CN104809439B - It is a kind of exception blink movement identification and based reminding method and device - Google Patents

It is a kind of exception blink movement identification and based reminding method and device Download PDF

Info

Publication number
CN104809439B
CN104809439B CN201510213887.7A CN201510213887A CN104809439B CN 104809439 B CN104809439 B CN 104809439B CN 201510213887 A CN201510213887 A CN 201510213887A CN 104809439 B CN104809439 B CN 104809439B
Authority
CN
China
Prior art keywords
blink
abnormal
movement
processing unit
unit
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.)
Active
Application number
CN201510213887.7A
Other languages
Chinese (zh)
Other versions
CN104809439A (en
Inventor
姜振宇
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.)
Individual
Original Assignee
Individual
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 Individual filed Critical Individual
Priority to CN201510213887.7A priority Critical patent/CN104809439B/en
Publication of CN104809439A publication Critical patent/CN104809439A/en
Application granted granted Critical
Publication of CN104809439B publication Critical patent/CN104809439B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR 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
    • G06V40/176Dynamic expression

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)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

The present invention relates to a kind of identification of abnormal blink movement and based reminding method and device, the device that the method uses includes: wearable terminal equipment, cloud signal processing unit, processing result is counter send unit;Wherein, wearable terminal equipment is worn on tester's body, for capturing and transmitting tested people's blink action data;Cloud signal processing unit is for calculating tested people's blink action data;Processing result is counter to send unit to be responsible for assigning cloud signal processing unit into the abnormal blink the result of the action that instruction needs to prompt and send back wearable terminal equipment by wireless network;The blink action data of tested people is carried out the processing of three phases: first stage by reception of wireless signals by cloud signal processing unit, and the blink for calculating tested people acts base-line data;Second stage captures the blink action data in test problem question and answer stage;The blink action data of second stage is compared the blink movement base-line data of first stage and carries out opposite operation by the phase III, and filtering obtains abnormal blink the result of the action.

