CN107665343B - Inner canthus distance measuring system for correcting interference of myopia glasses - Google Patents
Inner canthus distance measuring system for correcting interference of myopia glasses Download PDFInfo
- Publication number
- CN107665343B CN107665343B CN201711009469.1A CN201711009469A CN107665343B CN 107665343 B CN107665343 B CN 107665343B CN 201711009469 A CN201711009469 A CN 201711009469A CN 107665343 B CN107665343 B CN 107665343B
- Authority
- CN
- China
- Prior art keywords
- correction
- camera array
- channel
- cameras
- measurement
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
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
- G06V40/165—Detection; Localisation; Normalisation using facial parts and geometric relationships
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30041—Eye; Retina; Ophthalmic
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Geometry (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Eyeglasses (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention relates to the technical field of face recognition equipment; an inner canthus space measuring system for correcting interference of myopia glasses comprises a channel clamping table, a measuring camera array, a left correction camera array, a right correction camera array, a left correction target and a right correction target; the two channel clamping tables are arranged left and right, and a channel is formed in the middle of the channel clamping tables; taking one point in the middle of the channel as an observation point, arranging a measurement camera array along the direction of the channel in the right front direction, arranging a plurality of measurement cameras in an equal angle manner relative to the measurement point along the horizontal direction, respectively arranging correction camera arrays on a left channel clamp platform and a right channel clamp platform, and arranging correction target plates on the opposite sides of the correction cameras relative to the observation point; the invention realizes the function of correcting the inner canthus distance value interfered by the myopia glasses in the face recognition process, so that the data can be used for face recognition in public occasions such as security inspection and the like, and the overall recognition rate and the recognition accuracy of the face recognition system are improved.
Description
The technical field is as follows:
the invention relates to the technical field of face recognition equipment.
Background art:
in the field of face recognition, the inner canthus spacing is one of important recognition parameters, and when the inner canthus spacing is used for a face recognition algorithm, the inner canthus spacing has the characteristics of low expression correlation degree, difficulty in changing along with the age and the fat and thin problems, no change by makeup, less relation to a face-lifting project, very clear positioning and identifying characteristics, and is very suitable for operation for improving the face recognition accuracy.
At present, a considerable number of people wear myopia glasses due to the myopia problem, measurement interference is actually caused to the inner canthus distance, if the myopia glasses are not taken off, the measured inner canthus distance value can be larger than the actual value through a measurement camera, data failure identification failure can be caused when data of wearing the myopia glasses are not stored, and the problem of insufficient identification rate exists when the myopia glasses are applied to public safety facilities such as airport security inspection and other environments, so that the myopia glasses are often excluded from an algorithm.
The invention content is as follows:
in view of the above, there is a need to provide a measurement system design for face recognition that corrects for near vision lens interference.
An inner canthus space measuring system for correcting interference of myopia glasses comprises a channel clamping table, a measuring camera array, a left correction camera array, a right correction camera array, a left correction target and a right correction target; the two channel clamping tables are arranged left and right, and a channel is formed in the middle of the channel clamping tables; taking one point in the middle of the channel as an observation point, setting a measurement camera array by the observation point pointing to the right front along the channel, wherein the measurement camera array is formed by arranging a plurality of measurement cameras in an equal angle relative to the measurement point along the horizontal direction; a left correction camera array is arranged at the upper rear part of the left channel clamping table, and a plurality of correction cameras are arranged at equal angles relative to the measuring points along the horizontal direction in the left correction camera array; a right correction camera array is arranged at the upper rear part of the right channel clamping table, and a plurality of correction cameras are arranged at equal angles relative to the measuring points along the horizontal direction in the right correction camera array; a right correction target is arranged on the opposite side of the left correction camera array relative to the measuring point, the right correction target is a cambered surface, and the distance between each position on the right correction target and the longitudinal axis of the measuring point is equal; and a left correction target is arranged on the opposite side of the right correction camera array relative to the measuring point, the left correction target is a cambered surface, and the distance between each part of the left correction target and the longitudinal axis of the measuring point is equal.
When the device works, a tested person passes through a channel between channel clamping platforms, and when reaching an observation point, a system reaction is triggered to carry out observation; each measuring camera in the measuring camera array independently gives a reading to the inner canthus distance of a measured person, the face recognition computing system selects the maximum value in each reading, and records the number of the measuring camera obtaining the reading, and the number corresponds to the included angle between the face axis and the channel axis when the measured person passes through an observation point; meanwhile, each correction camera in the left correction camera array positioned at the left rear of the observation point individually identifies and shoots a right correction target through a left lens of a myopia lens to obtain an image distortion parameter, each correction camera in the right correction camera array positioned at the right rear of the observation point individually identifies and shoots a left correction target through a right lens of the myopia lens to obtain an image distortion parameter, the face recognition computing system selects corresponding left and right image distortion parameters according to the included angle between the face axis and the channel axis when the measured person passes through the observation point, looks up the table to obtain the degrees of the left and right lenses and corresponding correction values, and corrects the maximum value of the inner-eye angular spacing degrees of the measured person, so that a more accurate actual value of the inner-eye angular spacing of the measured person is obtained and is used for a subsequent face recognition algorithm.
