Palm recognition method and device and electronic equipment

Ultrasonic obtains palm profile and pattern information, and performs contour and pattern comparison, solving the problems of low efficiency and poor accuracy in existing palm recognition technology, achieving more efficient and accurate palm recognition.

CN118968570APending Publication Date: 2024-11-15CHINA MOBILE M2M +1
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411025490.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-29
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

Existing palm recognition technology relies on high-precision image capture and complex image processing algorithms, resulting in low recognition efficiency and great influence from environmental factors and poor accuracy.

Method used

Ultrasonic waves are used to obtain the outline and texture information of the palm, first perform the outline comparison, and then perform the check value of the texture information and the texture itself to generate the palm recognition result.

Benefits of technology

It improves the efficiency and accuracy of palm recognition, reduces the amount of data during the recognition process, and enhances the accurate recognition ability of palm recognition.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118968570A_ABST
    Figure CN118968570A_ABST
Patent Text Reader

Abstract

The invention discloses a palm recognition method and device and electronic equipment, and relates to the technical field of terminals. The palm recognition method comprises the following steps: acquiring first palm information of a palm to be recognized by using ultrasonic waves, wherein the first palm information comprises first contour information and first line information; comparing the first contour information with second contour information in second palm information in a palm database to obtain a contour comparison result; under the condition that the contour comparison result indicates that the first contour information is matched with second contour information in the target second palm information, comparing a verification value of the first line information with a verification value of second line information in the target second palm information to obtain a verification value comparison result; and under the condition that the verification value comparison result indicates that the verification value is matched, extracting target line information from the first line information, comparing the target line information with the second line information, and generating a palm recognition result. According to the invention, the accuracy and efficiency of palm recognition can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application belongs to the field of terminal technology, and in particular relates to a palm recognition method, device and electronic device. Background Art

[0002] Palm recognition technology has become a standard feature of mainstream mobile terminal manufacturers. Palm recognition can not only be used for functions such as unlocking and waking up mobile terminals, but also serve as a barrier to protect data information in terminal devices.

[0003] Existing palm recognition technology mainly uses optical scanning, which captures and analyzes high-definition images of the palm to identify its unique texture and lines.

[0004] However, this method relies on high-precision image capture and complex image processing algorithms, resulting in low recognition efficiency. It is also significantly affected by environmental factors, resulting in poor recognition accuracy. Summary of the Invention

[0005] The embodiments of the present application provide a palm recognition method, device, and electronic device, which can improve the accuracy and efficiency of palm recognition.

[0006] In one aspect of an embodiment of the present application, a palm recognition method is provided, comprising:

[0007] Acquire first palm information of a palm to be identified by using ultrasound, where the first palm information includes first contour information and first texture information;

[0008] Comparing the first contour information with the second contour information in each second palm information in the palm database to obtain a contour comparison result;

[0009] When the contour comparison result indicates that the first contour information matches the second contour information in the target second palm information, comparing the check value of the first grain information with the check value of the second grain information in the target second palm information to obtain a check value comparison result;

[0010] When the verification value comparison result indicates that the verification values ​​match, target texture information is extracted from the first texture information and compared with the second texture information to generate a palm recognition result.

[0011] In one aspect of an embodiment of the present application, a palm recognition device is provided, comprising:

[0012] An information acquisition module, configured to acquire first palm information of a palm to be identified using ultrasound, where the first palm information includes first contour information and first texture information;

[0013] a contour comparison module, configured to compare the first contour information with the second contour information in each second palm information in the palm database to obtain a contour comparison result;

[0014] a verification value comparison module, configured to compare the verification value of the first texture information with the verification value of the second texture information in the target second palm information, when the contour comparison result indicates that the first contour information matches the second contour information in the target second palm information, to obtain a verification value comparison result;

[0015] The pattern comparison module is used to extract target pattern information from the first pattern information and compare it with the second pattern information to generate a palm recognition result when the verification value comparison result indicates that the verification value matches.

[0016] In one aspect of an embodiment of the present application, an electronic device is provided, which includes: a memory and a program or instruction stored in the memory and executable on a processor, wherein when the program or instruction is executed by the processor, a palm recognition method as provided in any one of the above-mentioned embodiments of the present application is implemented.

[0017] In one aspect of an embodiment of the present application, a readable storage medium is provided, on which a program or instruction is stored. When the program or instruction is executed by a processor, a palm recognition method as provided in any aspect of the above-mentioned embodiment of the present application is implemented.