Description

It is a kind of exception blink movement identification and based reminding method and device
Technical field
The present invention relates to a kind of identification of abnormal blink movement and based reminding method and devices, belong to intelligent Expression Recognition neck Domain.
Background technique
Micro- expression is the very quick expression for a kind of duration being only 1/25 second to 1/5 second, expresses people and attempts to press Suppression and hiding real emotion.Micro- expression is that the mankind attempt to constrain or that whens hiding real feelings reveals is very of short duration, cannot The facial expression of autonomous control.As the effective clue of identification lie, micro- expression can be applied to the fields such as safety, the administration of justice, clinic.
Existing wearable (portable) Expression Recognition equipment is divided into two classes, and one kind is worn on the tested person, Yi Leipei It wears with tester, also has plenty of fixing camera on probation and be directed to tested personnel's shooting, non-portable but function and second Class is similar.
The first kind is worn on the blink action recognition equipment on the tested person, has the drawback that interference tested personnel's Natural blink movement.The ideal state of blink motion test is the interference for not having any visual aspects to tested personnel, otherwise The blink movement producing cause that tested personnel can not be differentiated, is difficult to change with its psychological condition carrying out causalnexus, having very much can Energy its blink movement is that the reasons such as the wearing by equipment, the curiosity to equipment, concern cause, so the data obtained is contaminated Data.
Second class is shot other than tested body by the equipment that tester side is worn or is used and identification is tested The expression of personnel and blink act, this kind of equipment there are the shortcomings that clearly.Either expression capture and identification software, still Blink motion capture and analytical equipment, all lack two vital factors, ask first is that having no idea to establish with mentioned test Association between topic, second is that not establishing the algorithmic procedure of baseline.So this kind of equipment is merely capable of playing " performance expression " Recognition reaction, and cannot capture and analyze the slight expression for representing the tested true phychology of personnel and abnormal blink movement.It will be more These disadvantages are mended, need to solve two problems, are followed by establish quilt with the correlation technology of test problem in test method first The algorithm of tester individual's base-line data.
Summary of the invention
To achieve the purpose that, according to micro- Expression analysis tested personnel psychological activity, the present invention relates to a kind of abnormal blinks to act Identification and based reminding method, the device that the method uses include: wearable terminal equipment, cloud signal processing unit, processing As a result counter to send unit;Wherein, wearable terminal equipment is worn on tester's body, for capturing and transmitting tested people's blink Action data;Cloud signal processing unit is for calculating tested people's blink action data;Processing result is counter send unit be responsible for by Cloud signal processing unit assigns the abnormal blink the result of the action that instruction needs to prompt and sends back wearable end by wireless network End equipment.
The blink action data of tested people is carried out three ranks by reception of wireless signals by cloud signal processing unit The processing of section:
First stage, the blink for calculating tested people act base-line data;
Second stage captures the blink action data in test problem question and answer stage;
The blink action data of second stage is compared the blink movement base-line data of first stage simultaneously by the phase III Opposite operation is carried out, filtering obtains abnormal blink the result of the action.
In addition, the present invention also provides a kind of identification of abnormal blink movement and alarm set, described device includes only mutually Vertical following equipment: wearable terminal equipment, cloud signal processing unit, processing result is counter send unit;Wherein, wearable terminal Equipment is worn on tester's body, for capturing and transmitting tested people's blink action data;Cloud signal processing unit is used People's blink action data is tested in calculating;Processing result is counter to send unit to be responsible for assigning cloud signal processing unit into instruction needs The abnormal blink the result of the action of prompt sends back wearable terminal equipment by wireless network.
The invention has the advantages that
1) device end is wearable (portable), and is worn on one side of tester, tested people will not be generated any Interference, will not cause concern, curiosity, sensitivity or the fear of tested people, gained test data is caused by test problem, no Contaminated data can be generated, the accuracy of test is greatly improved.
2) at the rear of wearable device terminal, the cloud signal processing unit being made of high performance computing system is gathered around There are unique algorithm routine and advanced processing capacity, three sport indexs can be divided into effectively analyze the exception of tested personnel and blink Eye movement is made.Moreover, during the test, for the tested personnel's individual of difference, initially setting up base-line data, it is ensured that test data Specific aim, greatly improve test accuracy.
3) according to the calculated result of cloud signal processing unit, unit is sent to feed back to tester in the form of audio counter Member, can allow tester to grasp the phychology and emotional state of tested personnel in real time, and subtest smoothly completes.
Detailed description of the invention
The exemplary embodiment that the present invention will be described in more detail by referring to accompanying drawing, the above and other aspect of the invention and Advantage will become more easily clear, in the accompanying drawings:
Fig. 1 is that a kind of identification of abnormal blink movement and the principle of alarm set of the invention are intended to;
Fig. 2 is handset structure schematic diagram used in the present invention;
Fig. 3 is Glasses structure schematic diagram of the invention;
Fig. 4 is the method flow diagram of the blink starting of basis of the present invention;
Fig. 5 is the method flow diagram of the number of winks of basis of the present invention;
Fig. 6 is the method flow diagram of the blink speed of basis of the present invention.
Specific embodiment
Hereinafter, now with reference to attached drawing, the present invention is more fully described, and various embodiments are shown in the attached drawings.So And the present invention can be implemented in many different forms, and should not be construed as limited to embodiment set forth herein.Phase Instead, it theses embodiments are provided so that the disclosure will be thorough and complete, and fully conveys the scope of the present invention to ability Field technique personnel.
Hereinafter, the exemplary embodiment that the present invention will be described in more detail with reference to the accompanying drawings.
The present invention is the wearable device for having " Expression Recognition and prompting of abnormal blink movement " function.
As shown in Figure 1, the present invention is made of three parts: wearable terminal equipment, cloud signal processing unit, processing knot Fruit is counter to send unit.Wherein, wearable terminal equipment is worn on tester's body, dynamic for capturing and transmitting tested people's blink Make data;Cloud signal processing unit is for calculating tested people's blink action data;Processing result is counter to send unit to be responsible for cloud End signal processing unit assigns the abnormal blink the result of the action that instruction needs to prompt and sends back wearable terminal by wireless network Equipment.
Wearable terminal equipment is worn on tester head, for capturing the blink action data of tested people.At this In the specific embodiment of invention, it can use as shown in Figure 2 but be not limited to mobile phone.The mobile phone is furnished with high-definition camera (1), leads to Believe module (2) and screen (3);After video data capture arrives, communication module (2) is transferred to cloud by wireless signal (Wi-Fi) End signal processing unit, mobile phone receive the anti-alarm signal for sending unit to issue by wireless receiver, are shielding in the form of images Tester's expression result is reminded on curtain (3).It is furnished with high-definition camera (1) among mobile phone, has automatic tracing and focus function, Always the eye motion of tested people is captured.Due to being combined with the active movement of wearer, the direction of tracking and range compared with Traditional blink movement instrument (not movable) is more accurate.
After video data capture arrives, communication module (2) is transferred to cloud signal processing list by wireless signal (Wi-Fi) Member.
The blink action data of tested people is carried out three ranks by reception of wireless signals by cloud signal processing unit The processing of section.
First stage, the blink for calculating tested people act base-line data.
The acquisition of base-line data needs to cooperate the question and answer of baseline topic.According to standard testing process, tester can be first It puts question to and is tested people's basket, in the question answering process of this group of problem, cloud signal processing unit is dynamic to the blink of tested people It is calculated as index, obtains blink movement base-line data.
Blink index, can be divided into three sub- indexs, be respectively:
1) the blink number of starts, the number of starts take during baseline test topic in the unit time (every 20 seconds) in the unit time The upper limit value of starting is baseline value.
2) times of exercise (it is primary that one, which opens one, which closes) blinked every time blinks number and takes times of exercise in blink every time [minimum, at most] interval value is baseline value.
3) movement velocity (it is primary that one, which opens one, which closes) blinked every time, as unit of millisecond, movement velocity takes mean value.
During baseline Questions, the vision signal that wearable terminal equipment is passed back is calculated, by above three data It counts and stores, the baseline value blinked extremely as comparison.
Second stage captures the blink action data in test problem question and answer stage.
The acquisition of practical blink action data, needs to cooperate special test topic question and answer.According to standard testing process, survey Examination personnel can put question to tested one group of actual test problem of people, the question answering process of this group of problem after baseline test inscribes completion In, cloud signal processing unit calculates the blink movement index of tested people, obtains practical blink action data.
Blink index, is divided into the unit time number of starts of blinking, (it is one that one, which opens one, closes to the times of exercise blinked every time It is secondary), and the movement velocity blinked every time (it is primary that one, which opens one, which closes).During actual test Questions, in real time may be used Eye movement data is compared with stored base-line data in the vision signal passed back of wearing terminal device, be transferred to the phase III into Row calculates and analysis.
Phase III compares baseline and carries out opposite operation, and filtering obtains abnormal blink the result of the action.
As shown in figure 4, if blink index the number of starts more than 1.2 times of baseline value, as shown in Figure 5 or blink movement Number is more than 1.5 times of baseline value, and perhaps the movement velocity of blink is more than 1.1 times of baseline value or above-mentioned three Xiang Yi as shown in Figure 6 Normal comparison value arbitrarily occurs 2 simultaneously, or all occurs, and all forms abnormal blink as a result, processing unit will send list by counter Member proposes sound warning to wearer;
If there is abnormal hint instructions of blinking, processing unit will send unit to propose sound warning to wearer by counter, Caution sound be " buzzer, it is noted that, blink is abnormal, and tonicity thinking Load lifting ratio is n% ", wherein n value is above-mentioned exception One in comparison value of blinking, e.g., times of exercise of blinking is more than 1.5 times of baseline value, then n=(1.5-1.0) %=50%.
As shown in figure 3, the wearable device can also be that glasses, the glasses are monolithic or biplate, the glasses are matched There are earphone (4) and signal transmission unit, the signal transmission unit has screen (5), can carry out visual information prompt.Glasses The anti-alarm signal for sending unit to issue is received by wireless receiver, tester's expression knot is reminded in the form of sound or image Fruit.Tester achievees the effect that detect a lie to judge the true heart activity for being tested personnel according to result.
The above description is only an embodiment of the present invention, is not intended to restrict the invention.The present invention can have various conjunctions Suitable change and variation.Any modification, equivalent substitution, improvement and etc. done within the spirit and principles of the present invention, should all It is included within protection scope of the present invention.

Claims (8)

1. identification and the based reminding method of a kind of exception blink movement,
The device that the method uses includes: wearable terminal equipment, cloud signal processing unit, processing result is counter send unit; Wherein, wearable terminal equipment is worn on tester's body, for capturing and transmitting tested people's blink action data;Cloud Signal processing unit is for calculating tested people's blink action data;Processing result is counter to send unit to be responsible for cloud signal processing list Member assigns the abnormal blink the result of the action that instruction needs to prompt and sends back wearable terminal equipment by wireless network;
The blink action data of tested people is carried out three phases by reception of wireless signals by cloud signal processing unit Processing:
First stage, the blink for calculating tested people act base-line data;
Second stage captures the blink action data in test problem question and answer stage;
The blink action data of second stage is compared the blink movement base-line data of first stage and carried out by the phase III Opposite operation, filtering obtain abnormal blink the result of the action, it is characterised in that: the phase III, the specific method is as follows:
If blink index the number of starts more than 1.2 times of baseline value, or blink times of exercise more than 1.5 times of baseline value, or The movement velocity of person's blink is more than that 1.1 times of baseline value or above-mentioned three abnormal comparison values arbitrarily occur 2 simultaneously, Huo Zhequan Portion occurs, and all forms abnormal blink as a result, processing unit will send unit to propose sound warning to wearer by counter;
If there is abnormal hint instructions of blinking, processing unit will send unit to propose sound warning, warning to wearer by counter Sound be " buzzer, it is noted that, blink is abnormal, and tonicity thinking Load lifting ratio is n% ", wherein n value is above-mentioned abnormal blink One in comparison value.
2. identification and the based reminding method of a kind of abnormal blink movement as described in claim 1, it is characterised in that:
In the first stage, the acquisition of base-line data needs to cooperate the question and answer of baseline topic;According to standard testing process, Tester puts question to first is tested people's basket, and in the question answering process of this group of problem, cloud signal processing unit is to tested The blink movement index of examination people calculates, and obtains blink movement base-line data;
Blink index, is divided into three sub- indexs, is respectively:
1) the blink number of starts in the unit time, the number of starts take the upper limit value started in the unit time during baseline test topic For baseline value;
2) times of exercise blinked every time, blinking number to take [minimum, at most] interval value of times of exercise in blink every time is base Line value;
3) movement velocity blinked every time, as unit of millisecond, movement velocity takes mean value;
During baseline Questions, the vision signal that wearable terminal equipment is passed back is calculated, by the sub- index of above three Data statistics goes out and stores, the baseline value blinked extremely as comparison.
3. identification and the based reminding method of a kind of abnormal blink movement as claimed in claim 1 or 2, it is characterised in that:
In the second stage, the acquisition of practical action data of blinking needs to cooperate special test topic question and answer;According to mark Quasi- testing process, tester can put question to tested one group of actual test problem of people after baseline test inscribes completion, this group is asked In the question answering process of topic, cloud signal processing unit calculates the blink movement index of tested people, obtains practical blink Action data;
Blink index, is divided into the unit time number of starts of blinking, the times of exercise blinked every time, and the movement blinked every time Speed;During actual test Questions, blink movement number in the vision signal of in real time passing wearable terminal equipment back It is compared according to stored base-line data, being transferred to the phase III is calculated and analyzed.
4. identification and the based reminding method of a kind of abnormal blink movement as claimed in claim 3, it is characterised in that:
It further include mobile phone, the wearable terminal equipment includes glasses and earphone, and the mobile phone is equipped with high-definition camera (1) and logical Believe module (2) and display screen (3).
5. identification and the based reminding method of a kind of abnormal blink movement as claimed in claim 4, it is characterised in that:
The glasses are monolithic or biplate, and the glasses are furnished with signal transmission unit, and the signal transmission unit has screen, can To carry out visual information prompt.
6. a kind of identification of exception blink movement and the device reminded,
Described device includes mutual independent following equipment: wearable terminal equipment, cloud signal processing unit, processing result are anti- Send unit;Wherein, wearable terminal equipment is worn on tester's body, for capturing and transmitting tested people's blink movement number According to;Cloud signal processing unit is for calculating tested people's blink action data;Processing result is counter to send unit to be responsible for believing in cloud Number processing unit assigns the abnormal blink the result of the action that instruction needs to prompt and sends back wearable terminal equipment by wireless network, It is characterized by: the wearable terminal equipment includes glasses and earphone, the glasses are monolithic or biplate, and the glasses are furnished with Signal transmission unit, the signal transmission unit have screen, can carry out visual information prompt.
7. identification and the alarm set of a kind of abnormal blink movement as claimed in claim 6, it is characterised in that:
It further include mobile phone, the mobile phone is equipped with high-definition camera (1) and communication module (2) and display screen (3).
8. identification and the alarm set of a kind of abnormal blink movement as claimed in claim 7, it is characterised in that:
The wearable terminal equipment uses mobile phone, and the mobile phone is furnished with high-definition camera (1), communication module (2) and screen (3);After video data capture arrives, communication module (2) gives cloud signal processing unit by wireless signal transmission, and mobile phone passes through Wireless receiver receives the anti-alarm signal for sending unit to issue, and reminds tester's expression on screen (3) in the form of images As a result.
CN201510213887.7A 2015-04-29 2015-04-29 It is a kind of exception blink movement identification and based reminding method and device Active CN104809439B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510213887.7A CN104809439B (en) 2015-04-29 2015-04-29 It is a kind of exception blink movement identification and based reminding method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510213887.7A CN104809439B (en) 2015-04-29 2015-04-29 It is a kind of exception blink movement identification and based reminding method and device