Preferably, the number of the measuring cameras in the measuring camera array is the same as the number of the correcting cameras in the left correcting camera array and the number of the correcting cameras in the right correcting camera array, the same clockwise or anticlockwise serial number can be adopted for each measuring camera, the correcting cameras in the left correcting camera array and the correcting cameras in the right correcting camera array, the same serial number left and right correcting camera data of the measuring camera with the maximum degree can be directly selected and obtained when distortion parameters are selected, table contents are simplified during subsequent table lookup, the identification speed is increased, and the measurement accuracy is improved.
Preferably, the positions of the correction cameras in the left correction camera array and the positions of the correction cameras in the right correction camera array in the same sequence are symmetrical relative to a channel, and the design can enable the distortion parameters of the left correction camera and the right correction camera to use the same table when the distortion parameters of the left correction camera and the right correction camera are used for table look-up, so that the recognition speed is further improved.
Preferably, the left correction target and the right correction target both adopt circle images which are arranged in a rectangular array and used for marking circle centers.
The inner canthus distance measuring system for correcting the interference of the myopia glasses realizes the function of correcting the inner canthus distance value interfered by the myopia glasses in the face recognition process, so that the data can be used for face recognition in public occasions such as security inspection and the like, and the overall recognition rate and the recognition accuracy of the face recognition system are improved.
Description of the drawings:
FIG. 1 is a schematic diagram of a specific embodiment of an intra-canthus distance measurement system for correcting near vision lens interference;
FIG. 2 is a schematic diagram of the deviation of the facial axis from the channel axis of an embodiment of the system for measuring the internal canthus distance for correcting near vision lens interference;
FIG. 3 is a schematic diagram of left and right correction targets of an inner canthus space measurement system for correcting interference of a myopia lens.
In the figure: the device comprises a channel clamping table 1, a channel 101, an observation point 102, a measurement camera array 2, a left correction camera array 3, a right correction camera array 4, a left correction target 5, a right correction target 6, a circle center 7 and a circular ring 8.
The specific implementation mode is as follows:
an inner canthus distance measuring system for correcting interference of myopia glasses comprises a channel clamping table 1, a measuring camera array 2, a left correcting camera array 3, a right correcting camera array 4, a left correcting target 5 and a right correcting target 6.
The two channel clamping tables 1 are arranged left and right, and a channel 101 is formed in the middle; and taking one point in the middle of the channel as an observation point 102, wherein the observation point 102 points to the right front along the channel 101 to set a measurement camera array 2, and 7 measurement cameras in the measurement camera array 2 are arranged at equal angles relative to the measurement point 102 along the horizontal direction.
A left correction camera array 3 is arranged at the upper rear part of the left channel clamping table, and 7 correction cameras are arranged in the left correction camera array 3 along the horizontal direction at equal angles relative to the measuring point 102; the right correction camera array 4 is arranged at the upper rear part of the right channel clamping table, 7 correction cameras are arranged in the right correction camera array 4 along the horizontal direction at equal angles relative to the measuring point 102, and the specific arrangement positions of the correction cameras are completely symmetrical relative to the channel 101 and the left correction camera array 3.
A right correction target 6 is arranged on the opposite side of the left correction camera array 3 relative to the measuring point 102, the right correction target 6 is a cambered surface, and the distance between each position on the cambered surface and the longitudinal axis of the measuring point 102 is equal; the left correction target 5 is arranged on the opposite side of the right correction camera array 4 relative to the measuring point, the left correction target 5 is a cambered surface, the distances between every part on the cambered surface and the longitudinal axis of the measuring point 102 are equal, and the left correction target 5 and the right correction target 6 both adopt an image of a mark circle center 7 and a circular ring 8 which are arranged in a rectangular array.
Claims (4)
1. The system for measuring the inner canthus distance for correcting the interference of the myopia glasses is characterized by comprising a channel clamping table, a measuring camera array, a left correction camera array, a right correction camera array, a left correction target and a right correction target;
the two channel clamping tables are arranged left and right, and a channel is formed in the middle of the channel clamping tables; taking one point in the middle of the channel as an observation point, setting a measurement camera array by the observation point pointing to the right front along the channel, wherein the measurement camera array is formed by arranging a plurality of measurement cameras in an equal angle relative to the measurement point along the horizontal direction;
a left correction camera array is arranged at the upper rear part of the left channel clamping table, and a plurality of correction cameras are arranged at equal angles relative to the measuring points along the horizontal direction in the left correction camera array; a right correction camera array is arranged at the upper rear part of the right channel clamping table, and a plurality of correction cameras are arranged at equal angles relative to the measuring points along the horizontal direction in the right correction camera array;
a right correction target is arranged on the opposite side of the left correction camera array relative to the measuring point, the right correction target is a cambered surface, and the distance between each position on the right correction target and the longitudinal axis of the measuring point is equal; and a left correction target is arranged on the opposite side of the right correction camera array relative to the measuring point, the left correction target is a cambered surface, and the distance between each part of the left correction target and the longitudinal axis of the measuring point is equal.
2. The system of claim 1, wherein the number of said measurement cameras in said measurement camera array is the same as the number of correction cameras in said left correction camera array and the number of correction cameras in said right correction camera array.
3. The system of claim 2, wherein the locations of each of the correction cameras in the left correction camera array are symmetrical with the locations of like-order correction cameras in the right correction camera array with respect to the channel.
4. The system of claim 1, wherein the left and right correction targets are circle images of circle with a center of circle arranged in a rectangular array.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711009469.1A CN107665343B (en) | 2017-10-25 | 2017-10-25 | Inner canthus distance measuring system for correcting interference of myopia glasses |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711009469.1A CN107665343B (en) | 2017-10-25 | 2017-10-25 | Inner canthus distance measuring system for correcting interference of myopia glasses |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107665343A CN107665343A (en) | 2018-02-06 |
CN107665343B true CN107665343B (en) | 2020-11-06 |
Family
ID=61098498
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711009469.1A Active CN107665343B (en) | 2017-10-25 | 2017-10-25 | Inner canthus distance measuring system for correcting interference of myopia glasses |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107665343B (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103020579A (en) * | 2011-09-22 | 2013-04-03 | 上海银晨智能识别科技有限公司 | Face recognition method and system, and removing method and device for glasses frame in face image |
CN103632136A (en) * | 2013-11-11 | 2014-03-12 | 北京天诚盛业科技有限公司 | Method and device for locating human eyes |
CN105046230A (en) * | 2015-07-27 | 2015-11-11 | 上海交通大学 | Image based human canthus detection method and system |
CN107184178A (en) * | 2017-06-26 | 2017-09-22 | 廖亮举 | A kind of hand-held vision drop instrument of intelligent portable and optometry method |
-
2017
- 2017-10-25 CN CN201711009469.1A patent/CN107665343B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103020579A (en) * | 2011-09-22 | 2013-04-03 | 上海银晨智能识别科技有限公司 | Face recognition method and system, and removing method and device for glasses frame in face image |
CN103632136A (en) * | 2013-11-11 | 2014-03-12 | 北京天诚盛业科技有限公司 | Method and device for locating human eyes |
CN105046230A (en) * | 2015-07-27 | 2015-11-11 | 上海交通大学 | Image based human canthus detection method and system |
CN107184178A (en) * | 2017-06-26 | 2017-09-22 | 廖亮举 | A kind of hand-held vision drop instrument of intelligent portable and optometry method |
Non-Patent Citations (1)
Title |
---|
"视线跟踪系统中的眼角点精确定位方法";高飞;《计算机工程》;20071231;第18卷(第33期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN107665343A (en) | 2018-02-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108416791B (en) | Binocular vision-based parallel mechanism moving platform pose monitoring and tracking method | |
US20200132451A1 (en) | Structural Light Parameter Calibration Device and Method Based on Front-Coating Plane Mirror | |
CN105258710B (en) | A kind of high-precision principal point for camera scaling method | |
CN105894499B (en) | A kind of space object three-dimensional information rapid detection method based on binocular vision | |
CN104730802B (en) | Calibration, focusing method and the system and dual camera equipment of optical axis included angle | |
WO2016062076A1 (en) | Camera-based positioning method, device, and positioning system | |
AU2019205611A1 (en) | Augmented reality displays with active alignment and corresponding methods | |
CN106289062B (en) | A kind of bearing calibration of benchmark camera offset | |
CN109472189B (en) | Pupil radius compensation | |
US11480816B2 (en) | Computer-implemented method for determining centration parameters | |
CN104899609B (en) | A kind of mechanical meter recognition methods based on image registration | |
CN110009682A (en) | A kind of object recognition and detection method based on monocular vision | |
WO2018025115A3 (en) | Method and system for calibrating components of an inertial measurement unit (imu) using scene-captured data | |
WO2015013022A1 (en) | Method and computations for calculating an optical axis vector of an imaged eye | |
JP2016173313A (en) | Visual line direction estimation system, visual line direction estimation method and visual line direction estimation program | |
CN106233330A (en) | For in the method and control equipment identifying that in the three-dimensional video-frequency system of vehicle relative yaw angle changes | |
CN110889829A (en) | Monocular distance measurement method based on fisheye lens | |
CN103983186A (en) | Binocular vision system correcting method and device | |
CN107543496A (en) | A kind of stereo-visiuon measurement handmarking point based on speckle image matching | |
CN105957041A (en) | Wide-angle lens infrared image distortion correction method | |
CN109974623A (en) | 3 D information obtaining method and device based on line laser and binocular vision | |
CN103234475A (en) | Sub-pixel surface morphology detecting method based on laser triangular measuring method | |
CN104315998B (en) | Door opening degree judgment method based on depth image and azimuth angle | |
CN106296703A (en) | Scaling board, camera calibration method and device | |
US11259000B2 (en) | Spatiotemporal calibration of RGB-D and displacement sensors |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |