CN104809439A - Abnormal nictation recognizing and reminding method and device - Google Patents
Abnormal nictation recognizing and reminding method and device Download PDFInfo
- Publication number
- CN104809439A CN104809439A CN201510213887.7A CN201510213887A CN104809439A CN 104809439 A CN104809439 A CN 104809439A CN 201510213887 A CN201510213887 A CN 201510213887A CN 104809439 A CN104809439 A CN 104809439A
- Authority
- CN
- China
- Prior art keywords
- nictation
- action
- abnormal
- processing unit
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/174—Facial expression recognition
- G06V40/176—Dynamic expression
Abstract
The invention relates to an abnormal nictation recognizing and reminding method and device. The device applied to the method includes wearable terminal equipment, a cloud signal processing unit and a processing result reverse feeding unit. The wearable terminal equipment is wore on the body of a testing staff and is used for capturing and transmitting the nictation data of a person to be tested; the cloud signal processing unit is used for calculating the nictation data of the person to be tested; the processing result reverse feeding unit is used for feeding an abnormal nictation result, for reminding according to the command transmitted by the cloud signal processing unit, to the wearable terminal equipment through a wireless network; the cloud signal processing unit processes the nictation data of the person to be tested in three steps through wireless signal receiving; in the first step, the nictation baseline data of the tested person are calculated; in the second step, the nictation data in a testing question answer step are captured; in the third step, the nictation data of the second step are compared with the nictation baseline data of the first step, relevant calculation is performed, and the abnormal nictation result can be acquired by filtering.
Description
Technical field
The present invention relates to a kind of identification of abnormal action nictation and based reminding method and device, belong to intelligent Expression Recognition field.
Background technology
Micro-expression is only 1/25 second to 1/5 second expressing one's feelings very fast at a kind of duration, have expressed people and attempt to constrain and the real emotion hidden.Micro-expression be the mankind attempt constrain or hiding real feelings time reveal very of short duration, can not from the facial expression of main control.As the effective clue identifying lie, micro-expression can be applicable to the fields such as safe, judicial, clinical.
Existing wearable (portable) Expression Recognition equipment is divided into two classes, one class is worn on the tested person, one class is worn on it tester, also has plenty of fixing camera on probation and takes for tested personnel, non-portable but function is similar to Equations of The Second Kind.
The first kind is worn on action recognition equipment nictation on the tested person, and the shortcoming had is the action of naturally blinking of interference tested personnel.The ideal state of motion test nictation is to the interference of tested personnel without any visual aspects, otherwise the action nictation producing cause of tested personnel cannot be differentiated, be difficult to carry out causalnexus with the change of its psychological condition, its action nictation very possible is by the wearing of equipment, causes, so the data obtained is contaminated data the reason such as curiosity, concern of equipment.
The equipment that Equations of The Second Kind is worn by tester side or used, take beyond tested health and identify the expression of tested personnel and action nictation, the shortcoming that this kind equipment exists clearly.No matter be that expression catches and identification software, or blink motion capture and analytical equipment, all lack two vital factors, one is have no idea to set up and associating between carried test problem, and two is the algorithmic procedures not setting up baseline.So the recognition reaction that this kind equipment only can play " performance expression ", and can not catch and analyze the slight expression and abnormal action of blinking that represent the true phychology of tested personnel.Making up these shortcomings, need to solve two problems, is first in method of testing and the corresponding technology of test problem, is secondly the algorithm setting up tested personnel individual base-line data.
Summary of the invention
For reaching the object according to micro-Expression analysis tested personnel psychological activity, the present invention relates to a kind of identification and based reminding method of abnormal action nictation, the device that described method uses comprises: wearable terminal equipment, high in the clouds signal processing unit, result is counter send unit; Wherein, wearable terminal equipment is worn on tester's health, to blink action data for catching and transmitting tested people; High in the clouds signal processing unit to be blinked action data for calculating tested people; Anti-exception the result of the action nictation sending unit to be responsible for high in the clouds signal processing unit to assign the prompting of instruction needs of result sends it back wearable terminal equipment by wireless network.
High in the clouds signal processing unit, by reception of wireless signals, carries out the process of three phases by action data nictation of tested people:
First stage, calculate the action nictation base-line data of tested people;
Subordinate phase, catches action data nictation in test problem question and answer stage;
Phase III, the action nictation base-line data of described action data comparison first stage nictation of subordinate phase is carried out relative computing, filter and draw abnormal the result of the action of blinking.
In addition, the present invention also provides a kind of identification and alarm set of abnormal action nictation, and described device comprises mutually independently following equipment: wearable terminal equipment, high in the clouds signal processing unit, result is counter send unit; Wherein, wearable terminal equipment is worn on tester's health, to blink action data for catching and transmitting tested people; High in the clouds signal processing unit to be blinked action data for calculating tested people; Anti-exception the result of the action nictation sending unit to be responsible for high in the clouds signal processing unit to assign the prompting of instruction needs of result sends it back wearable terminal equipment by wireless network.
Advantage of the present invention comprises:
1) device end wearable (portable), and be worn on tester one side, any interference can not be produced for tested people, the concern of tested people, curiosity, sensitivity or frightened can not be caused, gained test data is all caused by test problem, contaminated data can not be produced, significantly improve the accuracy of test.
2) at the rear of wearable device terminal, the high in the clouds signal processing unit be made up of high performance computing system, has unique algorithm routine and advanced processing power, and three sport indexs can be divided into effectively to analyze exception action nictation of tested personnel.And in test process, for difference, tested personnel are individual, first set up base-line data, guarantee the specific aim of test data, significantly improve test accuracy.
3) according to the result of calculation of high in the clouds signal processing unit, feed back to tester by the anti-unit that send with the form of audio frequency, tester can be allowed in real time to grasp phychology and the emotional state of tested personnel, completing smoothly of subtest.
Accompanying drawing explanation
Describe exemplary embodiment of the present invention in more detail by referring to accompanying drawing, above and other aspect of the present invention and advantage will become and more be readily clear of, in the accompanying drawings:
Fig. 1 is that a kind of abnormal identification of action nictation of the present invention and the principle of alarm set are intended to;
Fig. 2 is handset structure schematic diagram used in the present invention;
Fig. 3 is Glasses structure schematic diagram of the present invention;
Fig. 4 be the present invention according to the method flow diagram that starts nictation;
Fig. 5 be the present invention according to the method flow diagram of number of winks;
Fig. 6 be the present invention according to the method flow diagram of blink speed.
Embodiment
Hereinafter, more fully the present invention is described now with reference to accompanying drawing, various embodiment shown in the drawings.But the present invention can implement in many different forms, and should not be interpreted as being confined to embodiment set forth herein.On the contrary, provide these embodiments to make the disclosure will be thoroughly with completely, and scope of the present invention is conveyed to those skilled in the art fully.
Hereinafter, with reference to the accompanying drawings exemplary embodiment of the present invention is described in more detail.
The present invention is the wearable device possessing " Expression Recognition of abnormal action nictation and prompting " function.
As shown in Figure 1, the present invention is made up of three parts: wearable terminal equipment, high in the clouds signal processing unit, result is counter send unit.Wherein, wearable terminal equipment is worn on tester's health, to blink action data for catching and transmitting tested people; High in the clouds signal processing unit to be blinked action data for calculating tested people; Anti-exception the result of the action nictation sending unit to be responsible for high in the clouds signal processing unit to assign the prompting of instruction needs of result sends it back wearable terminal equipment by wireless network.
Wearable terminal equipment, is worn on tester's head, for catching action data nictation of tested people.In a particular embodiment of the present invention, can adopt as shown in Figure 2 but be not limited to mobile phone.Described mobile phone is furnished with high-definition camera (1), communication module (2) and screen (3); Video data capture is to afterwards, communication module (2) is transferred to high in the clouds signal processing unit by wireless signal (Wi-Fi), mobile phone receives the anti-alarm signal sending unit to send by wireless receiver, reminds tester to express one's feelings result screen (3) is upper in the form of images.Be furnished with high-definition camera (1) in the middle of mobile phone, possess automatic tracing and focus function, catch the eye motion of tested people all the time.Owing to being combined with the active movement of wearer, its follow the trail of direction and scope than tradition nictation action instrument (not movable) more accurate.