Publications (2)

Publication Number Publication Date
CN104809439A CN104809439A (en) 2015-07-29
CN104809439B true CN104809439B (en) 2019-03-05

Family

ID=53694250

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510213887.7A Active CN104809439B (en) 2015-04-29 2015-04-29 It is a kind of exception blink movement identification and based reminding method and device

Country Status (1)

Country Link
CN (1) CN104809439B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105913046A (en) * 2016-05-06 2016-08-31 姜振宇 Micro-expression identification device and method
CN106302637A (en) * 2016-07-28 2017-01-04 宁圣金融信息服务(上海)有限公司 Action command cloud operational approach, system and device

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN201200409Y (en) * 2008-06-12 2009-03-04 罗强 Lie detecting system with function for detecting visual stimulus
CN202060785U (en) * 2011-03-31 2011-12-07 上海天岸电子科技有限公司 Human eye pupil lie detector
CN104142583A (en) * 2014-07-18 2014-11-12 广州市香港科大霍英东研究院 Intelligent glasses with blinking detection function and implementation method thereof
CN204990333U (en) * 2015-04-29 2016-01-20 姜振宇 Discernment and reminding device of unusual action nictation

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6316023B2 (en) * 2013-05-17 2018-04-25 キヤノン株式会社 Camera system and camera control device

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN201200409Y (en) * 2008-06-12 2009-03-04 罗强 Lie detecting system with function for detecting visual stimulus
CN202060785U (en) * 2011-03-31 2011-12-07 上海天岸电子科技有限公司 Human eye pupil lie detector
CN104142583A (en) * 2014-07-18 2014-11-12 广州市香港科大霍英东研究院 Intelligent glasses with blinking detection function and implementation method thereof
CN204990333U (en) * 2015-04-29 2016-01-20 姜振宇 Discernment and reminding device of unusual action nictation

Also Published As

Publication number Publication date
CN104809439A (en) 2015-07-29

Similar Documents

Publication Publication Date Title
CN104820495B (en) A kind of micro- Expression Recognition of exception and based reminding method and device
US11032457B2 (en) Bio-sensing and eye-tracking system
CN105183170B (en) Wear-type wearable device and its information processing method, device
CN105006105B (en) Eye state identification device and eye state identification method based on infrared detection
CN104809440B (en) It is a kind of exception sight park identification and based reminding method and device
CN109431452B (en) Unmanned eye health screening instrument
CN104142583A (en) Intelligent glasses with blinking detection function and implementation method thereof
CN105913046A (en) Micro-expression identification device and method
CN105335727A (en) Identity identification system and method based on image and somatosensory analysis
CN109445578A (en) A kind of cognitive ability assessment system and method
Gupta et al. Blink as you sync: Uncovering eye and nod synchrony in conversation using wearable sensing
CN104809439B (en) It is a kind of exception blink movement identification and based reminding method and device
CN104808776A (en) Device and method for detecting continuous attaching of head-wearing intelligent device on human body
CN108414008A (en) A kind of city environmental quality monitoring system
Bœkgaard et al. In the twinkling of an eye: Synchronization of EEG and eye tracking based on blink signatures
CN109816951A (en) A kind of anti-cheat monitoring system in examination hall
CN104809371A (en) Device and method for determining validity of authentication information of head-wearing intelligent device
CN104834904B (en) It is a kind of exception Rotation of eyeball identification and based reminding method and device
CN204790850U (en) Unusual little expression discernment and reminding device
CN109199397A (en) A kind of more people's motion monitoring methods
CN204759445U (en) Unusual eyeball pivoted discernment and reminding device
CN208212008U (en) From survey formula vision inspection system
JP2017049781A (en) Glasses-type wearable device, control method thereof, and information management server
CN204990333U (en) Discernment and reminding device of unusual action nictation
CN116389691A (en) Intelligent safety wearing device based on 5G transmission

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
EXSB Decision made by sipo to initiate substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant