CN108960102A - The automatic detection cabin of Terahertz dangerous material and detection method - Google Patents
The automatic detection cabin of Terahertz dangerous material and detection method Download PDFInfo
- Publication number
- CN108960102A CN108960102A CN201810654361.6A CN201810654361A CN108960102A CN 108960102 A CN108960102 A CN 108960102A CN 201810654361 A CN201810654361 A CN 201810654361A CN 108960102 A CN108960102 A CN 108960102A
- Authority
- CN
- China
- Prior art keywords
- detection
- terahertz
- collecting device
- image
- image collecting
- 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
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
-
- 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
- G06V40/172—Classification, e.g. identification
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Data Mining & Analysis (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The automatic detection cabin of Terahertz dangerous material of the present invention and detection method relate to the use of automatic detection cabin and the detection method of device and method more particularly to Terahertz dangerous material that Terahertz equipment is detected.The automatic detection cabin of Terahertz dangerous material, it includes detection cabin, it detects and is equipped with sense channel in cabin, the outlet portal and entrance door being provided symmetrically in detection cabin, wherein outlet portal, sense channel and entrance door are interconnected, the first image collecting device and the second image collecting device are successively arranged above outlet portal and entrance door, sense channel side is equipped with Terahertz detection device, the automatic detection cabin of Terahertz dangerous material of the present invention, it is detected using detection cabin, improve detection efficiency, meet the dangerous goods detection demand in the case of larger flow of the people, alleviate the workload of operator.
Description
Technical field
It the present invention relates to the use of oneself for the device and method more particularly to Terahertz dangerous material that Terahertz equipment is detected
Dynamic detection cabin and detection method.
Background technique
Extreme tissue and extreme personnel seriously threaten the sternness hardly possible for becoming security for all countries department and facing to public safety
Topic, the public safety situation in China equally allow of no optimist, and used dangerous article detection system is formula detection system of stopping at present,
Such as metal detector and X ray tester etc., such system usually require Security Personnel and detect one by one to a suspect, when
Flow of the people is excessive, or needs to detect larger range, or when detecting simultaneously to multiple target, such system is due to detecting dangerous material
Inefficiency, while various Terahertz rays safety detection apparatus of detection, cannot automatically to human body take pictures detection carry it is hidden
It hides article, staff is needed to assist to carry out operation detection a suspect.And the work manually monitored is used not only to need to expend
A large amount of manpower, and be easy to make observer tired out, so that observer is easy to miss some important information, to bring
Huge economic loss.
Summary of the invention
The present invention proposes a kind of high-efficient, it can be achieved that the Terahertz dangerous material that dangerous material accurately detect for these reasons
Automatic detection cabin, and the method detected using the detection cabin.
The automatic detection cabin of Terahertz dangerous material of the present invention comprising detection cabin, including detection cabin detect cabin
Be equipped with sense channel in vivo, detect the outlet portal and entrance door that are provided symmetrically in cabin, wherein outlet portal, sense channel with
Entrance door is interconnected, and sense channel side is equipped with Terahertz detection device, is equipped at least one image in the detection cabin
Acquisition device.
Preferably, described image acquisition device is arranged above Terahertz detection device.
Preferably, there are three described image acquisition devices, respectively the first image collecting device, the second image collecting device
With third image collecting device, the first image collecting device and the second image wherein are successively arranged above outlet portal and entrance door
Acquisition device, Terahertz detection device top are equipped with third image collecting device.
Preferably, there are four described image acquisition devices, it is successively arranged the first image above outlet portal and entrance door and adopts
Acquisition means and the second image collecting device, Terahertz detection device top are equipped with third image collecting device, and Terahertz detection is set
Standby opposite is equipped with the 4th image collecting device.
Further, wherein the first image collecting device, the second image collecting device, third image collecting device and the 4th
Image collecting device is video camera.
Further, further include host computer, Terahertz detection device and image collecting device respectively with host computer phase
Even
The automatic detection cabin of Terahertz dangerous material of the present invention is detected using detection cabin, improves detection efficiency,
The dangerous goods detection demand in the case of larger flow of the people is met, the workload of operator, while present invention benefit are alleviated
With image acquisition device facial image, the detection of Terahertz equipment just can be carried out after obtaining face image, on the one hand
It can use Terahertz equipment and quick and precisely detect human body carrying concealment dangerous goods, on the other hand, when personnel conceal dangerous material
When, facial image can be quickly obtained and determine personnel, once dangerous material hiding people escapes, face image progress can be run through
It searches, convenient for arresting for public security officer.
The method that the automatic detection cabin of Terahertz dangerous material of the present invention is detected, the specific method is as follows:
Using whether having personnel's entrance at image collecting device detection entrance door, if having personnel's entrance, image collector
Set the facial image for obtaining enter personnel respectively；
The face image of third image collecting device and the 4th image acquisition device extracts the feature of facial image,
Judge whether it is face image, if not face image, then continuous collecting, until getting face image；
Personnel enter Terahertz detection device, are detected, and image collecting device takes pictures to personnel's body, obtain people
Body posture image identifies human posture's feature, judges whether posture meets testing requirements, if meeting, the detection of Terahertz equipment
Starting detects human body concealment belongings, obtains the size and shape of dangerous goods；Otherwise, human body appearance is persistently obtained
Gesture；
Detection is completed, and personnel leave from sense channel, and image collecting device judges whether personnel leave；If not leaving,
Prompt person is left.
Claim 2 is recycled, is persistently detected.
The specific method of the positive face detection is,
The face complexion area in facial image is obtained as candidate region；
Candidate region is divided, further determines that the exact extension of human face region；
By the exact extension of human face region, segmentation is normalized and the image extracted in feature, with face classification device is compared
It is right, judge whether it is face image.
The specific method of posture detection is,
(1) template posture of taking pictures is set；
(2) it is taken pictures with detection posture of the image collecting device to personnel；
(3) and using template matching algorithm photo is matched with template posture, if successful match, carries out Terahertz inspection
Otherwise the detection of measurement equipment persistently carries out posture detection.
Automatic testing method of the present invention based on Terahertz dangerous material, constantly obtains face using image collecting device
Face image and posture image, then start Terahertz equipment detection, on the one hand can accurately detect that personnel conceal
On the other hand dangerous material when personnel conceal dangerous material, can determine personnel by facial image, convenient for arresting for public security officer.
Detailed description of the invention
Fig. 1 is the structural schematic diagram in the automatic detection cabin of Terahertz dangerous material.
In figure: 1- outlet portal；2- entrance door；3- Terahertz detection device；The first image collecting device of 4-, 5- third image
Acquisition device, the 4th image collecting device of 6-；The second image collecting device of 7-.
Specific embodiment
Embodiment 1.
The automatic detection cabin of Terahertz dangerous material of the present invention comprising detection cabin, detection cabin is interior to be equipped with detection
The outlet portal 1 and entrance door 2 being provided symmetrically in cabin are detected, wherein outlet portal 1, sense channel and 2 phase of entrance door in channel
Intercommunicated, the top of outlet portal 1 and entrance door 2 is successively arranged the first image collecting device 4 and the second image collecting device 7, inspection
It surveys channel side and is equipped with Terahertz detection device 3, be equipped with third image collecting device 5, opposite above Terahertz detection device 3
Equipped with the 4th image collecting device 6, wherein the first image collecting device 4, the second image collecting device 7, third image collector
Set 5 and the 4th image collecting device 6 be video camera.
The invention also includes host computer, Terahertz detection device 3 and image collecting device are connected with host computer respectively.On
Detection system is equipped in the machine of position, which has multisource data fusion and processing capacity, Terahertz detection device 3 and Image Acquisition
The data information of device acquisition can be uploaded to host computer automatically, be detected by facial image and body of the system software to testing staff
The data such as image are judged, matched and are associated with, the processing and utilization in order to staff to testing result.
When being detected, the method specifically detected is as follows:
(1) using the first image collecting device 4 and the second image collecting device 7 detection be at entrance door 2 it is no have personnel into
Enter, if there is personnel's entrance, the first image collecting device 4, the second image collecting device 7, third image collecting device 5 and the 4th
Image collecting device 6 obtains the facial image into personnel respectively；
(2) Face datection is carried out using the method based on deep learning, and judges whether the face detected is positive face, is sentenced
If not face image, then continuous collecting, until getting face image；
The specific method of positive face detection is to obtain the face complexion area in facial image as candidate region；It will be candidate
Region segmentation further determines that the exact extension of human face region；The face that will be set in the exact extension of human face region and system
Information is compared, and judges whether it is face image.
The present invention utilizes the spy for all directions for having learnt face in face classification device in the detection system of host computer
Sign, specific learning method are as follows
Obtain the facial image in multiple angles and orientation；
Extract face characteristic, formula are as follows:
Gx (x, y)=H (x+1, y)-H (x-1, y)；
Gy (x, y)=H (x, y+1)-H (x, y-1).
Wherein, H is the image of input, and G and G are horizontal gradient and vertical gradient respectively, scan the pixel of whole image
The gradient of each pixel is calculated,
Convolution kernel is as follows:
[- 10 1] and [- 10 1]T, dot product (x, y)；
Gradient magnitude are as follows:
The gradient direction of point are as follows:
A window scan image is defined, is scanned by taking 8*8 size as an example.
The calculation method of the amplitude of pixel is as follows:
It is indicated with multidimensional characteristic vectors.
By the feature vector of calculated positive sample and the feature vector of calculated negative sample input SVM classifier in into
Row training, generates the classifier of human testing.
Face datection is carried out, judges whether equipment oriented: Face datection being carried out using the method based on deep learning, and is sentenced
Whether the disconnected face detected is positive face, if it is determined that the face that is positive then enters (3), if it is determined that not being that positive face then continues people
Face detection.
The present invention utilizes AdaBoost algorithm, by carrying out integrogram calculating to face candidate region, quickly calculates Harr-
Like feature, the Weak Classifier superposition for being generated Harr-like feature using AdaBoost algorithm become strong classifier, then will be more
A hierarchical classification device is cascaded into the classifier of Face datection.
The face complexion area that the present invention selects in facial image is detected as candidate region area of skin color, main cause
Be: the difference of the colour of skin is mainly the difference of brightness rather than the color difference of our surface cognitions, therefore pole when detection area of skin color
It is easy the influence being illuminated by the light, using YCbCr color space, the colour of skin can be made to have preferable cluster property.
To face candidate region segmentation, its object is to further determine that the exact extension of human face region, in YCbCr color
In space, Cb the and Cr component of eyes and skin has very big difference, and the gray value of eyes is relatively low, Y-component integrated distribution
In (0,120), and the Cb component of eyes is generally higher than the value of Cr component, thus combines the color of eyes and brightness mapping
The size and location of eye areas can be detected by getting up.The direction of mouth and the direction of face are consistent in most cases, have
The case where very strong stability, Mouth detection, the value of Cb ratio Cr component was much higher at this time similar to the detection of eyes, that is to say, that
Mouth is more easily detected with respect to eyes.Finally according to anthroposomatology feature, it is easy to really according to the general location of each component of face
Determine face candidate region.
(3) personnel enter Terahertz detection device 3, are detected, and third image collecting device 5 claps personnel's body
According to acquisition human posture's image identifies human posture's feature, judges whether posture meets testing requirements, if meeting, Terahertz
Equipment detection starting detects human body concealment belongings, obtains the size and shape of dangerous goods；Otherwise, it persistently obtains
Take human posture；
The present invention is to cooperate the detection of Terahertz detection device 3, and customized template posture of taking pictures is adopted using third image
Acquisition means 5 take pictures to the detection posture of personnel, and carry out gesture recognition using the algorithm of template matching and template posture, such as
Fruit detects to be matched with template posture, is carried out the detection of Terahertz detection device 3, is otherwise persistently carried out posture detection.
When detecting dangerous goods using Terahertz equipment, the terahertz image that will acquire carries out pretreatment binaryzation, denoising
Deng operation, detection positioning is carried out to the concealment article that human body carries using target detection, obtains the size and shape of dangerous goods.
(4) detection is completed, and personnel leave from sense channel, and the first image collecting device 4 and the second image collecting device 7 are sentenced
Whether disconnected personnel leave；If not leaving, prompt person is left.
(5) claim 2 is recycled, is persistently detected.
Automatic testing method of the present invention based on Terahertz dangerous material, constantly obtains face using image collecting device
Face image and posture image, then start Terahertz equipment detection, on the one hand can accurately detect that personnel conceal
On the other hand dangerous material when personnel conceal dangerous material, can determine personnel by facial image, convenient for arresting for public security officer.
In the present invention:
SVM is support vector machines, and English is whole to be known as Support Vector Machine, based on maximum class interval
A kind of linear classifier.
HOG is characterized detection algorithm, and should be whole is Histogram of Oriented Gridients, be earliest by
What French researcher Dalal etc. put forward on CVPR-2005, a kind of iamge description solving human body target detection, is one
Plant the descriptor for characterizing image Local gradient direction and gradient intensity distribution character.Its main thought is: specific at edge
In the case where Location-Unknown, the distribution of edge direction also can be very good to indicate the appearance profile of pedestrian target.