Video data capture is to afterwards, and communication module (2) is transferred to high in the clouds signal processing unit by wireless signal (Wi-Fi).
High in the clouds signal processing unit, by reception of wireless signals, carries out the process of three phases by action data nictation of tested people.
First stage, calculate the action nictation base-line data of tested people.
The acquisition of base-line data, needs the question and answer coordinating baseline exercise question.According to standard testing flow process, first tester can put question to tested people's basket, and in the question answering process of this group problem, the nictation action index of high in the clouds signal processing unit to tested people calculates, and obtains action nictation base-line data.
Nictation, index, can be divided into three sub-indexs, respectively:
1) the unit interval interior number of starts of blinking, the higher limit that during the number of starts gets baseline test exercise question, in the unit interval, (every 20 seconds) start is baseline value.
2) times of exercise (opens closes as once) of each nictation, the number of times that blinks get times of exercise in each nictation [minimum, at most] interval value is baseline value.
3) movement velocity (opens closes as once) of each nictation, in units of millisecond, movement velocity gets average.
In baseline Questions process, calculate the vision signal of wearable terminal device back, above-mentioned three data statisticss are gone out and store, as the baseline value of comparison abnormal nictation.
Subordinate phase, catches action data nictation in test problem question and answer stage.
The acquisition of actual action data of blinking, needs to coordinate special test exercise question question and answer.According to standard testing flow process, tester after baseline test question completes, can put question to tested people one group of actual test problem, in the question answering process of this group problem, the nictation action index of high in the clouds signal processing unit to tested people calculates, and obtains action data actual nictation.
Nictation, index, to be divided in the unit interval number of starts nictation, the times of exercise of each nictation (opens closes as once), and the movement velocity of each nictation (opens closes as once).In actual test problem question answering process, eye movement data in the vision signal of wearable terminal device back and the base-line data to have stored are compared in real time, proceeding to the phase III carries out computation and analysis.
Phase III, comparison baseline also carries out relative computing, filters and draws abnormal the result of the action of blinking.
As shown in Figure 4, if nictation, the number of starts of index exceeded baseline value 1.2 times, as shown in Figure 5 or nictation times of exercise exceed baseline value 1.5 times, as shown in Figure 6 or nictation movement velocity exceed baseline value 1.1 times, or above-mentioned three abnormal comparison value occur 2 arbitrarily simultaneously, or all occur, all form abnormal result of blinking, processing unit will propose sound warning by the anti-unit that send to wearer;
If there is abnormal hint instructions of blinking, processing unit will propose sound warning by the anti-unit that send to wearer, caution sound is " buzzer, note that nictation is abnormal; tonicity thinking Load lifting is than being n% ", wherein, n value is above-mentioned abnormal of blinking in comparison value, as, nictation, times of exercise exceeded baseline value 1.5 times, then n=(1.5-1.0) %=50%.
As shown in Figure 3, described wearable device can also be glasses, and described glasses are monolithic or biplate, and described glasses are furnished with earphone (4) and signal transmission unit, described signal transmission unit has screen (5), can carry out visual information prompting.Glasses receive the anti-alarm signal sending unit to send by wireless receiver, remind tester to express one's feelings result with the form of sound or image.Tester thus judge the true heart activity of tested personnel according to result, reaches the effect of detecting a lie.
The foregoing is only embodiments of the invention, be not limited to the present invention.The present invention can have various suitable change and change.All any amendments done within the spirit and principles in the present invention, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (10)
1. the identification of abnormal action nictation and a based reminding method, is characterized in that:
The device that described method uses comprises: wearable terminal equipment, high in the clouds signal processing unit, result is counter send unit; Wherein, wearable terminal equipment is worn on tester's health, to blink action data for catching and transmitting tested people; High in the clouds signal processing unit to be blinked action data for calculating tested people; Anti-exception the result of the action nictation sending unit to be responsible for high in the clouds signal processing unit to assign the prompting of instruction needs of result sends it back wearable terminal equipment by wireless network;
High in the clouds signal processing unit, by reception of wireless signals, carries out the process of three phases by action data nictation of tested people:
First stage, calculate the action nictation base-line data of tested people;
Subordinate phase, catches action data nictation in test problem question and answer stage;
Phase III, the action nictation base-line data of described action data comparison first stage nictation of subordinate phase is carried out relative computing, filter and draw abnormal the result of the action of blinking.
2. the identification of a kind of abnormal action nictation as claimed in claim 1 and based reminding method, is characterized in that:
In the described first stage, the acquisition of base-line data, needs the question and answer coordinating baseline exercise question; According to standard testing flow process, first tester puts question to tested people's basket, and in the question answering process of this group problem, the nictation action index of high in the clouds signal processing unit to tested people calculates, and obtains action nictation base-line data;
Nictation, index, was divided into three sub-indexs, respectively:
1) the unit interval interior number of starts of blinking, the higher limit that during the number of starts gets baseline test exercise question, in the unit interval, (every 20 seconds) start is baseline value;
2) times of exercise (opens closes as once) of each nictation, the number of times that blinks get times of exercise in each nictation [minimum, at most] interval value is baseline value;
3) movement velocity (opens closes as once) of each nictation, in units of millisecond, movement velocity gets average;
In baseline Questions process, calculate the vision signal of wearable terminal device back, the data statistics of above-mentioned three sub-indexs is gone out and stores, as the baseline value of comparison abnormal nictation.
3. the identification of a kind of abnormal action nictation as claimed in claim 1 or 2 and based reminding method, is characterized in that:
In described subordinate phase, the acquisition of actual action data of blinking, needs to coordinate special test exercise question question and answer; According to standard testing flow process, tester after baseline test question completes, can put question to tested people one group of actual test problem, in the question answering process of this group problem, the nictation action index of high in the clouds signal processing unit to tested people calculates, and obtains action data actual nictation;
Nictation, index, to be divided in the unit interval number of starts nictation, the times of exercise of each nictation (opens closes as once), and the movement velocity of each nictation (opens closes as once); In actual test problem question answering process, compared by action data of blinking in real time in the vision signal of wearable terminal device back with the base-line data to have stored, proceeding to the phase III carries out computation and analysis.
4. the identification of a kind of abnormal action nictation as claimed in claim 3 and based reminding method, is characterized in that:
The concrete grammar of described phase III is as follows:
If nictation, the number of starts of index exceeded baseline value 1.2 times, or the times of exercise of nictation exceedes baseline value 1.5 times, or the movement velocity of nictation exceedes baseline value 1.1 times, or above-mentioned three abnormal comparison value occur 2 arbitrarily simultaneously, or all occur, all form abnormal result of blinking, processing unit will propose sound warning by the anti-unit that send to wearer;
If there is abnormal hint instructions of blinking, processing unit will propose sound warning by the anti-unit that send to wearer, and caution sound is " buzzer; note that nictation is abnormal, tonicity thinking Load lifting is than being n% ", wherein, n value is above-mentioned abnormal of blinking in comparison value.
5. the identification of a kind of abnormal action nictation as claimed in claim 4 and based reminding method, is characterized in that:
Described wearable terminal equipment comprises glasses and earphone, and described mobile phone is furnished with high-definition camera (1) and communication module (2) and display screen (3).
6. the identification of a kind of abnormal action nictation as described in claim 4 or 5 and based reminding method, is characterized in that:
Described glasses are monolithic or biplate, and described glasses are furnished with signal transmission unit, and described signal transmission unit has screen, can carry out visual information prompting.
7. the abnormal identification of action nictation and a device for prompting, is characterized in that:
Described device comprises mutually independently following equipment: wearable terminal equipment, high in the clouds signal processing unit, result is counter send unit; Wherein, wearable terminal equipment is worn on tester's health, to blink action data for catching and transmitting tested people; High in the clouds signal processing unit to be blinked action data for calculating tested people; Anti-exception the result of the action nictation sending unit to be responsible for high in the clouds signal processing unit to assign the prompting of instruction needs of result sends it back wearable terminal equipment by wireless network.
8. the identification of a kind of abnormal action nictation as claimed in claim 7 and alarm set, is characterized in that:
Described wearable terminal equipment comprises glasses and earphone, and described mobile phone is furnished with high-definition camera (1) and communication module (2) and display screen (3).
9. the identification of a kind of abnormal action nictation as claimed in claim 8 and alarm set, is characterized in that:
Described glasses are monolithic or biplate, and described glasses are furnished with signal transmission unit, and described signal transmission unit has screen, can carry out visual information prompting.
10. a kind of abnormal sight line as claimed in claim 8 identification of parking and alarm set, is characterized in that:
Described wearable terminal equipment adopts mobile phone, and described mobile phone is furnished with high-definition camera (1), communication module (2) and screen (3); Video data capture is to afterwards, communication module (2) is transferred to high in the clouds signal processing unit by wireless signal (Wi-Fi), mobile phone receives the anti-alarm signal sending unit to send by wireless receiver, reminds tester to express one's feelings result screen (3) is upper in the form of images.
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 true CN104809439A (en) | 2015-07-29 |
CN104809439B 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) |
Cited By (2)
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 (5)
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 |
US20140341427A1 (en) * | 2013-05-17 | 2014-11-20 | Canon Kabushiki Kaisha | Surveillance camera system and surveillance camera control apparatus |
CN204990333U (en) * | 2015-04-29 | 2016-01-20 | 姜振宇 | Discernment and reminding device of unusual action nictation |
-
2015
- 2015-04-29 CN CN201510213887.7A patent/CN104809439B/en active Active
Patent Citations (5)
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 |
US20140341427A1 (en) * | 2013-05-17 | 2014-11-20 | Canon Kabushiki Kaisha | Surveillance camera system and surveillance camera control apparatus |
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 |
Cited By (2)
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 |
Also Published As
Publication number | Publication date |
---|---|
CN104809439B (en) | 2019-03-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104820495B (en) | A kind of micro- Expression Recognition of exception and based reminding method and device | |
WO2020034902A1 (en) | Smart desk having status monitoring function, monitoring system server, and monitoring method | |
US11032457B2 (en) | Bio-sensing and eye-tracking system | |
CN104142583A (en) | Intelligent glasses with blinking detection function and implementation method thereof | |
CN109431452B (en) | Unmanned eye health screening instrument | |
CN110013261B (en) | Emotion monitoring method and device, electronic equipment and storage medium | |
CN105468147A (en) | Intelligent device, system and method for preventing myopia | |
CN110013249B (en) | Portable adjustable head-mounted epilepsy monitor | |
CN205121478U (en) | Prevent near -sighted smart machine and system | |
CN105335727A (en) | Identity identification system and method based on image and somatosensory analysis | |
CN107137096A (en) | A kind of multi-modal physiology and behavioral data merge acquisition system | |
KR20150107268A (en) | Mirror device, wearable device and exercise management system | |
CN104809440A (en) | Abnormal sight stop recognizing and reminding method and device | |
CN105183170A (en) | Head-wearing-type wearable equipment and information processing method and device thereof | |
CN107480716A (en) | A kind of combination EOG and video pan signal recognition method and system | |
CN104473648A (en) | Physiological parameter monitoring-combined human body tumble warning and detecting method | |
CN109480816A (en) | Rhythm of the heart monitoring method, device, electronic equipment and computer readable storage medium | |
CN207087880U (en) | A kind of medical nurse robot | |
AU2014234955A1 (en) | Automatic detection of task transition | |
CN109276243A (en) | Brain electricity psychological test method and terminal device | |
CN104809439A (en) | Abnormal nictation recognizing and reminding method and device | |
CN204790850U (en) | Unusual little expression discernment and reminding device | |
CN204990333U (en) | Discernment and reminding device of unusual action nictation | |
CN204759445U (en) | Unusual eyeball pivoted discernment and reminding device | |
CN106096544A (en) | Contactless nictation and heart rate combined detection system and method based on second-order blind identification |
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 |