[go: up one dir, main page]

CN111680589A - Cognitive method for robot to finish face recognition based on voiceprint authentication - Google Patents

Cognitive method for robot to finish face recognition based on voiceprint authentication Download PDF

Info

Publication number
CN111680589A
CN111680589A CN202010456859.9A CN202010456859A CN111680589A CN 111680589 A CN111680589 A CN 111680589A CN 202010456859 A CN202010456859 A CN 202010456859A CN 111680589 A CN111680589 A CN 111680589A
Authority
CN
China
Prior art keywords
user
voiceprint
robot
face
recognition
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202010456859.9A
Other languages
Chinese (zh)
Inventor
刘则
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tianjin Weika Technology Co ltd
Original Assignee
Tianjin Weika Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Tianjin Weika Technology Co ltd filed Critical Tianjin Weika Technology Co ltd
Priority to CN202010456859.9A priority Critical patent/CN111680589A/en
Publication of CN111680589A publication Critical patent/CN111680589A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16Human faces, e.g. facial parts, sketches or expressions
    • G06V40/172Classification, e.g. identification
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16Human faces, e.g. facial parts, sketches or expressions
    • G06V40/174Facial expression recognition

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Manipulator (AREA)

Abstract

The invention provides a method for a robot to complete face recognition and cognition based on voiceprint authentication, which comprises the steps of acquiring a face image of a current user and calling a face atlas of the user corresponding to the user based on the voiceprint authentication; updating the storage information of the current user; modifying the storage parameters of the robot; and the robot carries out human-computer interaction with the current user according to the modified parameters. According to the invention, the storage parameters corresponding to the user are called through voiceprint recognition, the user storage information is updated in real time through expression recognition, scene recognition and voice recognition, the parameter setting of the robot is further modified, and in the following man-machine interaction, the robot can also carry out reasoning and feedback according to the user current state information of the user, so that the intelligent degree is improved, the structure is simple, and the cost is low.

Description

Cognitive method for robot to finish face recognition based on voiceprint authentication
Technical Field
The invention belongs to the technical field of intelligent robots, and particularly relates to a method for a robot to complete face recognition based on voiceprint authentication.
Background
With the progress of society, robots are not only widely used in industry, medicine, agriculture, or military, but also have been gradually incorporated into human social contact in life. At present, most of robots in the market only provide simple human-computer interaction, and user storage information related to a user is not stored, so that user information in the user storage information cannot be modified according to information input of the user, and thus diversified feedback cannot be presented. Meanwhile, the answer of the existing robot question-answering system does not generally consider the identity of a questioner, does not consider the expression and tone of the questioner, and is a universal answer, and the question-answering system has low intelligent degree and cannot well communicate with the questioner.
Disclosure of Invention
In view of the above, the present invention is directed to a method for a robot to complete face recognition and cognition based on voiceprint authentication, so that the robot can capture a large amount of user information through voiceprint recognition, thereby completing face recognition and cognition of a user in an interactive process, making feedback of the robot closer to a real-time state of the user, and communicating with a questioner well through a voiceprint recognition technology, an expression detection technology and an intelligent question and answer based on speaker identity and emotion.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
a method for a robot to complete face recognition cognition based on voiceprint authentication comprises the following specific steps:
s1: based on voiceprint authentication, the robot controller acquires a current user face image and calls a user face atlas corresponding to the user;
s2: after the robot controller compares the face image of the current user with the called face of the user, immediately updating the stored information of the current user;
s3: the robot controller modifies the storage parameters of the robot according to the updated storage information of the current user;
s4: and the robot carries out human-computer interaction with the current user according to the modified storage parameters.
Further, the method for acquiring the face image of the current user in S1 is based on artificial neural network pattern recognition.
Further, the voiceprint authentication-based method in S1 is an i-vector-based speaker identification system, which is divided into three parts, namely system model space training, enrollment speaker voiceprint generation, and test speaker identification.
Further, the specific implementation method of S1 is as follows: firstly, establishing a voiceprint and face image file of a human face; the voiceprint collector and the camera are used for collecting voiceprint files of unit personnel and face image files of human faces or taking pictures of the voiceprint files and the face image files to form voiceprint files and face print files, and the voiceprint files and the face print files are generated into face print codes to be stored;
step two, acquiring the voiceprint and the face print of the current user; capturing the voiceprint and the face print of the current user by using a voiceprint collector and a camera, and generating a face print code from the current voiceprint file and the face print file;
comparing the current face print code with the file stock; the face print coding mode is generated according to the essential characteristics of the face of the human face.
Further, the storage parameter includes a user expression of the user, the mood value in the user storage information is updated in real time according to the user expression in step S2, and the mood value is used to modify the speech algorithm of the robot in step S3.
Further, the robot controller further comprises a storage parameter acquisition module, an updating module and a modification module which are in signal connection with each other, wherein the storage parameter acquisition module comprises a scene recognition unit for recognizing a current scene, the updating module updates the user state of the user storage information in real time according to the current scene, and the modification module modifies the greeting algorithm of the robot by using the user state.
Compared with the prior art, the method for the robot to complete the face recognition cognition based on the voiceprint authentication has the following advantages:
the robot completes the face recognition cognitive method based on voiceprint authentication, calls a storage parameter corresponding to a user through voiceprint recognition, updates user storage information in real time through expression recognition, scene recognition and voice recognition, and further modifies the parameter setting of the robot, so that the robot performs man-machine interaction with the user according to the modified parameter setting; the robot can also carry out reasoning and feedback according to the current state information of the user, so that the intelligent degree is improved, the structure is simple, and the cost is low.
Detailed Description
It should be noted that the embodiments and features of the embodiments of the present invention may be combined with each other without conflict.
In the description of the present invention, the terms "first", "second", etc. are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implying any number of technical features indicated. Thus, a feature defined as "first," "second," etc. may explicitly or implicitly include one or more of that feature. In the description of the present invention, "a plurality" means two or more unless otherwise specified.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art through specific situations.
The present invention will be described in detail with reference to examples.
A method for a robot to complete face recognition cognition based on voiceprint authentication comprises the following specific steps:
s1: based on voiceprint authentication, the robot controller acquires a current user face image and calls a user face atlas corresponding to the user;
the specific implementation method of the S1 comprises the following steps: firstly, establishing a voiceprint and face image file of a human face; the voiceprint collector and the camera are used for collecting voiceprint files of unit personnel and face image files of human faces or taking pictures of the voiceprint files and the face image files to form voiceprint files and face print files, and the voiceprint files and the face print files are generated into face print codes to be stored;
step two, acquiring the voiceprint and the face print of the current user; capturing the voiceprint and the face print of the current user by using a voiceprint collector and a camera, and generating a face print code from the current voiceprint file and the face print file;
comparing the current face print code with the file stock; the face print coding mode is generated according to the essential characteristics of the face of the human face.
S2: after the robot controller compares the face image of the current user with the called face of the user, immediately updating the stored information of the current user;
s3: the robot controller modifies the storage parameters of the robot according to the updated storage information of the current user;
s4: and the robot carries out human-computer interaction with the current user according to the modified storage parameters.
The method for acquiring the face image of the current user in S1 is based on artificial neural network pattern recognition.
The voiceprint authentication-based method in the S1 is an i-vector-based speaker recognition system which is divided into three parts, namely system model space training, registered speaker voiceprint generation and speaker recognition testing.
The storage parameters include user expressions of the users, the mood values in the user storage information are updated in real time according to the user expressions in step S2, and the mood values are used to correct the speaker algorithm of the robot in step S3.
The robot controller further comprises a storage parameter acquisition module, an updating module and a correction module which are in signal connection with each other, wherein the storage parameter acquisition module comprises a scene recognition unit used for recognizing a current scene, the updating module updates the user state of the user storage information in real time according to the current scene, and the correction module corrects the greeting algorithm of the robot by using the user state.
The robot completes the face recognition cognitive method based on voiceprint authentication, calls a storage parameter corresponding to a user through voiceprint recognition, updates user storage information in real time through expression recognition, scene recognition and voice recognition, and further modifies the parameter setting of the robot, so that the robot performs man-machine interaction with the user according to the modified parameter setting; the robot can also carry out reasoning and feedback according to the current state information of the user, so that the intelligent degree is improved, the structure is simple, and the cost is low.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.

Claims (6)

1. A robot completes the cognitive method of face recognition based on voiceprint authentication, characterized by that: the method comprises the following specific steps:
s1: based on voiceprint authentication, the robot controller acquires a current user face image and calls a user face atlas corresponding to the user;
s2: after the robot controller compares the face image of the current user with the called face of the user, immediately updating the stored information of the current user;
s3: the robot controller modifies the storage parameters of the robot according to the updated storage information of the current user;
s4: and the robot carries out human-computer interaction with the current user according to the modified storage parameters.
2. The robot recognition method based on voiceprint authentication according to claim 1, wherein the method comprises the following steps: the method for acquiring the face image of the current user in S1 is based on artificial neural network pattern recognition.
3. The robot recognition method based on voiceprint authentication according to claim 1, wherein the method comprises the following steps: the voiceprint authentication-based method in the S1 is an i-vector-based speaker recognition system which is divided into three parts, namely system model space training, registered speaker voiceprint generation and speaker recognition testing.
4. The robot recognition method based on voiceprint authentication according to claim 1, wherein the method comprises the following steps: the specific implementation method of the S1 comprises the following steps: firstly, establishing a voiceprint and face image file of a human face; the voiceprint collector and the camera are used for collecting voiceprint files of unit personnel and face image files of human faces or taking pictures of the voiceprint files and the face image files to form voiceprint files and face print files, and the voiceprint files and the face print files are generated into face print codes to be stored;
step two, acquiring the voiceprint and the face print of the current user; capturing the voiceprint and the face print of the current user by using a voiceprint collector and a camera, and generating a face print code from the current voiceprint file and the face print file;
comparing the current face print code with the file stock; the face print coding mode is generated according to the essential characteristics of the face of the human face.
5. The robot recognition method based on voiceprint authentication according to claim 1, wherein the method comprises the following steps: the storage parameters include user expressions of the users, the mood values in the user storage information are updated in real time according to the user expressions in step S2, and the mood values are used to modify the speaker algorithm of the robot in step S3.
6. The robot recognition method based on voiceprint authentication according to claim 1, wherein the method comprises the following steps: the robot controller further comprises a storage parameter acquisition module, an updating module and a correction module which are in signal connection with each other, wherein the storage parameter acquisition module comprises a scene recognition unit used for recognizing a current scene, the updating module updates the user state of user storage information in real time according to the current scene, and the correction module corrects the greeting algorithm of the robot by using the user state.
CN202010456859.9A 2020-05-26 2020-05-26 Cognitive method for robot to finish face recognition based on voiceprint authentication Pending CN111680589A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010456859.9A CN111680589A (en) 2020-05-26 2020-05-26 Cognitive method for robot to finish face recognition based on voiceprint authentication

