CN106599779A - Human ear recognition method - Google Patents
Human ear recognition method Download PDFInfo
- Publication number
- CN106599779A CN106599779A CN201610958533.XA CN201610958533A CN106599779A CN 106599779 A CN106599779 A CN 106599779A CN 201610958533 A CN201610958533 A CN 201610958533A CN 106599779 A CN106599779 A CN 106599779A
- Authority
- CN
- China
- Prior art keywords
- ear
- user
- image
- depth
- human ear
- 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
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000012876 topography Methods 0.000 claims description 11
- 230000011218 segmentation Effects 0.000 claims description 9
- 238000001514 detection method Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 5
- 238000003384 imaging method Methods 0.000 claims description 4
- 241000208340 Araliaceae Species 0.000 claims 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims 1
- 235000003140 Panax quinquefolius Nutrition 0.000 claims 1
- 235000008434 ginseng Nutrition 0.000 claims 1
- 230000007547 defect Effects 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 5
- 238000011160 research Methods 0.000 description 2
- 238000012827 research and development Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000005021 gait Effects 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
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
- G06V40/161—Detection; Localisation; Normalisation
-
- 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
- G06V40/168—Feature extraction; Face representation
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
-
- 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)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a human ear recognition method. The human ear recognition method comprises the following steps of: (1), shooting and acquiring a depth image of a user so as to obtain depth information of the user; (2), according to the obtained depth information of the user, obtaining a depth distance of a position, where the user is; (3), judging whether the depth distance of the position, where the user is, is positioned in a distance range preset by the user or not, if so, sending preset human eye image shooting starting prompt information to the user and continuously executing the step (4), and if not, when the depth distance is less than the minimum threshold value of the distance range preset by the user or greater than the maximum threshold value, respectively and correspondingly sending preset human eye image shooting preparation prompt information. By means of the human ear recognition method disclosed by the invention, human ear characteristics and contour characteristics thereof are recognized; therefore, the current recognition defects are made up; and the recognition precision is high.
Description
Technical field
The present invention relates to a kind of recognition methodss, specifically a kind of human ear identification method.
Background technology
At present, with the continuous development of human scienceses' technology, biometrics identification technology is widely used.It is biological
Feature mainly has including several mode：Face, fingerprint, iris, palmmprint, hand, gait, sound, signature etc..Wherein, facial area
Domain is easier to obtain corresponding image feature information as minimum position is blocked suffered by human body, therefore face and iris become mesh
Front conventional biological characteristic mode.Face mode has the advantages that image is convenient and obtains compared with iris mode, but it easily receives table
The factors such as feelings, age, illumination affect, and discrimination is significantly less than iris feature identification.Iris feature be although current accuracy most
The best biological mode of high, antifalsification, but, due to iris dimensions it is less, it is difficult to carry out iris image acquisition, iris image is obtained
It is link more difficult during iris identification to take.
At present, business application more ripe iris or face recognition device is focused using low pixel and short focus mostly
Camera lens, shooting distance is near, general to complete iris identification or recognition of face by limiting standing distance (in 50cm).It is this near
The recognition method of distance limits application of the iris identification/recognition of face under scene on a large scale, therefore, carry out to long distance at present
Research from living creature characteristic recognition system has important using value.Due to iris dimensions it is less, so distant range iris know
The research and development of other system face more challenges, and in recent years part research institution also actively develops correlational study, based on video camera
Do a lot of work in terms of array and the distant range iris recognition system research and development based on both man-machine interaction forms of rotary head,
The use distance of iris identification has been expanded, but, however it remains iris image resolution is low, user's location response is relatively slow or positioning
Inaccurate, system delay causes iris image to be easier to the problems such as defocus blur occur, have impact on the business of distant range iris recognition system
Industry the process of the popularization.
Therefore, at present in the urgent need to developing a kind of technology, it can carry out multi-modal biological characteristic identification, and compare biography
For single living things feature recognition of system, maximizing favourable factors and minimizing unfavourable ones, having complementary advantages between each feature not only can be realized, and can be in long distance
From while identification, the accuracy of identification is further improved, the multi-modal biological characteristic for realizing remote, high-resolution, high speed is known
Not.
The content of the invention
It is an object of the invention to provide a kind of human ear identification method, to solve the problems, such as above-mentioned background technology in propose.
For achieving the above object, the present invention provides following technical scheme：
A kind of human ear identification method, including step：The first step：The depth image of shooting, collecting user, obtains the depth letter of user
Breath；Second step：According to the depth information of the user for being obtained, the depth distance of user position is obtained；3rd step：Judge to use
Whether the depth distance of family position is located within the distance range of user preset, if it is, issuing the user with default
Ear image shoots and starts information, and continues executing with the step of step the four, if not, when the depth distance is pre- less than user
If during during the minimum threshold values of distance range or more than maximum threshold values, corresponding to respectively to send default ear image and shoot preparation and carrying
Show information；4th step：The side image of shooting, collecting user；5th step：The side image of the user of captured collection is carried out
Ear detection, then locating segmentation obtain user's side image in ear image；6th step：Judge obtained ear image
Whether the image quality parameter having is located in the numerical range of default ear image mass parameter, if it is, will be described
Ear image is stored in real time, if not, returning the step of execution step the 4th；7th step：Needed for issuing the user with iris imaging
Near infrared light, and the human ear subregion image of shooting, collecting user, and splitting from the image of the human ear subregion
Obtain ear contour area image；8th step：The ear contour area image of the user to being obtained carries out ear contour detecting,
Then locating segmentation obtains the ear profile topography in user's ear contour area image；9th step：What judgement was obtained
Whether the image quality parameter that ear profile topography has is located at default ear contour images mass parameter numerical range
It is interior, if it is, the ear profile topography is stored in real time, if not, returning the step of execution step the 7th；Tenth
Step：Iris region in ear profile topography is positioned, the ear image of stored active user is then extracted
The human ear characteristic having, and human ear characteristic that the user is had and ear contour feature and the multiple validated users for prestoring
The human ear characteristic and ear contour feature information having respectively is compared matching, completes identification process.
As further scheme of the invention：In the first step and second step, shot by depth camera collection
The depth image of collection user, obtains the depth distance of user position.
As further scheme of the invention：The human ear video camera is that autozoom video camera or numeral are focused again
Lightfield camera.
Compared with prior art, the invention has the beneficial effects as follows：The present invention is by human ear characteristic and its contour feature
It is identified, compensate for existing identification defect, accuracy of identification is high.
Specific embodiment
The technical scheme in the embodiment of the present invention is clearly and completely described below, it is clear that described embodiment
Only a part of embodiment of the invention, rather than the embodiment of whole.Based on the embodiment in the present invention, the common skill in this area
The every other embodiment that art personnel are obtained under the premise of creative work is not made, belongs to the model of present invention protection
Enclose.
In the embodiment of the present invention, a kind of human ear identification method, including step：The first step：The depth map of shooting, collecting user
Picture, obtains the depth information of user；Second step：According to the depth information of the user for being obtained, the depth of user position is obtained
Degree distance；3rd step：Whether the depth distance for judging user position is located within the distance range of user preset, if
It is then to issue the user with default ear image and shoot to start information, and continues executing with the step of step the four, if not, works as
The depth distance less than user preset distance range minimum threshold values when or during more than maximum threshold values, correspond to send pre- respectively
If ear image shoot prepare information；4th step：The side image of shooting, collecting user；5th step：Adopt to captured
The side image of the user of collection carries out ear detection, and then locating segmentation obtains the ear image in user's side image；6th
Step：Whether the image quality parameter that the obtained ear image of judgement has is located at the numerical value of default ear image mass parameter
In the range of, if it is, the ear image is stored in real time, if not, returning the step of execution step the 4th；7th step：
Issue the user with the near infrared light needed for iris imaging, and the human ear subregion image of shooting, collecting user, and from described
Segmentation in the image of human ear subregion obtains ear contour area image；8th step：The ear profile region of the user to being obtained
Area image carries out ear contour detecting, and then locating segmentation obtains the ear profile Local map in user's ear contour area image
Picture；9th step：Judge whether the image quality parameter that obtained ear profile topography has is located at default ear wheel
In wide image quality parameter numerical range, if it is, the ear profile topography is stored in real time, if not,
Return the step of execution step the 7th；Tenth step：Iris region in ear profile topography is positioned, is then extracted and is deposited
The human ear characteristic that the ear image of the active user of storage has, and human ear characteristic that the user is had and ear contour feature with
The human ear characteristic and ear contour feature information that the multiple validated users for prestoring have respectively is compared matching, completes to know
Other process；In the first step and second step, the depth image of shooting, collecting user is gathered by depth camera, obtained
The depth distance of user position；The human ear video camera is the light field shooting that autozoom video camera or numeral are focused again
Machine.
The present invention operation principle be：The present invention is comprised the following steps：
Step S101：The depth image of shooting, collecting user, obtains the depth information (three-dimensional feature information of user) of user；
Step S102：According to the depth information of the user for being obtained, (i.e. user's depth distance of acquisition user position is located
The distance between position and spot for photography)；
For the present invention, for step S101 and S102, implement, can be by the depth of depth camera shooting, collecting user
Degree image, and the depth distance of user position is exported, particular by multi views anaglyph, photometric stereo, color
Degree forming process defocuses the existing depth computing method based on image such as deduction method with obtaining user position and shooting
Depth distance between point (such as depth camera infield).
Step S103：Whether the depth distance for judging user position is located within the distance range of user preset, such as
Fruit is then to issue the user with default ear image and shoot to start information, and continues executing with step S104, if not, working as
The depth distance less than user preset distance range minimum threshold values when or during more than maximum threshold values, correspond to send pre- respectively
If ear image shoot prepare information；
For the present invention, in step s 103, implement, the ear image shoot start information can according to
The needs at family are configured in advance, and the content that for example can be played pre-recorded is " please to stop movement, stand still and look squarely
One section of sound in left side ".
For the present invention, in step s 103, implement, when the depth distance is less than user preset distance range
Minimum threshold values when, it can be that the content prerecorded is that the default described ear image that sends of correspondence shoots preparation information
One section of sound of " please be moved rearwards by "；When maximum threshold values of the depth distance more than user preset distance range, correspondence is sent out
The default ear image for going out shoots and prepares one section of sound that information can be that the content prerecorded is " please move forward "
Sound.
Step S104：The side image of shooting, collecting user；
For the present invention, in step S104, can be by human ear video camera come the side image of shooting, collecting user, the people
Ear video camera can adopt the video camera of COMS or ccd imaging sensor.The human ear video camera is preferably and adopts autozoom
Video camera can realize the lightfield camera that numeral is focused again.
Step S105：Ear detection is carried out to the side image of the user of captured collection, then locating segmentation is used
Ear image in the side image of family；
For the present invention, it should be noted that ear detection and positioning belong to specific algorithm part, implement, the present invention
Ear image can be partitioned into using the result of existing ripe ear detection and positioning scheduling algorithm.
Implement, for example can be using ear detection be carried out based on haar (Ha Er) classifier algorithm, using SDM
(Supervised Descent Method (having the gradient descent method of supervision) algorithm carries out human ear key point location.
Step S106：Judge whether the image quality parameter that obtained ear image has is located at default ear image
(ear image quality evaluation is carried out in the numerical range of mass parameter), if it is, the ear image is carried out in real time
Storage, if not, returning execution step S104；
For the present invention, in step s 106, described image mass parameter can include in resolution, contrast and colour temperature
Plant or various.The numerical range of the default ear image mass parameter, can in advance be set according to the needs of user
Put.
For the present invention, in step s 106, the ear image is possibly stored to the cloud with data storage function and puts down
Platform, remote server or other devices.
It is obvious to a person skilled in the art that the invention is not restricted to the details of above-mentioned one exemplary embodiment, Er Qie
In the case of spirit or essential attributes without departing substantially from the present invention, the present invention can be in other specific forms realized.Therefore, no matter
From the point of view of which point, embodiment all should be regarded as exemplary, and be nonrestrictive, the scope of the present invention is by appended power
Profit is required rather than described above is limited, it is intended that all in the implication and scope of the equivalency of claim by falling
Change is included in the present invention.Moreover, it will be appreciated that although this specification is been described by according to embodiment, not each
Embodiment only includes an independent technical scheme, and this narrating mode of description is only this area for clarity
Technical staff should using description as an entirety, the technical scheme in each embodiment can also Jing it is appropriately combined, form this
Art personnel may be appreciated other embodiment.
Claims (3)
1. a kind of human ear identification method, it is characterised in that including step：The first step：The depth image of shooting, collecting user, obtains
The depth information of user；Second step：According to the depth information of the user for being obtained, the depth distance of user position is obtained；
3rd step：Whether the depth distance for judging user position is located within the distance range of user preset, if it is, to
Family sends default ear image and shoots and starts information, and continues executing with the step of step the four, if not, when the depth away from
From minimum threshold values less than user preset distance range when or during more than maximum threshold values, correspond to send default human ear figure respectively
Prepare information as shooting；4th step：The side image of shooting, collecting user；5th step：To the user's of captured collection
Side image carries out ear detection, and then locating segmentation obtains the ear image in user's side image；6th step：Judgement is obtained
Whether the image quality parameter that the ear image for obtaining has is located in the numerical range of default ear image mass parameter, if
It is then in real time to be stored the ear image, if not, returning the step of execution step the 4th；7th step：Issue the user with rainbow
Near infrared light needed for film imaging, and the human ear subregion image of shooting, collecting user, and from the human ear subregion
Segmentation in image obtains ear contour area image；8th step：The ear contour area image of the user to being obtained carries out ear
Piece contour detecting, then locating segmentation obtain the ear profile topography in user's ear contour area image；9th step：Sentence
Whether the image quality parameter that disconnected obtained ear profile topography has is positioned at default ear contour images quality ginseng
In number numerical range, if it is, the ear profile topography is stored in real time, if not, returning execution step
7th step；Tenth step：Iris region in ear profile topography is positioned, stored active user is then extracted
The human ear characteristic that has of ear image, and human ear characteristic that the user is had and ear contour feature are more with what is prestored
The human ear characteristic and ear contour feature information that individual validated user has respectively is compared matching, completes identification process.
2. human ear identification method according to claim 1, it is characterised in that in the first step and second step, pass through
Depth camera gathers the depth image of shooting, collecting user, obtains the depth distance of user position.
3. human ear identification method according to claim 1, it is characterised in that the human ear video camera is autozoom shooting
The lightfield camera that machine or numeral are focused again.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610958533.XA CN106599779A (en) | 2016-10-28 | 2016-10-28 | Human ear recognition method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610958533.XA CN106599779A (en) | 2016-10-28 | 2016-10-28 | Human ear recognition method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106599779A true CN106599779A (en) | 2017-04-26 |
Family
ID=58589827
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610958533.XA Pending CN106599779A (en) | 2016-10-28 | 2016-10-28 | Human ear recognition method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106599779A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107169483A (en) * | 2017-07-12 | 2017-09-15 | 深圳奥比中光科技有限公司 | Tasks carrying based on recognition of face |
| CN107229925A (en) * | 2017-07-12 | 2017-10-03 | 深圳奥比中光科技有限公司 | Conversed using ear recognition |
| CN110197149A (en) * | 2019-05-23 | 2019-09-03 | 北京达佳互联信息技术有限公司 | Ear's critical point detection method, apparatus, storage medium and electronic equipment |
| CN113228615A (en) * | 2018-12-28 | 2021-08-06 | 索尼集团公司 | Information processing apparatus, information processing method, and information processing program |
| US12126895B2 (en) | 2018-12-28 | 2024-10-22 | Sony Group Corporation | Side-view head and ear image capturing for head related transfer functions |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1916936A (en) * | 2006-09-07 | 2007-02-21 | 北京理工大学 | ID recognizing device of combining side profile and characteristic of ear |
| CN102831390A (en) * | 2012-07-02 | 2012-12-19 | 北京科技大学 | Human ear authenticating system and method |
| CN105554385A (en) * | 2015-12-18 | 2016-05-04 | 天津中科智能识别产业技术研究院有限公司 | Remote multimode biometric recognition method and system thereof |
-
2016
- 2016-10-28 CN CN201610958533.XA patent/CN106599779A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1916936A (en) * | 2006-09-07 | 2007-02-21 | 北京理工大学 | ID recognizing device of combining side profile and characteristic of ear |
| CN102831390A (en) * | 2012-07-02 | 2012-12-19 | 北京科技大学 | Human ear authenticating system and method |
| CN105554385A (en) * | 2015-12-18 | 2016-05-04 | 天津中科智能识别产业技术研究院有限公司 | Remote multimode biometric recognition method and system thereof |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107169483A (en) * | 2017-07-12 | 2017-09-15 | 深圳奥比中光科技有限公司 | Tasks carrying based on recognition of face |
| CN107229925A (en) * | 2017-07-12 | 2017-10-03 | 深圳奥比中光科技有限公司 | Conversed using ear recognition |
| CN113228615A (en) * | 2018-12-28 | 2021-08-06 | 索尼集团公司 | Information processing apparatus, information processing method, and information processing program |
| CN113228615B (en) * | 2018-12-28 | 2023-11-07 | 索尼集团公司 | Information processing apparatus, information processing method, and computer-readable recording medium |
| US12126895B2 (en) | 2018-12-28 | 2024-10-22 | Sony Group Corporation | Side-view head and ear image capturing for head related transfer functions |
| CN110197149A (en) * | 2019-05-23 | 2019-09-03 | 北京达佳互联信息技术有限公司 | Ear's critical point detection method, apparatus, storage medium and electronic equipment |
| CN110197149B (en) * | 2019-05-23 | 2021-05-18 | 北京达佳互联信息技术有限公司 | Ear key point detection method and device, storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105554385B (en) | A kind of remote multi-modal biological characteristic recognition methods and its system | |
| CN103106401B (en) | Mobile terminal iris recognition device with human-computer interaction mechanism | |
| CN104834901B (en) | A kind of method for detecting human face, apparatus and system based on binocular stereo vision | |
| CN104380729B (en) | The context driving adjustment of camera parameters | |
| CN110837750B (en) | Face quality evaluation method and device | |
| CN109190522B (en) | Living body detection method based on infrared camera | |
| CN102855471B (en) | Remote iris intelligent imaging device and method | |
| JP2004320287A (en) | Digital camera | |
| CN107230187A (en) | The method and apparatus of multimedia signal processing | |
| CN105809144A (en) | Gesture recognition system and method adopting action segmentation | |
| CN101587542A (en) | Field depth blending strengthening display method and system based on eye movement tracking | |
| CN110929566A (en) | Human face living body detection method based on visible light and near-infrared binocular camera | |
| CN106599779A (en) | Human ear recognition method | |
| CN109453517B (en) | Virtual character control method and device, storage medium and mobile terminal | |
| TW201203134A (en) | Facial expression capturing method and apparatus therewith | |
| CN107609475B (en) | Pedestrian detection false detection extraction method based on light field camera | |
| CN105022999A (en) | Man code company real-time acquisition system | |
| CN114241379B (en) | Passenger abnormal behavior identification method, device, equipment and passenger monitoring system | |
| CN106881716A (en) | Human body follower method and system based on 3D cameras robot | |
| CN112666705A (en) | Eye movement tracking device and eye movement tracking method | |
| CN105761243A (en) | Three-dimensional full face photographing system based on structured light projection and photographing method thereof | |
| JP2004320285A (en) | Digital camera | |
| US11875080B2 (en) | Object sharing method and apparatus | |
| CN105488780A (en) | Monocular vision ranging tracking device used for industrial production line, and tracking method thereof | |
| CN102759953A (en) | Automatic camera |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170426 |