CN105335691A - Smiling face identification and encouragement system - Google Patents
Smiling face identification and encouragement system Download PDFInfo
- Publication number
- CN105335691A CN105335691A CN201410397483.3A CN201410397483A CN105335691A CN 105335691 A CN105335691 A CN 105335691A CN 201410397483 A CN201410397483 A CN 201410397483A CN 105335691 A CN105335691 A CN 105335691A
- Authority
- CN
- China
- Prior art keywords
- expression
- face
- image
- facial
- anxiety
- 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
Links
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a smiling face identification and encouragement system, and belongs to the technical field of image processing and artificial intelligence. The smiling face identification and encouragement system is implemented through the following steps: collecting basic expression samples; automatically starting videos at startup; collecting the expressions in real time; pre-processing the expression images; identifying the expression images; carrying out comprehensive statistics, analysis and judgment; summing up the phased expressions; and encouraging the staff to relax. According to the technical key point of the invention, a plurality of expression characteristics represented through vectors are matched with corresponding key characteristics in several pre-shot user typical expression samples to compare the similarity; the difference and geometric shape change between the Euclidean distance at a captured expression key characteristic and the Euclidean distance at a preset typical expression characteristic are judged; and after normalization, a statistic shape analysis method is used for judging whether the expression in the phase is anxiety or happiness according to the expression distribution probability of the staff in a certain time period. The system has the benefit of encouraging the staff to feel anxious less and smile more so as to improve the working efficiency and the living quality.
Description
Technical field
The invention belongs to image processing method and artificial intelligence field, use human face expression collection, analysis, recognition technology, give to remind and help to the expression of anxiety, the expression of smile or calmness is given encouragement, relates to the technology such as man face image acquiring and detection, facial image pre-service, facial image feature extraction, facial image matching and recognition, integrating shape statistical study, artificial intelligence and network interdynamic.
Background technology
Work, the life stress of present worker are large, normal bear with a worried frown, nervous anxiety, the passive expression such as unhappy unconsciously, long-time this expression can cause bad mood, this negative energy health risk, affect the quality of working life, need by external help, remind in time, remove anxiety, interrupt the vicious cycle of bad mood.
Current face recognition technology is mainly used in safety check, identification and Expression analysis, the Expression Recognition of face is used in virtual emotional interaction less with analysis, the image of face is detected with computer camera collection, a series of correlation technique process of face, analysis and judgement are carried out to the face detected, and then provides reminding employees to loosen and give affectional provisions.
Summary of the invention
The object of the invention is: be keep even-tempered and good-humoured in order to encourage when the many smiles of employee or work, abandon worry, the phychology upwards of keeping pleasant and good appearance.
The technical scheme that the present invention takes is: the implementation step of this system is: the collection of basic facial expression sample, start start video, expression Real-time Collection, expression detections, facial expression image pre-service, facial expression image identification, comprehensive statistics analysis judges, interim expression is summed up, encouragement employee loosens courtesy notification automatically.
Technical essential of the present invention is by the multiple expressive features by vector representation, in the sample that the user typical case taken in advance with several expresses one's feelings, corresponding key feature mates and contrasts similarity, judge the Euclidean distance at the expression key feature place captured and the Euclidean distance difference at typical expressive features place preset, the change of geometric configuration, after normalization, use Statistical Shape analytical approach, judge to express one's feelings in this stage as anxiety or happiness according to the expression distribution probability of employee in certain hour section.
Require when running first to set up employee's face archives: first gathered and several expressions of employee of filing by the camera head of computer: tranquil, glad, angry, distress, as the sample compared with the expression of Real-time Collection from now on, every day is when starting shooting, this program starts automatically, when employee work, gather once in the face of employee's facial expression image of computer every a few minutes, Image semantic classification in addition, can according to grey-tone image, face edge detection results and face and background segment result export facial contour, determine that the key feature of expressing one's feelings on the face can be represented by vector, the Feature Combination of multiple characteristic portion is got up, expressive features is exported together with facial contour, the key feature corresponding with the sample that several user typical case taken in advance expresses one's feelings contrasts, judge the Euclidean distance difference at typical expressive features place in the Euclidean distance at expression key feature place that captures and sample, the change of geometric configuration, through statistical study, judge that the expression of employee is anxiety or happiness, if employee continues have anxiety to express one's feelings in half an hour, every half an hour, computing machine just sends friendly prompting in time, please employee smile, or eject its happy expression and contrast photo with two of to express one's feelings at that time, or jump out one section of humorous joke, comprise image capture, Face detection, Image semantic classification, expression detects, Expression Recognition, statistical study and judgement, interactive prompting, the psychological tactics adopted is marketing of smiling.
The invention has the beneficial effects as follows: can improve mood when office worker works, smile with happyly bring in the work of employee, beauty and health care, the work of employee and quality of life can make moderate progress, and can also increase work efficiency, the enhancing performance of enterprises.
Accompanying drawing explanation
Fig. 1 is the implementing procedure figure that smiling face of the present invention identifies Motivational systems.
Embodiment
The present invention realizes by following technical scheme and step.
Before system uses, employee can select whether use this cover to smile in advance and identify Motivational systems.
1, the collection of basic facial expression sample:
First end user is registered, then end user's face-image is taken, take to each employee and the three kinds of basic facial expression photos that file: happiness, anxiety, calmness, the object of reference contrasted is carried out as the expression produced in later and work, after end user confirms image, system uses Euclidean distance to measure, by characteristic stored in database after carrying out all normalized operations in side to the key position representing expressive features in image.
2, start starts video automatically:
If employee's choice for use is smiled identify Motivational systems, automatically the smiling face running program as a setting during start identifies Motivational systems, that time opening computer carries or join camera, system is run dumbly on backstage, the work of user can not be affected, if user does not want to continue to use this cover system, shutdown system can be selected.
3, expression Real-time Collection:
Face with 50 ~ 100cm distance just to video camera, utilize routine work light illumination, light-source brightness and direction basically identical when gathering, the first accurate calibration in the picture of Face datection goes out position and the size of face, the computer camera of face Autofocus Technology function can be used: it judges according to the head region of people, first head is determined, then the head feature such as eyes and face is judged, by the comparison of feature database, be confirmed to be user's face, complete face to catch, then be that focus carries out auto-focusing with face, the sharpness taking photo can be promoted, contrast mould, be confirmed to be the face of the user once logged in, can arrange every shooting in a 5 minutes facial expression image.
human face expression detects
The pattern feature comprised in facial image is very abundant, and as histogram feature, color characteristic, template characteristic, architectural feature and Haar feature etc., the information that this is wherein useful picks out, and utilizes these features to realize Face datection.
First the exterior contour having face's organ of substantial connection with expression shape change is extracted, facial contour can be exported according to grey-tone image, face edge detection results and face and background segment result, then geometric description is carried out, as the key character of expression recognition to the various changes of position shape, size, luminance brightness and the relative positions such as eyes, nose, face, chin, cheek.
Face identification system accurately, provide good pictorial database technique, face recognition algorithms then processes image further, to eliminate the negative effect that distance and head pose bring, the human-face detector based on Adaboost algorithm can be used in expression testing process to detect facial image, Adaboost algorithm picks out the rectangular characteristic (Weak Classifier) that some can represent human face expression, according to the mode of Nearest Neighbor with Weighted Voting, Weak Classifier is configured to a strong classifier, the cascade filtering of will the some strong classifiers obtained be trained to be composed in series a cascade structure again, effectively improve the detection speed of sorter.
facial Expression Image pre-service
Input picture is due to the difference of image capture environment, as the quality etc. of illumination bright-dark degree and equipment performance, often have noise, the shortcomings such as contrast is inadequate, in addition, distance, focal length size etc. make again the size of face in the middle of the entire image and position uncertain, in order to ensure face size in facial image, the consistance of position and quality of human face image, before face characteristic is extracted, face righting must be carried out to image, image enhaucament, the pre-service such as image normalization and image restoration, comprise the light compensation of facial image, greyscale transformation, histogram equalization, normalization, geometry correction, filtering and sharpening etc.