[0018] In one aspect of an embodiment of the present application, a computer program product is provided. When instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the palm recognition method provided in any aspect of the above-mentioned embodiment of the present application.

[0019] In the palm recognition method provided in an embodiment of the present application, first palm information of a palm to be identified is acquired via ultrasound. The first palm information includes first outline information and first texture information. The first outline information is then compared with the second outline information in each second palm information in a palm database. Only when the first outline information matches the second outline information is the check value of the texture information and the partial texture information itself further verified. By acquiring the first palm information via ultrasound and then, during the palm recognition process, first comparing the outline information and, if the outline information matches, then comparing the partial texture information, the data volume of the palm recognition process is reduced, thereby improving the efficiency of palm recognition. Furthermore, by separately verifying the outline information, the check value of the texture information, and the texture information itself, the present application can accurately identify the palm and improve the accuracy of palm recognition. Thus, the embodiment of the present application utilizes the palm outline information, the check value of the texture information, and the partial texture information itself for verification, thereby improving the accuracy and efficiency of palm recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0021] Figure 1 This is a flowchart of a palm recognition method provided by an embodiment of the present application;

[0022] Figure 2 is a flowchart of a palm recognition method provided by another embodiment of the present application;

[0023] Figure 3 is a flowchart of a palm recognition method provided by another embodiment of the present application;

[0024] Figure 4 is a flowchart of a palm recognition method provided by another embodiment of the present application;

[0025] Figure 5 is a flowchart of a palm recognition method provided by another embodiment of the present application;

[0026] Figure 6 This is a schematic structural diagram of a palm recognition device provided by an embodiment of the present application;

[0027] Figure 7 This is a structural diagram of a palm recognition device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0028] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is merely to provide a better understanding of the present application by illustrating the examples of the present application.

[0029] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, the elements defined by the phrase "comprising..." do not exclude the presence of other identical elements in the process, method, article, or device comprising the elements.

[0030] It should be noted that the acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.

[0031] It should be noted that in the embodiments of the present application, certain software, components, models and other existing solutions in the industry may be mentioned. They should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present application, but it does not mean that the applicant has or will necessarily use the solution.

[0032] Existing palm recognition technology primarily relies on optical scanning, capturing and analyzing high-definition images of the palm to identify its unique texture and lines. However, this method relies on high-precision image capture and complex image processing algorithms, resulting in low recognition efficiency. Furthermore, this method is significantly affected by environmental factors, resulting in poor recognition accuracy.

[0033] The present application aims to provide a palm recognition method, apparatus, and electronic device. In the palm recognition method provided in the embodiments of the present application, first palm information of a palm to be recognized is acquired via ultrasound. The first palm information includes first outline information and first texture information. The first outline information is then compared with the second outline information of each second palm information in a palm database. Only when the first outline information matches the second outline information is the check value of the texture information and the partial texture information itself verified. By acquiring the first palm information via ultrasound and then, during the palm recognition process, first comparing the outline information and, if the outline information matches, then comparing the partial texture information, the data volume during the palm recognition process is reduced, thereby improving the efficiency of palm recognition. Furthermore, by separately verifying the outline information, the check value of the texture information, and the texture information itself, the present application can accurately identify the palm and improve the accuracy of palm recognition. Thus, the embodiments of the present application utilize the palm outline information, the check value of the texture information, and the partial texture information itself for verification, thereby improving the accuracy and efficiency of palm recognition.

[0034] The following describes specific embodiments of the palm recognition method, device, and electronic device provided by the embodiments of the present application.

[0035] Figure 1 A flowchart of a palm recognition method is provided. The palm recognition method can be applied to a server and may include the following steps S101 to S104.

[0036] S101 , obtaining first palm information of a palm to be identified by using ultrasound, where the first palm information includes first outline information and first line information.

[0037] In this embodiment, the first contour information may include at least one of the palm contour size and the palm thickness size.

[0038] The first palm print information is used to represent the palm print information of the palm to be identified.

[0039] As an example, when the user places the palm to be identified within the ultrasonic detection range, the server obtains the first contour information and the first texture information of the palm to be identified through ultrasonic waves.

[0040] S102: Compare the first contour information with the second contour information in each second palm information in the palm database to obtain a contour comparison result.

[0041] In this embodiment, the second palm information is pre-entered palm information stored in the palm database.

[0042] As an example, after inputting the second palm information, the server generates a 32-bit first character string using a message digest algorithm (MD5 algorithm) according to the second contour information in the second palm information.

[0043] After obtaining the first palm information, the server will also generate a 32-bit second character string based on the first outline information in the first palm information through the Message-Digest Algorithm 5 (MD5 algorithm).

[0044] Then, the server compares the second character string with each first character string to generate an outline comparison result.

[0045] S103: When the contour comparison result indicates that the first contour information matches the second contour information in the target second palm information, the verification value of the first grain information is compared with the verification value of the second grain information in the target second palm information to obtain a verification value comparison result.

[0046] In this embodiment, the check value is character information calculated by using a data check algorithm to calculate the texture information.

[0047] The target second palm information is the second palm information corresponding to the second contour information matching the first contour information.

[0048] As an example, after inputting the second palm information, the server performs a cyclic redundancy check (CRC check) based on the second grain information in the second palm information to obtain a corresponding check value.

[0049] After obtaining the first palm information, the server also performs a cyclic redundancy check (CRC check) based on the first grain information in the first palm information to obtain a corresponding check value.

[0050] Then, if there is second contour information matching the first contour information, the verification value of the first texture information is compared with the verification value of the second texture information in the target second palm information corresponding to the matching second contour information, thereby obtaining a verification value comparison result.

[0051] If there is no second outline information matching the first outline information, it indicates that the palm database has not recorded the first palm information of the palm to be recognized, and a palm recognition failure result is output.

[0052] S104: When the verification value comparison result indicates that the verification values ​​match, extract target texture information from the first texture information and compare it with the second texture information to generate a palm recognition result.

[0053] In this embodiment, the target texture information is any part of the texture information in the first texture information, and the palm recognition result is used to indicate whether the palm to be recognized is successfully recognized.

[0054] As an example, when the verification value of the first texture information matches the verification value of the second texture information in the target second palm information, the server further extracts the target texture information from the first texture information, and compares the target texture information with the second texture information to determine whether there is a part in the second texture information corresponding to the target texture information.

[0055] If there is a portion corresponding to the target texture information in the second texture information, a palm recognition result is generated indicating that the palm recognition is successful; if there is no portion corresponding to the target texture information in the second texture information, a palm recognition result is generated indicating that the palm recognition is failed.

[0056] In this embodiment, first palm information of the palm to be identified is acquired via ultrasound. The first palm information includes first outline information and first texture information. The first outline information is then compared with the second outline information in each second palm information in a palm database. Only when the first outline information matches the second outline information is the check value of the texture information and the partial texture information itself verified. This application utilizes ultrasound to acquire the first palm information, and then compares the outline information during palm recognition. If the outline information matches, the partial texture information is then compared. This reduces the amount of data required for palm recognition and improves palm recognition efficiency. Furthermore, by separately verifying the outline information, the check value of the texture information, and the texture information itself, the present application can accurately identify the palm and improve palm recognition accuracy. Thus, this embodiment utilizes the palm outline information, the check value of the texture information, and the partial texture information itself for verification, improving both the accuracy and efficiency of palm recognition.

[0057] As an optional embodiment, Figure 2 A flowchart of another palm recognition method is provided. Before S102, the palm recognition method may further include the following steps S201 to S204:

[0058] S201, using ultrasound to obtain second contour information of the palm to be recorded and first local texture information of the palm to be recorded at at least one placement angle;

[0059] S202, combining the first partial texture information to obtain second texture information of the palm to be recorded;

[0060] S203, combining the second outline information with the second texture information to obtain second palm information of the palm to be recorded;

[0061] S204: Store the second palm information in the palm database.

[0062] In this embodiment, the user places the palm to be recorded in front of the ultrasonic transmitter, and the server obtains the second contour information of the palm to be recorded using ultrasonic waves for the first time.

[0063] Then, the user switches to a plurality of different placement angles according to the voice prompt or display, and the server uses ultrasound to sequentially obtain the first local texture information at each different placement angle.

[0064] Then, the first partial texture information is combined to obtain the second texture information of the palm to be recorded. Finally, the second contour information and the second texture information are combined and stored in the palm database.

[0065] As another example, the server may also store the character string generated by the MD5 algorithm for the second contour information in the palm database, and store the verification value generated by calculating the second texture information using the data verification algorithm in the palm database, and at the same time perform advanced encryption (Advanced Encryption Standard, AES encryption) on the second texture information stored in the palm database.

[0066] This embodiment uses ultrasound to obtain the second contour information of the palm to be recorded and the texture information of the palm to be recorded at various angles, thereby ensuring the integrity of the recorded palm information. This facilitates subsequent palm recognition using the complete palm information and improves the accuracy of palm recognition.

[0067] As an optional embodiment, Figure 3 A flowchart of another palm recognition method is provided. Before S103, the palm recognition method may further include the following S301 to S303:

[0068] S301, dividing the first texture information into N second local texture information according to a preset division strategy, where N is a positive integer;

[0069] S302, performing a cyclic redundancy check on each piece of second local texture information to obtain a local check value corresponding to the second local texture information;

[0070] S303: Combine the local check values ​​corresponding to the second local texture information to obtain the check value of the first texture information.

[0071] In this embodiment, the preset division strategy is a pre-set strategy for dividing texture information.

[0072] As an example, after obtaining the first texture information of the palm to be identified through ultrasound, the server may divide the first texture information into 9 parts according to a preset division strategy, thereby obtaining 9 pieces of second partial texture information.

[0073] Then, CRC check is performed on each of the nine second partial texture information to obtain corresponding check values. Finally, the nine check values ​​are combined to obtain the check value corresponding to the first texture information.

[0074] Through this embodiment, the first texture information is divided into N pieces of second partial texture information according to a preset division strategy. During CRC verification, the nine pieces of second partial texture information can be verified simultaneously, thereby improving data processing efficiency. Furthermore, during subsequent verification value comparison, the verification values ​​corresponding to the nine pieces of second partial texture information can be used to accurately identify whether the verification values ​​of the first texture information are the same, and any differences can be quickly and accurately located.

[0075] As an optional embodiment, S104 may specifically include:

[0076] When the check value comparison result indicates that the check values ​​match, randomly extracting one piece of second local texture information from the N pieces of second local texture information as target texture information;

[0077] Comparing the target texture information with each third local texture information in the second texture information, where the third local texture information is local texture information obtained by dividing the second texture information according to a preset division strategy;

[0078] If there is third local texture information matching the target texture information, generating a palm recognition result indicating that the palm recognition is successful;

[0079] In the absence of the third local texture information matching the target texture information, a palm recognition result is generated indicating that the palm recognition has failed.

[0080] In this embodiment, the target texture information is any one of the N second partial texture information.

[0081] As an example, if the checksum matches, the server further verifies the texture information itself. In this case, the server randomly extracts a target texture information from the N second partial texture information of the first texture information. Simultaneously, the second texture information is partitioned using the same pre-set partitioning strategy as the first texture information to obtain N third partial texture information of the second texture information.

[0082] Then, the target pattern information is compared with N pieces of third local pattern information respectively. If there is third local pattern information that matches the target pattern information, a palm recognition result is generated to indicate that the palm recognition is successful; if there is no third local pattern information that matches the target pattern information, a palm recognition result is generated to indicate that the palm recognition fails.

[0083] Through this embodiment, only part of the texture information is randomly extracted from the N second partial texture information of the first texture information for verification, and the amount of data for palm recognition is small, thereby improving the efficiency of palm recognition.

[0084] As an optional embodiment, Figure 4 A flowchart of another palm recognition method is provided. After S104, the palm recognition method may further include the following S401 to S403:

[0085] S401, obtaining a gesture type of at least one target gesture of a palm to be recognized, where the target gesture has a corresponding time tag;

[0086] S402, generating a first gesture sequence according to the gesture type and time tag of the target gesture;

[0087] S403: Match the first gesture sequence with each second gesture sequence in the gesture database to generate a gesture recognition result.

[0088] In this embodiment, the gesture type is used to represent the type of target gesture made by the palm to be recognized. For example, the gesture type may be a thumbs-up.

[0089] The gesture sequence includes at least one target gesture arranged in time sequence.

[0090] The gesture recognition result is used to represent the gesture meaning represented by the first gesture sequence of the palm to be recognized.

[0091] As an example, after the palm recognition is passed, the server can further recognize the gesture. In this case, the server will obtain at least one target gesture of the palm to be recognized through ultrasound and determine the gesture type corresponding to the target gesture.

[0092] Then, based on the time tags of each target gesture, the gestures are sorted chronologically to generate a first gesture sequence. The first gesture sequence is then matched with each second gesture sequence pre-stored in the gesture database to obtain a second gesture sequence that matches the first gesture sequence. Finally, based on the gesture meanings of the second gesture sequences that match the first gesture sequence, a gesture recognition result is generated.

[0093] Through this embodiment, after the palm is recognized, the meaning of the target gesture made by the palm to be recognized is further recognized, so that the corresponding mobile terminal can be instructed to perform a corresponding action according to the meaning of the target gesture, thereby improving the security of the mobile terminal.

[0094] As an optional embodiment, Figure 5 A flowchart of another palm recognition method is provided. Before S403, the palm recognition method may further include the following steps S501 to S503:

[0095] S501, using ultrasound to obtain a local gesture sequence of the palm to be recorded at at least one placement angle;

[0096] S502, combining the partial gesture sequences of the palm to be recorded at at least one placement angle to obtain a second gesture sequence of the palm to be recorded;

[0097] S503: Store the second gesture sequence and the gesture meaning of the second gesture sequence into a gesture database according to a preset storage strategy.

[0098] In this embodiment, the preset storage strategy is a storage method of a preset second gesture sequence and the gesture meaning corresponding to the second gesture sequence.

[0099] As an example, the user places the palm to be recorded in front of the ultrasonic transmitter. The user switches to multiple different placement angles according to voice prompts or displays. The server uses ultrasonic waves to obtain local gesture sequences at different placement angles in turn.

[0100] Then, the local gesture sequences are combined to obtain a second gesture sequence of the palm to be recorded, and finally the second gesture sequence and the gesture meaning corresponding to the second gesture sequence are stored in the gesture database according to a preset storage strategy.

[0101] This embodiment uses ultrasound to obtain a sequence of partial gestures of the palm to be recorded at various angles, ensuring the integrity of the recorded gesture information. This facilitates subsequent use of the complete gesture information for gesture recognition, improving the accuracy of gesture recognition.

[0102] As an optional embodiment, S401 may specifically include:

[0103] Using ultrasonic waves to obtain gesture information of the target gesture of the palm to be recognized;

[0104] Through convolutional neural network, the gesture feature information of the target gesture is extracted from the gesture information;

[0105] The gesture feature information is input into the support vector machine classifier to obtain the gesture type of the target gesture.

[0106] In this embodiment, the gesture information is information indicating the gesture behavior of the target gesture. For example, the gesture information may include the gesture rate and amplitude energy acquired by ultrasound.

[0107] The convolutional neural network is a feature extractor used to further extract gesture feature information from gesture information.

[0108] As an example, the server uses ultrasound to obtain gesture information of the target gesture of the palm to be recognized, and then uses a convolutional neural network as a feature extractor to extract gesture feature information of the target gesture from the gesture information.

[0109] Then, the gesture feature information of the target gesture is input into a support vector machine (SVM) classifier, so that the gesture type of the target gesture is output through the SVM classifier.

[0110] This embodiment uses a convolutional neural network to extract the target gesture's gesture features from the gesture information. This information is then fed into a support vector machine classifier to determine the target gesture's gesture type. This facilitates subsequent gesture recognition based on the target gesture's gesture type, improving gesture recognition efficiency.

[0111] As an optional embodiment, S402 may specifically include:

[0112] generating a third gesture sequence through a hidden Markov model according to the gesture type and time label of the target gesture;

[0113] The third gesture sequence is corrected through a recurrent neural network to obtain the first gesture sequence.

[0114] In this embodiment, a recurrent neural network is used to solve the problems of intervals and delays in the third gesture sequence. For example, the recurrent neural network can be a long short-term memory network or a gated recurrent unit network.

[0115] As an example, the server uses a Hidden Markov Model (HMM) to process the target gestures according to their gesture types and time tags to obtain a third gesture sequence to represent the state transition of the target gestures.

[0116] Then, the third gesture sequence is modified using a long short-term memory network or a gated recurrent unit network to obtain the first gesture sequence.

[0117] This embodiment first generates a third gesture sequence using a hidden Markov model, and then further modifies the third gesture sequence using a recurrent neural network to obtain a more accurate first gesture sequence. Thus, this embodiment of the application accurately characterizes the state transition of the target gesture by obtaining an accurate first gesture sequence, thereby improving the accuracy of gesture recognition.

[0118] As an optional embodiment, in order to improve the accuracy and stability of ultrasonic acquisition, the present application chooses to use a 40kHz ultrasonic sensor to avoid the grating lobe effect and rapid attenuation problems caused by high frequency.

[0119] At the same time, a high-density matrix ultrasonic transmitter is used, and the resolution reaches the distance between the grain gaps, thereby improving the resolution of grain information.

[0120] Furthermore, based on the characteristics of the human palm, a dual ultrasonic sensor structure is used, involving data synchronization and data fusion. Both sensors are activated using the same clock source, and the information collected by both sensors is processed simultaneously. The upper sensor is responsible for collecting contour information, while the lower sensor is responsible for collecting texture information.

[0121] Based on the palm recognition method, the present application also provides a specific embodiment of a palm recognition device.

[0122] like Figure 6 As shown, the palm recognition device provided in the embodiment of the present application includes an information acquisition module 610 , a contour comparison module 620 , a verification value comparison module 630 and a texture comparison module 640 .

[0123] The information acquisition module 610 is configured to acquire first palm information of a palm to be identified by using ultrasound, where the first palm information includes first outline information and first texture information.

[0124] The contour comparison module 620 is configured to compare the first contour information with the second contour information in each second palm information in the palm database to obtain a contour comparison result.

[0125] The verification value comparison module 630 is used to compare the verification value of the first texture information with the verification value of the second texture information in the target second palm information when the contour comparison result indicates that the first contour information matches the second contour information in the target second palm information to obtain a verification value comparison result.

[0126] The pattern comparison module 640 is configured to extract target pattern information from the first pattern information and compare it with the second pattern information to generate a palm recognition result when the verification value comparison result indicates that the verification values ​​match.

[0127] In this embodiment, first palm information of the palm to be identified is acquired via ultrasound. The first palm information includes first outline information and first texture information. The first outline information is then compared with the second outline information in each second palm information in a palm database. Only when the first outline information matches the second outline information is the check value of the texture information and the partial texture information itself verified. This application utilizes ultrasound to acquire the first palm information, and then compares the outline information during palm recognition. If the outline information matches, the partial texture information is then compared. This reduces the amount of data required for palm recognition and improves palm recognition efficiency. Furthermore, by separately verifying the outline information, the check value of the texture information, and the texture information itself, the present application can accurately identify the palm and improve palm recognition accuracy. Thus, this embodiment utilizes the palm outline information, the check value of the texture information, and the partial texture information itself for verification, improving both the accuracy and efficiency of palm recognition.

[0128] As an optional embodiment, the palm recognition device further includes the following modules:

[0129] The information acquisition module 610 is further configured to use ultrasound to acquire second contour information of the palm to be recorded and first local texture information of the recorded palm at at least one placement angle;

[0130] An information combination module, configured to combine the first partial texture information to obtain second texture information of the palm to be recorded;

[0131] The information combination module is further used to combine the second contour information with the second texture information to obtain the second palm information to be recorded;

[0132] The information storage module is used to store the second palm information in the palm database.

[0133] As an optional embodiment, the palm recognition device further includes the following modules:

[0134] An information division module, configured to divide the first texture information into N second local texture information according to a preset division strategy, where N is a positive integer;

[0135] A check value generating module is used to perform a cyclic redundancy check on each second local texture information to obtain a local check value corresponding to the second local texture information;

[0136] The check value combination module is used to combine the local check values ​​corresponding to the second local texture information to obtain the check value of the first texture information.

[0137] As an optional embodiment, the texture comparison module 640 includes the following units:

[0138] an information extraction unit, configured to extract, when the check value comparison result indicates that the check values ​​match, any one piece of second local texture information from the N pieces of second local texture information as target texture information;

[0139] a texture comparison unit, configured to compare the target texture information with each third local texture information in the second texture information, wherein the third local texture information is local texture information obtained by dividing the second texture information according to a preset division strategy;

[0140] A result generating unit, configured to generate a palm recognition result indicating that the palm recognition is successful when there is third local texture information matching the target texture information;

[0141] The result generating unit is further configured to generate a palm recognition result indicating palm recognition failure when there is no third local texture information matching the target texture information.

[0142] As an optional embodiment, the palm recognition device further includes the following modules:

[0143] A gesture acquisition module, configured to acquire a gesture type of at least one target gesture of a palm to be recognized, wherein the target gesture has a corresponding time tag;

[0144] A sequence generation module, configured to generate a first gesture sequence according to the gesture type and time tag of the target gesture;

[0145] The sequence matching module is used to match the first gesture sequence with each second gesture sequence in the gesture database to generate a gesture recognition result.

[0146] As an optional embodiment, the palm recognition device further includes the following modules:

[0147] A sequence acquisition module, configured to use ultrasound to acquire a local gesture sequence of a palm to be recorded at at least one placement angle;

[0148] a sequence combination module, configured to combine a local gesture sequence of the palm to be recorded at at least one placement angle to obtain a second gesture sequence of the palm to be recorded;

[0149] The sequence storage module is used to store the second gesture sequence and the gesture meaning of the second gesture sequence into the gesture database according to a preset storage strategy.

[0150] As an optional embodiment, the gesture acquisition module includes the following units:

[0151] an information acquisition unit, configured to acquire gesture information of a target gesture of a palm to be recognized using ultrasonic waves;

[0152] A feature extraction unit, configured to extract gesture feature information of a target gesture from the gesture information through a convolutional neural network;

[0153] The type determination unit is used to input the gesture feature information into the support vector machine classifier to obtain the gesture type of the target gesture.

[0154] As an optional embodiment, the sequence generation module includes the following units:

[0155] a sequence generation unit, configured to generate a third gesture sequence through a hidden Markov model according to the gesture type and time label of the target gesture;

[0156] The sequence correction unit is used to correct the third gesture sequence through a recurrent neural network to obtain the first gesture sequence.

[0157] Based on the palm recognition method, the present application also provides a specific embodiment of a palm recognition device.

[0158] Figure 7 A hardware structure diagram of a palm recognition device provided in an embodiment of the present application is shown.

[0159] The palm recognition device may include a processor 701 and a memory 702 storing computer program instructions.

[0160] Specifically, the processor 701 may include a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0161] The memory 702 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 702 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 702 may include removable or non-removable (or fixed) media. Where appropriate, the memory 702 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 702 is a non-volatile solid-state memory.

[0162] The memory may include read-only memory (ROM), random access memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical or other physical / tangible memory storage devices. Thus, generally, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to an aspect of the present disclosure.

[0163] The processor 701 reads and executes computer program instructions stored in the memory 702 to implement any one of the palm recognition methods in the above embodiments.

[0164] In one example, the palm recognition device may further include a communication interface 703 and a bus 710. Figure 7 As shown, the processor 701, the memory 702, and the communication interface 703 are connected via a bus 710 and communicate with each other.

[0165] The communication interface 703 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0166] Bus 710 includes hardware, software or both, and the parts of palm recognition device are coupled to each other.For example, and not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industry standard architecture (EISA) bus, front side bus (FSB), hypertransport (HT) interconnection, industry standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 710 may include one or more buses. Although the present application embodiment describes and shows specific bus, the application considers any suitable bus or interconnection.

[0167] In addition, in conjunction with the palm recognition method in the above embodiments, the present application embodiment may provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by a processor, any of the palm recognition methods in the above embodiments is implemented.

[0168] In addition, in combination with the palm recognition method in the above embodiments, the present application can provide a computer program product to implement the palm recognition method in the above embodiments. When the instructions in the computer program product are executed by a processor of an electronic device, any one of the palm recognition methods in the above embodiments is implemented.

[0169] It should be understood that the present application is not limited to the specific configurations and processes described above and illustrated in the figures. For the sake of brevity, a detailed description of known methods is omitted here. In the above embodiments, several specific steps are described and illustrated as examples. However, the method process of the present application is not limited to the specific steps described and illustrated. Those skilled in the art can make various changes, modifications, and additions, or change the order of the steps after understanding the spirit of the present application.

[0170] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium that can store or transmit information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROMs, flash memories, erasable ROMs (EROMs), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0171] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps. In other words, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0172] Aspects of the present disclosure have been described above with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor or a field programmable logic circuit. It is also understood that each box in the block diagram and / or flowchart and the combination of the boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0173] The above description is only a specific embodiment of the present application. Those skilled in the art will clearly understand that for the convenience and brevity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the scope of protection of the present application.

Claims

1. A palm recognition method, characterized in that: The method comprises: Acquire first palm information of a palm to be identified using ultrasound, where the first palm information includes first outline information and first texture information; Comparing the first contour information with the second contour information in each second palm information in the palm database to obtain a contour comparison result; If the contour comparison result indicates that the first contour information matches the second contour information in the target second palm information, comparing the check value of the first grain information with the check value of the second grain information in the target second palm information to obtain a check value comparison result; When the verification value comparison result indicates that the verification values ​​match, target texture information is extracted from the first texture information and compared with the second texture information to generate a palm recognition result.

2. The method according to claim 1, characterized in that Before comparing the first contour information with the second contour information in each second palm information in the palm database to obtain a contour comparison result, the method further includes: Acquire second contour information of the palm to be recorded and first local texture information of the palm to be recorded at at least one placement angle using ultrasound; combining the first partial texture information to obtain the second texture information of the palm to be recorded; combining the second contour information and the second texture information to obtain second palm information of the palm to be recorded; The second palm information is stored in the palm database.

3. The method according to claim 1, characterized in that When the contour comparison result indicates that the first contour information matches the second contour information in the target second palm information, before obtaining the verification value comparison result, the method further includes: Dividing the first texture information into N second local texture information according to a preset division strategy, where N is a positive integer; Performing a cyclic redundancy check on each piece of the second local texture information to obtain a local check value corresponding to the second local texture information; The local check values ​​corresponding to the respective pieces of the second local texture information are combined to obtain the check value of the first texture information.

4. The method according to claim 3, characterized in that When the verification value comparison result indicates that the verification values ​​match, extracting target texture information from the first texture information and comparing it with the second texture information to generate a palm recognition result includes: When the check value comparison result indicates that the check values ​​match, randomly extracting one piece of the second local texture information from the N pieces of second local texture information as the target texture information; comparing the target texture information with each piece of third local texture information in the second texture information, wherein the third local texture information is local texture information obtained by dividing the second texture information according to the preset division strategy; If the third local texture information matches the target texture information, generating the palm recognition result to indicate that the palm recognition is successful; In the absence of the third local texture information matching the target texture information, the palm recognition result is generated to indicate palm recognition failure.

5. The method according to claim 1, wherein When the verification value comparison result indicates that the verification values ​​match, extracting target texture information from the first texture information and comparing it with the second texture information to generate a palm recognition result, the method further includes: Acquire a gesture type of at least one target gesture of the palm to be identified, wherein the target gesture has a corresponding time tag; generating a first gesture sequence according to the gesture type of the target gesture and the time tag; The first gesture sequence is matched with each second gesture sequence in a gesture database to generate a gesture recognition result.

6. The method according to claim 5, characterized in that Before matching the first gesture sequence with each second gesture sequence in the gesture database to generate a gesture recognition result, the method further includes: Using ultrasound to obtain a local gesture sequence of the palm to be recorded at at least one placement angle; combining the partial gesture sequences of the palm to be recorded at at least one placement angle to obtain a second gesture sequence of the palm to be recorded; The second gesture sequence and the gesture meaning of the second gesture sequence are stored in the gesture database according to a preset storage strategy.

7. The method according to claim 5, characterized in that The acquiring the gesture type of at least one target gesture of the palm to be recognized includes: Acquiring gesture information of a target gesture of the palm to be recognized using ultrasonic waves; Extracting gesture feature information of the target gesture from the gesture information through a convolutional neural network; The gesture feature information is input into a support vector machine classifier to obtain the gesture type of the target gesture.

8. The method according to claim 5, characterized in that The generating a first gesture sequence according to the gesture type of the target gesture and the time tag includes: generating a third gesture sequence by a hidden Markov model according to the gesture type of the target gesture and the time tag; The third gesture sequence is modified through a recurrent neural network to obtain the first gesture sequence.

9. A palm recognition device, characterized in that: The device comprises: An information acquisition module, configured to acquire first palm information of a palm to be identified using ultrasound, wherein the first palm information includes first contour information and first texture information; a contour comparison module, configured to compare the first contour information with the second contour information in each second palm information in a palm database to obtain a contour comparison result; a verification value comparison module, configured to compare the verification value of the first texture information with the verification value of the second texture information in the target second palm information to obtain a verification value comparison result when the contour comparison result indicates that the first contour information matches the second contour information in the target second palm information; The pattern comparison module is used to extract target pattern information from the first pattern information and compare it with the second pattern information to generate a palm recognition result when the verification value comparison result indicates that the verification value matches.

10. An electronic device, characterized in that: The device includes: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the palm recognition method according to any one of claims 1 to 8 is implemented.

Citation Information

Cited By

  • Laryngeal cancer atomization control method and atomization equipment

    CN119818783A