Claims (10)
1. the automatic detection cabin of Terahertz dangerous material, it is characterised in that: it is logical to be equipped with detection including detecting cabin, in detection cabin
Road detects the outlet portal and entrance door being provided symmetrically in cabin, and wherein outlet portal, sense channel are mutually interconnected with entrance door
Logical, sense channel side is equipped with Terahertz detection device, is equipped at least one image collecting device in the detection cabin.
2. the automatic detection cabin of Terahertz dangerous material as described in claim 1, it is characterised in that: the setting of described image acquisition device
Above Terahertz detection device.
3. the automatic detection cabin of Terahertz dangerous material as described in claim 1, it is characterised in that: described image acquisition device has three
It is a, respectively the first image collecting device, the second image collecting device and third image collecting device, wherein outlet portal and entrance
The top of door is successively arranged the first image collecting device and the second image collecting device, is equipped with third above Terahertz detection device
Image collecting device.
4. the automatic detection cabin of Terahertz dangerous material as described in claim 1, it is characterised in that: described image acquisition device has four
It is a, the first image collecting device and the second image collecting device, Terahertz detection are successively arranged above outlet portal and entrance door
Third image collecting device is equipped with above equipment, the opposite of Terahertz detection device is equipped with the 4th image collecting device 6.
5. the automatic detection cabin of Terahertz dangerous material as described in claim 1, it is characterised in that: the first image acquisition dress
It sets, the second image collecting device, third image collecting device and the 4th image collecting device are video camera.
6. the automatic detection cabin of Terahertz dangerous material as described in claim 1, it is characterised in that: further include host computer, Terahertz
Detection device and image collecting device are connected with host computer respectively.
7. the method detected using the automatic detection cabin of Terahertz dangerous material as described in claim 1, it is characterised in that: tool
Body method is as follows:
(1) using whether having personnel's entrance at image collecting device detection entrance door, if having personnel's entrance, image collecting device
The facial image for entering personnel is obtained respectively；
(2) facial image of third image collecting device and the acquisition of the 4th image collecting device 6, extracts the feature of facial image,
Judge whether it is face image, if not face image, then continuous collecting, until getting face image；
(3) personnel enter Terahertz detection device, are detected, and third image collecting device and the 4th image collecting device are to people
Member's body is taken pictures, and human posture's image is obtained, and is identified human posture's feature, is judged whether posture meets testing requirements, if
Meet, then Terahertz equipment detection starting, human body concealment belongings are detected, the size and shape of dangerous goods are obtained
Shape；Otherwise, human posture is persistently obtained；
(4) detection is completed, and personnel leave from sense channel, and image collecting device judges whether personnel leave；If not leaving, mention
The person of leting others have a look at leaves.
8. the method detected using the automatic detection cabin of Terahertz dangerous material as described in claim 1, it is characterised in that: follow
Ring claim 2, is persistently detected.
9. the automatic testing method based on Terahertz dangerous material as described in Claims 2 or 3, it is characterised in that: positive face detection
Specific method is,
(1) face complexion area in facial image is obtained as candidate region；
(2) candidate region is divided, further determines that the exact extension of human face region；
(3) it by the exact extension of human face region, is split normalization and extracts face characteristic, with the image in face classification device
It is compared, judges whether it is face image.
10. the automatic testing method based on Terahertz dangerous material as described in Claims 2 or 3, it is characterised in that: posture detection
Specific method is,
(1) template posture of taking pictures is set；
(2) it is taken pictures with detection posture of the image collecting device to personnel；
(3) and using template matching algorithm photo is matched with template posture, if successful match, carries out Terahertz detection and set
Otherwise standby detection persistently carries out posture detection.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810654361.6A CN108960102A (en) | 2018-06-22 | 2018-06-22 | The automatic detection cabin of Terahertz dangerous material and detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810654361.6A CN108960102A (en) | 2018-06-22 | 2018-06-22 | The automatic detection cabin of Terahertz dangerous material and detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108960102A true CN108960102A (en) | 2018-12-07 |
Family
ID=64486246
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810654361.6A Pending CN108960102A (en) | 2018-06-22 | 2018-06-22 | The automatic detection cabin of Terahertz dangerous material and detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108960102A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113673576A (en) * | 2021-07-26 | 2021-11-19 | 浙江大华技术股份有限公司 | Image detection method, terminal and computer readable storage medium thereof |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103163565A (en) * | 2011-12-16 | 2013-06-19 | 同方威视技术股份有限公司 | Pass-type human body safety inspection system |
| KR20130077221A (en) * | 2011-12-29 | 2013-07-09 | 한국식품연구원 | Apparatus for inspecting objects using terahertz wave |
| CN103901490A (en) * | 2012-12-27 | 2014-07-02 | 同方威视技术股份有限公司 | Human body security check device and human body security check method |
| CN104392220A (en) * | 2014-11-27 | 2015-03-04 | 苏州福丰科技有限公司 | Three-dimensional face recognition airport security inspection method based on cloud server |
| CN106707362A (en) * | 2016-12-02 | 2017-05-24 | 北京航星机器制造有限公司 | Human body safety inspection supervision system |
| CN107092040A (en) * | 2017-06-01 | 2017-08-25 | 上海理工大学 | Terahertz imaging rays safety detection apparatus and video procession method |
| CN107884428A (en) * | 2017-10-31 | 2018-04-06 | 重庆楚新业科技有限公司 | A kind of dangerous article detection system and its control method |
-
2018
- 2018-06-22 CN CN201810654361.6A patent/CN108960102A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103163565A (en) * | 2011-12-16 | 2013-06-19 | 同方威视技术股份有限公司 | Pass-type human body safety inspection system |
| KR20130077221A (en) * | 2011-12-29 | 2013-07-09 | 한국식품연구원 | Apparatus for inspecting objects using terahertz wave |
| CN103901490A (en) * | 2012-12-27 | 2014-07-02 | 同方威视技术股份有限公司 | Human body security check device and human body security check method |
| CN104392220A (en) * | 2014-11-27 | 2015-03-04 | 苏州福丰科技有限公司 | Three-dimensional face recognition airport security inspection method based on cloud server |
| CN106707362A (en) * | 2016-12-02 | 2017-05-24 | 北京航星机器制造有限公司 | Human body safety inspection supervision system |
| CN107092040A (en) * | 2017-06-01 | 2017-08-25 | 上海理工大学 | Terahertz imaging rays safety detection apparatus and video procession method |
| CN107884428A (en) * | 2017-10-31 | 2018-04-06 | 重庆楚新业科技有限公司 | A kind of dangerous article detection system and its control method |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113673576A (en) * | 2021-07-26 | 2021-11-19 | 浙江大华技术股份有限公司 | Image detection method, terminal and computer readable storage medium thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Li et al. | Rapid and robust human detection and tracking based on omega-shape features | |
| CN109101871A (en) | A kind of living body detection device based on depth and Near Infrared Information, detection method and its application | |
| Kawai et al. | Person re-identification using view-dependent score-level fusion of gait and color features | |
| Grundmann et al. | 3D shape context and distance transform for action recognition | |
| CN102663411B (en) | Recognition method for target human body | |
| CN101739546A (en) | Image cross reconstruction-based single-sample registered image face recognition method | |
| CN102902986A (en) | Automatic gender identification system and method | |
| CN103390164A (en) | Object detection method based on depth image and implementing device thereof | |
| WO2009123354A1 (en) | Method, apparatus, and program for detecting object | |
| CN107480586B (en) | Face characteristic point displacement-based biometric photo counterfeit attack detection method | |
| CN106682578A (en) | Human face recognition method based on blink detection | |
| Wang et al. | Segment and label indoor scene based on RGB-D for the visually impaired | |
| CN109359577A (en) | A kind of Complex Background number detection system based on machine learning | |
| CN109344909A (en) | A kind of personal identification method based on multichannel convolutive neural network | |
| DU et al. | Face detection in video based on AdaBoost algorithm and skin model | |
| CN106909883A (en) | A kind of modularization hand region detection method and device based on ROS | |
| Sali et al. | Combining Class-Specific Fragments for Object Classification. | |
| Kwaśniewska et al. | Face detection in image sequences using a portable thermal camera | |
| CN108288040A (en) | Multi-parameter face identification system based on face contour | |
| CN108960102A (en) | The automatic detection cabin of Terahertz dangerous material and detection method | |
| Li et al. | Analysis of face detection based on skin color characteristic and AdaBoost algorithm | |
| Zhang et al. | Iris image classification based on color information | |
| CN106407878B (en) | Method for detecting human face and device based on multi-categorizer | |
| Javed et al. | An intelligent alarm based visual eye tracking algorithm for cheating free examination system | |
| Bagherian et al. | Extract of facial feature point |
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: 20181207 |
|
| RJ01 | Rejection of invention patent application after publication |