure that the cut area is not too narrow and long, which is helpful for learning the local features of the image and increasing the diversity of data.
Regarding brightness adjustment, contrast adjustment and saturation adjustment, the modified brightness, contrast and saturation are between [0.5,1.5], thereby simulating palm vein images under different lighting conditions. The adjustment parameters for each image are constrained to be within a range, and are typically randomly determined within this range.
Considering that several points of the ROI are ordered, pictures generated in a random turning mode and other modes which may occur in other data enhancement may not accord with the characteristics of the palm vein images, and finally enabling the palm vein feature extraction model to learn features which do not accord with practical situations and reduce the performance of the model.
It should be noted that the preset proportion may be a proportion of data enhancement performed in all original sample data, for example, 30% or 35% of all original sample data is randomly selected as target sample data for data enhancement; the data enhancement may be performed by using a certain enhancement method in all the original sample data, for example, randomly selecting 20% as the target sample data for occlusion, randomly selecting 25% as the target sample data for center clipping, and the like. Furthermore, the foregoing adjustment parameter is only an exemplary example, and does not indicate that data enhancement is necessarily performed according to the parameter, for example, the probability value of occlusion may be 0.1, but other values, for example, 0.15, may also be selected.
Step S133: and maintaining the direction attribute of the target sample data, and enhancing the corresponding target sample data according to the corresponding enhancement mode to obtain enhanced sample data.
When target sample data is enhanced, partial information or picture effect of the target sample data may be changed, but regardless of how the enhancement is performed, the enhancement sample data and the corresponding target sample data still have the same directional attribute.
In a specific processing process, in order to enrich the diversity of the enhancement sample data, thereby enriching the number and diversity of the sample data, the target sample data can be respectively enhanced through corresponding enhancement modes to obtain a plurality of enhancement sample data, for example, a certain target sample data confirms that the corresponding enhancement mode has brightness adjustment and shielding, and then the target sample data can respectively obtain two corresponding enhancement sample data through brightness adjustment and shielding; or performing comprehensive enhancement through a corresponding enhancement mode to obtain one enhancement sample data, for example, in the previous corresponding enhancement mode, performing brightness adjustment and shielding on the target sample data, and obtaining one enhancement sample data through two enhancement modes. In fact, any combination of corresponding enhancement modes may also be used, for example, if it is determined that a certain target sample data corresponds to an enhancement mode having brightness adjustment, contrast adjustment, and center clipping, the target sample data may be simultaneously and independently enhanced by three enhancement modes to obtain three enhancement sample data, any two enhancement modes may be combined and enhanced to obtain three enhancement sample data, and three enhancement modes may be combined and enhanced to obtain one enhancement sample data.
Step S140: and adding the original sample data and the enhanced sample data into a sample data set, wherein the sample data set is used for training a palm vein feature extraction model.
The original sample data and the enhanced sample data are added into the sample data set to serve as training samples of the palm vein feature extraction model, and the process of training the network model based on the training samples is realized in the prior art, is not an innovative key point of the scheme, and is not particularly described here.
The method comprises the steps of obtaining initial palm vein image data; performing image detection on the initial palm vein image data, extracting a corresponding ROI (region of interest) region as original sample data, and marking the direction attribute of the original sample data according to the result of the image detection; performing data enhancement on the original sample data based on the direction attribute to obtain enhanced sample data; and adding the original sample data and the enhanced sample data into a sample data set, wherein the sample data set is used for training a palm vein feature extraction model. The ROI area is extracted from the initial palm vein image to serve as original sample data, data enhancement based on the characteristics of the palm vein image is performed on the basis of the original sample data, a sample data set which is as rich as possible is constructed under the condition that fewer original samples are available, and the feature extraction accuracy of the palm vein feature extraction model is improved as much as possible based on the sample data set.
Fig. 3 is a schematic structural diagram of a palm vein data enhancement device according to an embodiment of the present invention. Referring to fig. 3, the palm vein data enhancement apparatus includes a data acquisition unit 210, a region extraction unit 220, an enhancement processing unit 230, and a data addition unit 240.
The data acquiring unit 210 is configured to acquire initial palm vein image data;
a region extracting unit 220, configured to perform image detection on the initial palm vein image data, extract a corresponding ROI region as original sample data, and mark a direction attribute of the original sample data according to an image detection result;
an enhancement processing unit 230, configured to perform data enhancement on the original sample data based on the direction attribute, to obtain enhanced sample data;
and a data adding unit 240, configured to add the original sample data and the enhanced sample data to a sample data set, where the sample data set is used to train a palm vein feature extraction model.
On the basis of the above embodiment, the enhancement processing unit 230 includes:
the data selection module is used for randomly selecting target sample data from the original sample data according to a preset proportion;
the mode confirming module is used for acquiring the direction attribute of the target sample data and confirming at least one enhancement mode corresponding to the target sample data;
and the enhancement processing module is used for maintaining the direction attribute of the target sample data and enhancing the corresponding target sample data according to the corresponding enhancement mode to obtain the enhancement sample data.
On the basis of the above embodiment, the target sample data is respectively enhanced by corresponding enhancement modes to obtain a plurality of enhancement sample data; or carrying out comprehensive enhancement through a corresponding enhancement mode to obtain enhancement sample data.
On the basis of the above embodiment, the enhancement mode includes: shading, center clipping, aspect ratio clipping, brightness adjustment, contrast adjustment and saturation adjustment.
On the basis of the above embodiment, the ROI region is a square region.
The palm vein data enhancement device provided by the embodiment of the invention is contained in the electronic equipment of the equipment, can be used for executing any palm vein data enhancement method provided by the embodiment, and has corresponding functions and beneficial effects.
It should be noted that, in the embodiment of the palm vein data enhancement device, the included units and modules are only divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
Fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. As shown in fig. 4, the electronic device includes a processor 310, a memory 320, an input device 330, an output device 340, and a communication device 350; the number of the processors 310 in the electronic device may be one or more, and one processor 310 is taken as an example in fig. 4; the processor 310, the memory 320, the input device 330, the output device 340 and the communication device 350 in the electronic apparatus may be connected by a bus or other means, and fig. 4 illustrates the connection by the bus as an example.
The memory 320 may be used as a computer-readable storage medium for storing software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the palm vein data enhancement method in the embodiment of the present invention (for example, the data acquisition unit 210, the region extraction unit 220, the enhancement processing unit 230, and the data addition unit 240 in the palm vein data enhancement device). The processor 310 executes various functional applications and data processing of the electronic device by executing software programs, instructions and modules stored in the memory 320, so as to implement the palm vein data enhancement method.
The memory 320 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function; the storage data area may store data created according to use of the electronic device, and the like. Further, the memory 320 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, the memory 320 may further include memory located remotely from the processor 310, which may be connected to the electronic device through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 330 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the electronic apparatus. The output device 340 may include a display device such as a display screen.
The electronic equipment comprises the palm vein data enhancement device, can be used for executing any palm vein data enhancement method, and has corresponding functions and beneficial effects.
Embodiments of the present invention also provide a storage medium containing computer-executable instructions, which when executed by a computer processor, are configured to perform operations related to the palm vein data enhancement method provided in any of the embodiments of the present application, and have corresponding functions and advantages.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product.
Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein. The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks. These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory. The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A palm vein data enhancement method is characterized by comprising the following steps:
acquiring initial palm vein image data;
performing image detection on the initial palm vein image data, extracting a corresponding ROI (region of interest) region as original sample data, and marking the direction attribute of the original sample data according to the result of the image detection;
performing data enhancement on the original sample data based on the direction attribute to obtain enhanced sample data;
and adding the original sample data and the enhanced sample data into a sample data set, wherein the sample data set is used for training a palm vein feature extraction model.
2. The palm vein data enhancement method according to claim 1, wherein the data enhancement is performed on the original sample data based on the direction attribute to obtain enhanced sample data, specifically:
randomly selecting target sample data from the original sample data according to a preset proportion;
obtaining the direction attribute of the target sample data, and confirming at least one enhancement mode corresponding to the target sample data;
and maintaining the direction attribute of the target sample data, and enhancing the corresponding target sample data according to the corresponding enhancement mode to obtain enhanced sample data.
3. The palm vein data enhancement method according to claim 2, wherein the target sample data is respectively enhanced by corresponding enhancement modes to obtain a plurality of enhanced sample data; or carrying out comprehensive enhancement through a corresponding enhancement mode to obtain enhancement sample data.
4. The palm vein data enhancement method according to claim 2 or 3, wherein the enhancement mode comprises: shading, center clipping, aspect ratio clipping, brightness adjustment, contrast adjustment and saturation adjustment.
5. The palm vein data enhancement method according to claim 1, wherein the ROI region is a square region.
6. A palm vein data enhancement device, comprising:
the data acquisition unit is used for acquiring initial palm vein image data;
the region extraction unit is used for carrying out image detection on the initial palm vein image data, extracting a corresponding ROI (region of interest) region as original sample data, and marking the direction attribute of the original sample data according to the image detection result;
the enhancement processing unit is used for carrying out data enhancement on the original sample data based on the direction attribute to obtain enhanced sample data;
and the data adding unit is used for adding the original sample data and the enhanced sample data into a sample data set, and the sample data set is used for training a palm vein feature extraction model.
7. The palm vein data enhancement device according to claim 6, wherein the enhancement processing unit includes:
the data selection module is used for randomly selecting target sample data from the original sample data according to a preset proportion;
the mode confirming module is used for acquiring the direction attribute of the target sample data and confirming at least one enhancement mode corresponding to the target sample data;
and the enhancement processing module is used for maintaining the direction attribute of the target sample data and enhancing the corresponding target sample data according to the corresponding enhancement mode to obtain the enhancement sample data.
8. The palm vein data enhancement device according to claim 7, wherein the target sample data is enhanced by corresponding enhancement modes respectively to obtain a plurality of enhanced sample data; or carrying out comprehensive enhancement through a corresponding enhancement mode to obtain enhancement sample data.
9. An electronic device, comprising:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, cause the electronic device to implement a palm vein data enhancement method as claimed in any one of claims 1-5.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a method of palm vein data enhancement according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111435301.3A CN114140424B (en) | 2021-11-29 | 2021-11-29 | Palm vein data enhancement method, palm vein data enhancement device, electronic equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111435301.3A CN114140424B (en) | 2021-11-29 | 2021-11-29 | Palm vein data enhancement method, palm vein data enhancement device, electronic equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114140424A true CN114140424A (en) | 2022-03-04 |
| CN114140424B CN114140424B (en) | 2023-07-18 |
Family
ID=80389081
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111435301.3A Active CN114140424B (en) | 2021-11-29 | 2021-11-29 | Palm vein data enhancement method, palm vein data enhancement device, electronic equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114140424B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102194111A (en) * | 2011-06-21 | 2011-09-21 | 哈尔滨工程大学 | Non-contact self-adapting extraction method for ROI (Region of Interest) of fist-clenching-type hand back vein sample |
| CN105474234A (en) * | 2015-11-24 | 2016-04-06 | 厦门中控生物识别信息技术有限公司 | Method and apparatus for palm vein recognition |
| CN112149521A (en) * | 2020-09-03 | 2020-12-29 | 浙江工业大学 | Palm print ROI extraction and enhancement method based on multitask convolutional neural network |
| 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 |
| CN112364805A (en) * | 2020-11-21 | 2021-02-12 | 西安交通大学 | Rotary palm image detection method |
-
2021
- 2021-11-29 CN CN202111435301.3A patent/CN114140424B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102194111A (en) * | 2011-06-21 | 2011-09-21 | 哈尔滨工程大学 | Non-contact self-adapting extraction method for ROI (Region of Interest) of fist-clenching-type hand back vein sample |
| CN105474234A (en) * | 2015-11-24 | 2016-04-06 | 厦门中控生物识别信息技术有限公司 | Method and apparatus for palm vein recognition |
| CN112149521A (en) * | 2020-09-03 | 2020-12-29 | 浙江工业大学 | Palm print ROI extraction and enhancement method based on multitask convolutional neural network |
| CN112364805A (en) * | 2020-11-21 | 2021-02-12 | 西安交通大学 | Rotary palm image detection method |
| 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 |
Non-Patent Citations (1)
| Title |
|---|
| 王鹏: "基于深度学习的掌静脉特征提取与识别算法研究", pages 4 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114140424B (en) | 2023-07-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111462183A (en) | Behavior identification method and system based on attention mechanism double-current network | |
| US9373030B2 (en) | Automated document recognition, identification, and data extraction | |
| US20210004587A1 (en) | Image detection method, apparatus, device and storage medium | |
| CN109086734B (en) | Method and device for positioning pupil image in human eye image | |
| CN110516672A (en) | Card card information identifying method, device and terminal | |
| CN109712144A (en) | Processing method, training method, equipment and the storage medium of face-image | |
| CN107622497A (en) | Image cropping method, apparatus, computer-readable recording medium and computer equipment | |
| CN111476234A (en) | Method and device for recognizing characters of shielded license plate, storage medium and intelligent equipment | |
| CN110502961B (en) | Face image detection method and device | |
| CN110717484A (en) | Image processing method and system | |
| CN106940904A (en) | Attendance checking system based on recognition of face and speech recognition | |
| WO2019205603A1 (en) | Image fuzziness measurement method and apparatus, computer device and readable storage medium | |
| CN114140424B (en) | Palm vein data enhancement method, palm vein data enhancement device, electronic equipment and medium | |
| CN102622596A (en) | Interactive positioning method based on biometric recognition | |
| CN112749696A (en) | Text detection method and device | |
| CN116822623A (en) | Method, device, equipment and storage medium for generating countermeasures network joint training | |
| CN116740794A (en) | Face fake image identification method, system, equipment and storage medium | |
| CN109598201B (en) | Action detection method and device, electronic equipment and readable storage medium | |
| US20230127373A1 (en) | Video processing method and apparatus, device and computer readable storage medium | |
| CN108171246B (en) | Clothing salient region detection method | |
| CN110348377B (en) | Fingerprint identification method and equipment | |
| CN105760913A (en) | Information recording method and information extracting method | |
| CN112308812A (en) | Method, terminal and storage medium for detecting picture definition | |
| CN112819173A (en) | Sample generation method and device and computer readable storage medium | |
| CN116109891B (en) | Image data amplification method, device, computing equipment and storage medium |
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 |