Determine that the feature of the face key position of expressing one's feelings can use geometrical normalization and gray scale normalization to process image for extracting.
Geometrical normalization: head instability when same Face datection algorithm is owing to being examined, as rotation, position, distortion etc., the human face region size detected is not quite similar, in order to the integrity that follow-up face characteristic extracts, be necessary that the proper property of the size to face, length and width when face does normalized, make the face sample of detection be more suitable for carrying out feature extraction, ensure the validity of feature extraction.
Gray scale normalization: the image of different time often gray scale not in same scope, this is mainly because light unevenness causes, unified process is convenient in order to allow the facial image of different gray scale, be necessary that the gray level of regulation facial image is in some specific scopes, or light crossed how dark mistake is bright will be normalized in this gray level, i.e. light compensation, formula specific as follows:
M in formula.Desirable average and variance with VARa, usual desirable city Mo=100, VARa=10, M.Be average according to input picture actual estimated and variance with VARa, the object of gray scale normalization reduces light unevenness to face characteristic impact so that impact Expression Recognition rate below.
facial expression recognition, analysis, judgement
At image enhaucament, on a series of images process operation bases such as Iamge Segmentation, for visual signature, pixels statistics feature, facial image conversion coefficient feature, the facial image algebraic characteristic of face, carry out feature modeling, extract human face expression feature, available Knowledge based engineering characterizing method (comprising the method based on geometric properties and template matching method), or carry out graphical analysis based on the characterizing method of algebraic characteristic or statistical learning.
The expression of people when anxiety is generally: brows tighten, curved under mouth, curved now, cheek is gloomy, when people is glad, brows are unfolded, curved on mouth, curved on eye, radiant, according to the shape description of these human faces and the range performance between them, the characteristic contributing to facial expression classification can be obtained, as the Euclidean distance between unique point, curvature and angle etc., determine that the feature of expressing one's feelings on the face can be represented by vector, the Feature Combination of multiple characteristic portion is got up, export expressive features data, carry out search with the user typical case expressive features template stored in database to mate, judge the Euclidean distance difference at typical expressive features place in the Euclidean distance at expression key feature place that captures and sample, the change of geometric configuration, when similarity exceedes the threshold value of setting, export mating the result obtained, thus expression is at that time judged, each Expression analysis result is stored in database, the picture archiving caught.
Statistical Shape analytical approach can be utilized to analyze human face expression, by change expression abstract be stochastic variable, after its normalization, landmark point is adopted to set up points distribution models to facial image, Maximum Likelihood Estimation is adopted to carry out parameter estimation to the probability distribution of obtained expression space, obtain a probability distribution of expressing one's feelings in special time period, draw the Expression analysis result during this period of time.
interim expression is summed up, courtesy notification
This cover system can arrange often how often gather a user expression before use, as 5 minutes, and every how long, as added up the expression of user in this stage every half an hour, if in this stage user expression statistical analysis after be judged as anxiety, or in the expression collected sometime by analysis afterwards for special anxiety, system can preserve the image of user's anxiety that captures, arrive this half an hour or at that moment, system reads presets type of reminders, enter prompting by type, can be eject simple friendly prompting, wish that user loosens mood, to the prompting of user can be: please smile, keep good mood, the expression picture that also can be set to simultaneously to eject the user's anxiety collected and the user gathered in advance glad time expression picture, a humorous cross-talk can also be jumped out, user is allowed to smile, remind and encourage language and content of joke to be kept at lane database, according to Expression analysis result, output to user interface.Section at regular intervals, as every day deletes the user's anxiety image on the same day preserved.
This cover system is not only applicable to the employee using computer for a long time, also sale, service industry employee is applicable to, promote its with smile in the face of client or allow client can feel from phone or language sales, attendant smile, contribute to raising sales achievement, improve service quality.
In sum, the invention of native system gathers the facial expression image of people by computer camera, after image procossing, contrast the image pattern of happiness, calmness and anxiety taken in advance and carry out identifying, contrast, analyze, give the courtesy notification of smiling and emotion help to the user of expression anxiety more.
Claims (8)
1. smiling face identifies Motivational systems, it is characterized in that: the method is divided into seven steps to realize:
1) collection of basic facial expression sample;
2) start starts video automatically;
3) expression Real-time Collection;
4) human face expression detects;
5) Facial Expression Image pre-service;
6) facial expression recognition, analysis, judgement;
7) interim expression end, courtesy notification.
2. smiling face as claimed in claim 1 identifies Motivational systems, it is characterized in that: registration end user takes end user's happiness, anxiety, tranquil face-image, confirm image, Euclidean distance is used to measure, by characteristic stored in database after carrying out all normalized operations in side to the key position representing expressive features in image.
3. the smiling face as described in claim 1,2 identifies Motivational systems, it is characterized in that: if employee's choice for use is smiled identify Motivational systems, during start, will automatically allow camera that is that computer carries or that join open, and start smiling face and identify Motivational systems.
4. the smiling face as described in claim 1,2,3 identifies Motivational systems, it is characterized in that: use the computer camera having face Autofocus Technology function, complete face to catch, every shooting in a 5 minutes facial expression image, accurate calibration goes out position and the size of face in the picture.
5. the smiling face as described in claim 1,2,3,4 identifies Motivational systems, it is characterized in that: extract the pattern feature comprised in facial image, geometric description is carried out to it, as the key character of expression recognition, first the exterior contour having face's organ of substantial connection with expression shape change is extracted, facial contour can be exported according to grey-tone image, face edge detection results and face and background segment result, then use the human-face detector based on Adaboost algorithm to detect facial image, further image is processed.
6. the smiling face as described in claim 1,2,3,4,5 identifies Motivational systems, it is characterized in that: before face characteristic is extracted, image is carried out to the pre-service such as face righting, image enhaucament, image normalization and image restoration, use geometrical normalization and gray scale normalization to process to extract the feature of the face key position determining to express one's feelings to image.
7. as claim 1, 2, 3, 4, 5, smiling face described in 6 identifies Motivational systems, it is characterized in that: for the visual signature of face, pixels statistics feature, facial image conversion coefficient feature, facial image algebraic characteristic, carry out feature modeling, extract human face expression feature, can according to people anxiety and glad time the shape description of human face and the range performance between them, obtain the characteristic contributing to facial expression classification, as the Euclidean distance between unique point, curvature and angle etc., the expressive features captured and expressive features template are compared, according to similarity degree, expression is at that time judged, by the statistical study to human face expression space, obtain an expression scoring in special time period, each Expression analysis result is stored in database, file the image at every turn captured.
8. as claim 1, 2, 3, 4, 5, 6, smiling face described in 7 identifies Motivational systems, it is characterized in that: add up the expression scoring of user in this stage every half an hour, if the expression weighted scoring of user is anxiety in this stage, or in the expression collected sometime by analysis afterwards for special anxiety, system can preserve the image of user's anxiety that captures, arrive this half an hour or at that moment, system reads presets type of reminders, enter prompting by type, eject friendly prompting or ejection happiness and anxiety photo and compare or play humorous cross-talk, reminding user loosens mood, delete the facial expression image filed in a day every day.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410397483.3A CN105335691A (en) | 2014-08-14 | 2014-08-14 | Smiling face identification and encouragement system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410397483.3A CN105335691A (en) | 2014-08-14 | 2014-08-14 | Smiling face identification and encouragement system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105335691A true CN105335691A (en) | 2016-02-17 |
Family
ID=55286208
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410397483.3A Pending CN105335691A (en) | 2014-08-14 | 2014-08-14 | Smiling face identification and encouragement system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105335691A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105354527A (en) * | 2014-08-20 | 2016-02-24 | 南京普爱射线影像设备有限公司 | Negative expression recognizing and encouraging system |
| CN107613550A (en) * | 2017-09-27 | 2018-01-19 | 广东欧珀移动通信有限公司 | Solve lock control method and Related product |
| CN108564007A (en) * | 2018-03-27 | 2018-09-21 | 深圳市智能机器人研究院 | A kind of Emotion identification method and apparatus based on Expression Recognition |
| CN109215763A (en) * | 2018-10-26 | 2019-01-15 | 广州华见智能科技有限公司 | A kind of emotional health monitoring method and system based on facial image |
| CN109446880A (en) * | 2018-09-05 | 2019-03-08 | 广州维纳斯家居股份有限公司 | Intelligent subscriber participation evaluation method, device, intelligent elevated table and storage medium |
| CN109934097A (en) * | 2019-01-23 | 2019-06-25 | 深圳市中银科技有限公司 | A kind of expression and mental health management system based on artificial intelligence |
| CN110770845A (en) * | 2017-07-18 | 2020-02-07 | 梅德拉控股公司 | Method and interactive system for improving pump performance and user experience |
| CN111291623A (en) * | 2020-01-15 | 2020-06-16 | 浙江连信科技有限公司 | Heart physiological characteristic prediction method and device based on face information |
| CN113050843A (en) * | 2019-12-27 | 2021-06-29 | 深圳富泰宏精密工业有限公司 | Emotion recognition and management method, computer program, and electronic device |
| CN113657188A (en) * | 2021-07-26 | 2021-11-16 | 浙江大华技术股份有限公司 | Face age identification method, system, electronic device and storage medium |
| CN116489475A (en) * | 2019-12-31 | 2023-07-25 | 武汉星巡智能科技有限公司 | Video editing method, device, equipment and storage medium based on interesting expression |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101604382A (en) * | 2009-06-26 | 2009-12-16 | 华中师范大学 | A kind of learning fatigue recognition interference method based on human facial expression recognition |
| CN101887513A (en) * | 2009-05-12 | 2010-11-17 | 联咏科技股份有限公司 | Expression detecting device and method |
| CN103488293A (en) * | 2013-09-12 | 2014-01-01 | 北京航空航天大学 | Man-machine motion interaction system and method based on expression recognition |
| CN103679159A (en) * | 2013-12-31 | 2014-03-26 | 海信集团有限公司 | Face recognition method |
| CN103824059A (en) * | 2014-02-28 | 2014-05-28 | 东南大学 | Facial expression recognition method based on video image sequence |
-
2014
- 2014-08-14 CN CN201410397483.3A patent/CN105335691A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101887513A (en) * | 2009-05-12 | 2010-11-17 | 联咏科技股份有限公司 | Expression detecting device and method |
| CN101604382A (en) * | 2009-06-26 | 2009-12-16 | 华中师范大学 | A kind of learning fatigue recognition interference method based on human facial expression recognition |
| CN103488293A (en) * | 2013-09-12 | 2014-01-01 | 北京航空航天大学 | Man-machine motion interaction system and method based on expression recognition |
| CN103679159A (en) * | 2013-12-31 | 2014-03-26 | 海信集团有限公司 | Face recognition method |
| CN103824059A (en) * | 2014-02-28 | 2014-05-28 | 东南大学 | Facial expression recognition method based on video image sequence |
Non-Patent Citations (2)
| Title |
|---|
| 徐敏: "基于视频的实时人脸识别的研究与实践", 《万方学位论文数据库》 * |
| 曹青媚: "人脸识别技术的研究", 《信息科技》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105354527A (en) * | 2014-08-20 | 2016-02-24 | 南京普爱射线影像设备有限公司 | Negative expression recognizing and encouraging system |
| CN110770845A (en) * | 2017-07-18 | 2020-02-07 | 梅德拉控股公司 | Method and interactive system for improving pump performance and user experience |
| CN107613550A (en) * | 2017-09-27 | 2018-01-19 | 广东欧珀移动通信有限公司 | Solve lock control method and Related product |
| CN108564007A (en) * | 2018-03-27 | 2018-09-21 | 深圳市智能机器人研究院 | A kind of Emotion identification method and apparatus based on Expression Recognition |
| CN109446880A (en) * | 2018-09-05 | 2019-03-08 | 广州维纳斯家居股份有限公司 | Intelligent subscriber participation evaluation method, device, intelligent elevated table and storage medium |
| CN109215763A (en) * | 2018-10-26 | 2019-01-15 | 广州华见智能科技有限公司 | A kind of emotional health monitoring method and system based on facial image |
| CN109934097A (en) * | 2019-01-23 | 2019-06-25 | 深圳市中银科技有限公司 | A kind of expression and mental health management system based on artificial intelligence |
| CN113050843A (en) * | 2019-12-27 | 2021-06-29 | 深圳富泰宏精密工业有限公司 | Emotion recognition and management method, computer program, and electronic device |
| CN116489475A (en) * | 2019-12-31 | 2023-07-25 | 武汉星巡智能科技有限公司 | Video editing method, device, equipment and storage medium based on interesting expression |
| CN116489475B (en) * | 2019-12-31 | 2024-06-11 | 武汉星巡智能科技有限公司 | Video editing method, device, equipment and storage medium based on interesting expression |
| CN111291623A (en) * | 2020-01-15 | 2020-06-16 | 浙江连信科技有限公司 | Heart physiological characteristic prediction method and device based on face information |
| CN113657188A (en) * | 2021-07-26 | 2021-11-16 | 浙江大华技术股份有限公司 | Face age identification method, system, electronic device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105354527A (en) | Negative expression recognizing and encouraging system | |
| CN105335691A (en) | Smiling face identification and encouragement system | |
| CN106446753A (en) | Negative expression identifying and encouraging system | |
| CN107862299B (en) | Living body face detection method based on near-infrared and visible light binocular cameras | |
| Balcoh et al. | Algorithm for efficient attendance management: Face recognition based approach | |
| CN101587485B (en) | Face information automatic login method based on face recognition technology | |
| CN103824059B (en) | Facial expression recognition method based on video image sequence | |
| CN104036236B (en) | A kind of face gender identification method based on multiparameter exponential weighting | |
| CN104361326A (en) | Method for distinguishing living human face | |
| KR100944247B1 (en) | System and method for face recognition | |
| CN110443102B (en) | Living body face detection method and device | |
| CN104598888B (en) | A kind of recognition methods of face gender | |
| CN105975938A (en) | Smart community manager service system with dynamic face identification function | |
| CN111666845B (en) | Small sample deep learning multi-mode sign language recognition method based on key frame sampling | |
| CN104021397A (en) | Face identifying and comparing method and device | |
| Ali et al. | A robust and efficient system to detect human faces based on facial features | |
| Shrivastava et al. | Conceptual model for proficient automated attendance system based on face recognition and gender classification using Haar-Cascade, LBPH algorithm along with LDA model | |
| WO2013075295A1 (en) | Clothing identification method and system for low-resolution video | |
| CN110598574A (en) | Intelligent face monitoring and identifying method and system | |
| Mady et al. | Efficient real time attendance system based on face detection case study “MEDIU staff” | |
| Dey et al. | Computer vision based gender detection from facial image | |
| Hirzi et al. | Literature study of face recognition using the viola-jones algorithm | |
| JP5552946B2 (en) | Face image sample collection device, face image sample collection method, program | |
| Gupta et al. | HaarCascade and LBPH Algorithms in Face Recognition Analysis | |
| Zhou et al. | Real-time gender recognition based on eigen-features selection from facial images |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: 211112 Jiangning, Jiangsu Province, open source road, No. 168, No. Applicant after: NANJING PERLOVE MEDICAL EQUIPMENT CO., LTD. Address before: 211112 Jiangning, Jiangsu Province, open source road, No. 168, No. Applicant before: Nanjing Perlove Radial-video Equipment Co., Ltd. |
|
| COR | Change of bibliographic data | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160217 |