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010456859.9A CN111680589A (en) 2020-05-26 2020-05-26 Cognitive method for robot to finish face recognition based on voiceprint authentication

Publications (1)

Publication Number Publication Date
CN111680589A true CN111680589A (en) 2020-09-18

Family

ID=72434849

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010456859.9A Pending CN111680589A (en) 2020-05-26 2020-05-26 Cognitive method for robot to finish face recognition based on voiceprint authentication

Country Status (1)

Country Link
CN (1) CN111680589A (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1905445A (en) * 2005-07-27 2007-01-31 国际商业机器公司 System and method of speech identification using mobile speech identification card
CN106127156A (en) * 2016-06-27 2016-11-16 上海元趣信息技术有限公司 Robot interactive method based on vocal print and recognition of face
CN106462384A (en) * 2016-06-29 2017-02-22 深圳狗尾草智能科技有限公司 Multi-modal based intelligent robot interaction method and intelligent robot
CN109036435A (en) * 2018-08-15 2018-12-18 深圳平安综合金融服务有限公司上海分公司 Authentication and recognition methods based on voiceprint

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1905445A (en) * 2005-07-27 2007-01-31 国际商业机器公司 System and method of speech identification using mobile speech identification card
US20070036289A1 (en) * 2005-07-27 2007-02-15 Fu Guo K Voice authentication system and method using a removable voice id card
CN106127156A (en) * 2016-06-27 2016-11-16 上海元趣信息技术有限公司 Robot interactive method based on vocal print and recognition of face
CN106462384A (en) * 2016-06-29 2017-02-22 深圳狗尾草智能科技有限公司 Multi-modal based intelligent robot interaction method and intelligent robot
CN109036435A (en) * 2018-08-15 2018-12-18 深圳平安综合金融服务有限公司上海分公司 Authentication and recognition methods based on voiceprint

Similar Documents

Publication Publication Date Title
CN109769099B (en) Method and device for detecting abnormality of call person
CN110991381B (en) A real-time classroom student status analysis and instruction reminder system and method based on behavior and voice intelligent recognition
US5666400A (en) Intelligent recognition
CN107808145B (en) Interactive identity authentication and tracking method and system based on multi-mode intelligent robot
CN109941231A (en) Vehicle-mounted terminal equipment, vehicle-mounted interactive system and exchange method
CN112653980B (en) Interactive self-checking and matching method for intelligent hearing aid
CN111368053A (en) Mood pacifying system based on legal consultation robot
CN115439892B (en) An identity recognition method based on palm print and palm vein multimodal fusion
CN108670128A (en) The method and sweeping robot of voice control sweeping robot
CN112307975A (en) Multi-modal emotion recognition method and system integrating voice and micro-expressions
CN108376144A (en) Man-machine more wheel dialogue methods that scene based on deep neural network automatically switches
CN109934097A (en) A kind of expression and mental health management system based on artificial intelligence
CN118782212A (en) A social simulation digital intervention system based on virtual reality
US7246061B2 (en) Method for the voice-operated identification of the user of a telecommunications line in a telecommunications network in the course of a dialog with a voice-operated dialog system
CN119576121A (en) Emotional perception interaction method and system of brain-computer interface headset
CN111680589A (en) Cognitive method for robot to finish face recognition based on voiceprint authentication
Khan et al. EEG based aptitude detection system for stress regulation in health care workers
CN118013010A (en) Robot interaction method based on large language model
CN112102808A (en) Method and system for constructing deep neural network for voice forgery
CN120125082A (en) A teaching evaluation system based on sensing device
CN111159676A (en) Multi-dimensional identity authentication system and method based on face recognition
CN109919127B (en) Mute language conversion system
CN117251052A (en) Brain-computer adaptive learning method of brain-computer fusion
CN110867106B (en) Chinese teaching system
CN115878776A (en) Multi-round dialog emotional reasoning method and system based on emotional dynamics

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20200918

RJ01 Rejection of invention patent application after publication