CN106248070B - A kind of navigator based on iris recognition starting - Google Patents
A kind of navigator based on iris recognition starting Download PDFInfo
- Publication number
- CN106248070B CN106248070B CN201610548382.0A CN201610548382A CN106248070B CN 106248070 B CN106248070 B CN 106248070B CN 201610548382 A CN201610548382 A CN 201610548382A CN 106248070 B CN106248070 B CN 106248070B
- Authority
- CN
- China
- Prior art keywords
- iris
- submodule
- point
- iris image
- navigator
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- 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
- G06V40/18—Eye characteristics, e.g. of the iris
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Health & Medical Sciences (AREA)
- Ophthalmology & Optometry (AREA)
- Human Computer Interaction (AREA)
- General Health & Medical Sciences (AREA)
- Automation & Control Theory (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Image Processing (AREA)
Abstract
A kind of navigator based on iris recognition starting of the present invention, including navigator and the iris recognition device connecting with navigator electric signal, the iris recognition device includes: (1) sampling module；(2) preprocessing module；(3) feature coding module, it extracts and encodes for the feature to iris image comprising first time LBP operator handles submodule, second of LBP operator processing submodule, third time LBP operator processing submodule and the 4th LBP operator and handles submodule；(4) codes match module.Invention increases the relevances of central point and the other neighborhoods of surrounding, it can satisfy the image texture of different scale and frequency, after the processing submodule processing of multiple LBP operator, in the case where not influencing the relevance of central point and surrounding neighbors, code length is constantly reduced, memory space has been saved, reduce calculation amount, recognition speed is improved, recognition accuracy is enhanced, has obtained higher robustness.
Description
Technical field
The present invention relates to navigator system design fields, and in particular to a kind of navigator based on iris recognition starting.
Background technique
In the related technology, the navigator with identification verification function generallys use basic LBP (local binary patterns) operator
Iris image feature is extracted and encoded, LBP operator is a kind of method for describing textural characteristics within the scope of image grayscale, right
There is very strong robustness for illumination variation, to be widely used in the texture feature extraction of image.
Basic LBP operator is commonly defined as: by central point n in 3 × 3 windowscAnd 8 neighborhood n around it0,...n7Group
At wherein defining texture T are as follows: T=(n0-nc,n1-nc,...,n7-nc), binary conversion treatment is carried out to it, with ncIt is adjacent for threshold value
8 points and n in domaincCompare, is labeled as 1 if more than the value of central point, is otherwise labeled as 0.Texture T after binaryzation are as follows: T=
(sgn(n0-nc),sgn(n1-nc),...,sgn(n7-nc)), whereinBy calculating, will obtain with ncFor
Then 8 binary numbers at center are weighted the LBP value that summation just obtains central point to different pixels position, wherein LBP value
Calculation formula are as follows:LBP operation is carried out to pixel each in image, can be obtained
To the LBP texture description of image.
However, making itself and other neighborhoods around since basic LBP operator covers only 8 neighborhood territory pixels of central point
Relevance is not comprehensive enough, is unable to satisfy the image texture of different scale and frequency.
Summary of the invention
It is opened in view of the above-mentioned problems, the present invention provides one kind that a kind of recognition speed is fast, identification range is wide based on iris recognition
Dynamic navigator solves the navigator that iris image feature is extracted and encoded using basic LBP operator in the related technology
System cannot handle the problem of image texture of different scale and frequency.
The purpose of the present invention is realized using following technical scheme:
A kind of navigator based on iris recognition starting, including navigator and the iris recognition being connect with navigator electric signal
Device, the navigator include:
Set casing, navigator shell, it is characterised in that: the navigator set casing is set with navigator shell upper and lower surfaces
There is buffer layer, the buffer layer is filled between navigator set casing, navigator shell, four inside the navigator set casing
Corner is equipped with grip block, and the tensioning bullet of parallel arrangement is equipped between each described grip block and navigator set casing inner wall
Spring, navigator set casing two sides vertical section are equipped with several heat release holes, and the heat release hole is arranged in low inside and high outside shape.
Preferably, characterized in that the buffer layer is made of elastic material.
Preferably, characterized in that the tensioning spring both ends are to be fixedly connected.
Preferably, characterized in that the iris recognition device includes:
(1) sampling module, for obtaining, correcting iris image and acquire the information of iris image, due to what is actually obtained
Can slightly have deviation between iris image and the iris image of standard acquisition in the same plane, need to the iris actually obtained
Image carries out plane correction, sets image rectification submodule, the updating formula that described image correction module uses are as follows:
Wherein, I (x, y)AIndicate the iris image actually obtained, I (x, y)BIndicate the iris image of standard acquisition, it is practical
Standard deviation between each pixel point value of the iris image of the iris image and standard acquisition of acquisition；
(2) preprocessing module, for carrying out positioning and normalized to the iris image of acquisition comprising hot spot point is filled out
Submodule is filled, the hot spot point filling submodule is filled for being filled to each hot spot point detected in iris image
The gray value of four envelope points up and down in non-spot area Shi Liyong adjacent with hot spot point calculates the ash of hot spot point
Angle value, defining a hot spot point in iris image is P0(x0,y0), four envelopes point is followed successively by P1(x1,y1)、P2(x2,
y2)、P3(x3,y3)、P4(x4,y4), define the gray value calculation formula of hot spot point are as follows:
Preferably, characterized in that the iris recognition device further include:
(3) feature coding module is extracted and is encoded for the feature to iris image, comprising:
A, first time LBP operator handles submodule: for any point n in iris imagecWith K in 5 × 5 windows
Pixel is compared to calculate LBP value, and the K pixel is with point ncCentered on be distributed in point ncPeriphery, if ncCoordinate be
(xc,yc), the calculation formula of LBP value are as follows:
Wherein, the K pixel is labeled as n0~nK, the value range of K is [20,24], 1st-LBP (xc,yc) take
Being worth range is [0, K]；
B, second of LBP operator handles submodule, for reinforcing the point n under the premise of guaranteeing code lengthcWith week
The relevance of neighborhood is enclosed, with point nc8 neighborhood territory pixel points as sub-center point, be denoted as nvc0,nvc1,...,nvc7, use 3
× 3 windows, with the mean value of entire pixels in windowInstead of the value of sub-center point, LBP operator is reused to central point
ncIt is calculated, calculation formula are as follows:
C, third time LBP operator handles submodule, for shortening through second LBP operator processing submodule treated square
The feature coding length of shape image, with point ncCentered on, according to custom function { n in 3 × 3 windowvcj,|nvcj-nc|
=rank4(|nvci-nc|, i=0,1 ..., 7), j=0,1,2,3 } 4 sub-center points of selection are calculated, calculation formula are as follows:
Wherein, rank4(|nvci-nc|, i=0,1 ..., 7) indicate to 7 | nvci-nc| value arranged from small to large
After take preceding 4 numbers, nvcjIndicate the 4 sub-center points chosen；
D, the 4th LBP operator handles submodule: on the basis of treated for third time LBP operator processing submodule
Continue to reduce code length, calculation formula are as follows:
Output indicates the coding of iris image feature after having been calculated；
(4) codes match module, for receive it is described indicate iris image feature coding and by its in database
Feature coding is compared, and completes the identification to identity.
Wherein, the preprocessing module further include:
(1) coarse positioning submodule: connecting with hot spot point filling submodule, for cut to iris image and tentatively fixed
Position pupil position, when cutting centered on the pupil position, 5 times of radius cuts the iris image after filling hot spot
It cuts；
(2) it fine positioning submodule: is connect with coarse positioning submodule, for being accurately positioned iris region；
(3) submodule is normalized, for the iris region after positioning to be launched into the iris image of fixed resolution.
Wherein, the fine positioning submodule includes sequentially connected downsampling unit, first positioning unit and reposition
Unit, the downsampling unit are used to carry out down-sampling to the iris image after cutting, and the first positioning unit is for passing through
Improved Canny edge detection operator and Hough loop truss position iris inside and outside circle, and the reposition unit is used for
It is accurately positioned on iris image with the parameter that first positioning unit positions.
Wherein, the improved Canny edge detection operator is the inhibition that non-maximum is only carried out to vertical direction
Canny edge detection operator.
Wherein, the improved Canny edge detection operator is the side Canny that strong edge detection is carried out only with high threshold
Edge detective operators.
The invention has the benefit that
1, image rectification submodule is set, and defines updating formula, improves the precision of image procossing；
2, setting hot spot point fills submodule, and defines the gray value calculation formula of hot spot point, remains rainbow well
Positioning can be effectively performed in the structural information of film image, filled iris image；
3, the first positioning unit being arranged, by improved Canny edge detection operator and Hough loop truss to iris
Inside and outside circle is positioned, convenient for the speed of iris positioned and improve iris；
4, the first time LBP operator being arranged handles submodule, increases the relevance of central point Yu the other neighborhoods of surrounding, energy
Enough meet the image texture of different scale and frequency；
5, second of LBP operator processing submodule, third time LBP operator processing submodule and the 4th LBP being arranged are calculated
Subprocessing submodule constantly reduces code length in the case where not influencing the relevance of central point and surrounding neighbors, and it is empty to have saved storage
Between, reduce calculation amount, improve recognition speed, enhance recognition accuracy, obtains higher robustness.
Detailed description of the invention
The present invention will be further described with reference to the accompanying drawings, but the embodiment in attached drawing is not constituted to any limit of the invention
System, for those of ordinary skill in the art, without creative efforts, can also obtain according to the following drawings
Other attached drawings.
Fig. 1 is iris recognition device connection schematic diagram of the invention.
Fig. 2 is navigator schematic diagram of the invention.
Specific embodiment
The invention will be further described with the following Examples.
Embodiment 1
Referring to Fig. 1, Fig. 2, a kind of navigator based on iris recognition starting of the present embodiment, including navigator and and navigator
The iris recognition device of electric signal connection, the navigator include:
Set casing, navigator shell, it is characterised in that: the navigator set casing is set with navigator shell upper and lower surfaces
There is buffer layer, the buffer layer is filled between navigator set casing, navigator shell, four inside the navigator set casing
A corner is equipped with grip block, and the tensioning bullet of parallel arrangement is equipped between each described grip block and navigator set casing inner wall
Spring, navigator set casing two sides vertical section are equipped with several heat release holes, and the heat release hole is arranged in low inside and high outside shape.
Preferably, characterized in that the buffer layer is made of elastic material.
Preferably, characterized in that the tensioning spring both ends are to be fixedly connected.
Preferably, characterized in that the iris recognition device includes:
(1) sampling module, for obtaining iris image and acquiring the information of iris image；
(2) preprocessing module, for obtaining, correcting iris image and acquire the information of iris image, due to practical acquisition
Iris image and standard acquisition iris image between can slightly have deviation in the same plane, need to the rainbow actually obtained
Film image carries out plane correction, sets image rectification submodule, the updating formula that described image correction module uses are as follows:
Wherein, I (x, y)AIndicate the iris image actually obtained, I (x, y)BIndicate the iris image of standard acquisition, it is practical
Standard deviation between each pixel point value of the iris image of the iris image and standard acquisition of acquisition；
Preferably, characterized in that the iris recognition device further include:
(3) feature coding module is extracted and is encoded for the feature to iris image, comprising:
A, first time LBP operator handles submodule: for any point n in iris imagecWith 20 in 5 × 5 windows
A pixel is compared to calculate LBP value, and 20 pixels are with point ncCentered on be distributed in point ncPeriphery, if ncSeat
It is designated as (xc,yc), the calculation formula of LBP value are as follows:
Wherein, 20 pixels are labeled as n0~n20, 1st-LBP (xc,yc) value range be [0,20]；
B, second of LBP operator handles submodule, for reinforcing the point n under the premise of guaranteeing code lengthcWith week
The relevance of neighborhood is enclosed, with point nc8 neighborhood territory pixel points as sub-center point, be denoted as nvc0,nvc1,...,nvc7, use 3
× 3 windows, with the mean value of entire pixels in windowInstead of the value of sub-center point, LBP operator is reused to central point
ncIt is calculated, calculation formula are as follows:
C, third time LBP operator handles submodule, for shortening through second LBP operator processing submodule treated square
The feature coding length of shape image, with point ncCentered on, according to custom function { n in 3 × 3 windowvcj,|nvcj-nc|
=rank4(|nvci-nc|, i=0,1 ..., 7), j=0,1,2,3 } 4 sub-center points of selection are calculated, calculation formula are as follows:
Wherein, rank4(|nvci-nc|, i=0,1 ..., 7) indicate to 7 | nvci-nc| value arranged from small to large
After take preceding 4 numbers, nvcjIndicate the 4 sub-center points chosen；
D, the 4th LBP operator handles submodule: on the basis of treated for third time LBP operator processing submodule
Continue to reduce code length, calculation formula are as follows:
Output indicates the coding of iris image feature after having been calculated；
(4) codes match module, for receive it is described indicate iris image feature coding and by its in database
Feature coding is compared, and completes the identification to identity.
Wherein, the preprocessing module includes:
(1) hot spot point fills submodule: for being filled to each hot spot point detected in iris image, when filling
The gray scale of hot spot point is calculated using the gray value of four envelope points up and down in the non-spot area adjacent with hot spot point
Value, defining a hot spot point in iris image is P0(x0,y0), four envelopes point is followed successively by P1(x1,y1)、P2(x2,
y2)、P3(x3,y3)、P4(x4,y4), define the gray value calculation formula of hot spot point are as follows:
(2) coarse positioning submodule: connecting with hot spot point filling submodule, for cut to iris image and tentatively fixed
Position pupil position, when cutting centered on the pupil position, 5 times of radius cuts the iris image after filling hot spot
It cuts；
(3) it fine positioning submodule: is connect with coarse positioning submodule, for being accurately positioned iris region；
(4) submodule is normalized, for the iris region after positioning to be launched into the iris image of fixed resolution.
Wherein, the fine positioning submodule includes sequentially connected downsampling unit, first positioning unit and reposition
Unit, the downsampling unit are used to carry out down-sampling to the iris image after cutting, and the first positioning unit is for passing through
Improved Canny edge detection operator and Hough loop truss position iris inside and outside circle, and the reposition unit is used for
It is accurately positioned on iris image with the parameter that first positioning unit positions.
Wherein, the improved Canny edge detection operator is the inhibition that non-maximum is only carried out to vertical direction
Canny edge detection operator.
Wherein, the improved Canny edge detection operator is the side Canny that strong edge detection is carried out only with high threshold
Edge detective operators.
The present embodiment is arranged hot spot point and fills submodule, remains the structural information of iris image well, filled
Positioning can be effectively performed in iris image；The first positioning unit being arranged, by improved Canny edge detection operator and
Hough loop truss positions iris inside and outside circle, convenient for the speed of iris positioned and improve iris；The first time of setting
LBP operator handles submodule, increases the relevance of central point Yu the other neighborhoods of surrounding, can satisfy different scale and frequency
Image texture；Second of LBP operator processing submodule, third time LBP operator processing submodule and the 4th LBP operator being arranged
Submodule is handled, in the case where not influencing the relevance of central point and surrounding neighbors, code length is constantly reduced, it is empty to have saved storage
Between, reduce calculation amount, improve recognition speed, enhance recognition accuracy, has obtained higher robustness, used CASIA
It is as a result as follows when V1.0 iris library is tested:
Embodiment 2
Referring to Fig. 1, Fig. 2, a kind of navigator based on iris recognition starting of the present embodiment, including navigator and and navigator
The iris recognition device of electric signal connection, the navigator include:
Set casing, navigator shell, it is characterised in that: the navigator set casing is set with navigator shell upper and lower surfaces
There is buffer layer, the buffer layer is filled between navigator set casing, navigator shell, four inside the navigator set casing
Corner is equipped with grip block, and the tensioning bullet of parallel arrangement is equipped between each described grip block and navigator set casing inner wall
Spring, navigator set casing two sides vertical section are equipped with several heat release holes, and the heat release hole is arranged in low inside and high outside shape.
Preferably, characterized in that the buffer layer is made of elastic material.
Preferably, characterized in that the tensioning spring both ends are to be fixedly connected.
Preferably, characterized in that the iris recognition device includes:
(1) sampling module, for obtaining iris image and acquiring the information of iris image；
(2) preprocessing module, for obtaining, correcting iris image and acquire the information of iris image, due to practical acquisition
Iris image and standard acquisition iris image between can slightly have deviation in the same plane, need to the rainbow actually obtained
Film image carries out plane correction, sets image rectification submodule, the updating formula that described image correction module uses are as follows:
Wherein, I (x, y)AIndicate the iris image actually obtained, I (x, y)BIndicate the iris image of standard acquisition, it is practical
Standard deviation between each pixel point value of the iris image of the iris image and standard acquisition of acquisition；
Preferably, characterized in that the iris recognition device further include:
(3) feature coding module is extracted and is encoded for the feature to iris image, comprising:
A, first time LBP operator handles submodule: for any point n in iris imagecWith 21 in 5 × 5 windows
A pixel is compared to calculate LBP value, and 21 pixels are with point ncCentered on be distributed in point ncPeriphery, if ncSeat
It is designated as (xc,yc), the calculation formula of LBP value are as follows:
Wherein, 21 pixels are labeled as n0~n21, 1st-LBP (xc,yc) value range be [0,21]；
B, second of LBP operator handles submodule, for reinforcing the point n under the premise of guaranteeing code lengthcWith week
The relevance of neighborhood is enclosed, with point nc8 neighborhood territory pixel points as sub-center point, be denoted as nvc0,nvc1,...,nvc7, use 3
× 3 windows, with the mean value of entire pixels in windowInstead of the value of sub-center point, LBP operator is reused to central point
ncIt is calculated, calculation formula are as follows:
C, third time LBP operator handles submodule, for shortening through second LBP operator processing submodule treated square
The feature coding length of shape image, with point ncCentered on, according to custom function { n in 3 × 3 windowvcj,|nvcj-nc|
=rank4(|nvci-nc|, i=0,1 ..., 7), j=0,1,2,3 } 4 sub-center points of selection are calculated, calculation formula are as follows:
Wherein, rank4(|nvci-nc|, i=0,1 ..., 7) indicate to 7 | nvci-nc| value arranged from small to large
After take preceding 4 numbers, nvcjIndicate the 4 sub-center points chosen；
D, the 4th LBP operator handles submodule: on the basis of treated for third time LBP operator processing submodule
Continue to reduce code length, calculation formula are as follows:
Output indicates the coding of iris image feature after having been calculated；
(4) codes match module, for receive it is described indicate iris image feature coding and by its in database
Feature coding is compared, and completes the identification to identity.
Wherein, the preprocessing module includes:
(1) hot spot point fills submodule: for being filled to each hot spot point detected in iris image, when filling
The gray scale of hot spot point is calculated using the gray value of four envelope points up and down in the non-spot area adjacent with hot spot point
Value, defining a hot spot point in iris image is P0(x0,y0), four envelopes point is followed successively by P1(x1,y1)、P2(x2,
y2)、P3(x3,y3)、P4(x4,y4), define the gray value calculation formula of hot spot point are as follows:
(2) coarse positioning submodule: connecting with hot spot point filling submodule, for cut to iris image and tentatively fixed
Position pupil position, when cutting centered on the pupil position, 5 times of radius cuts the iris image after filling hot spot
It cuts；
(3) it fine positioning submodule: is connect with coarse positioning submodule, for being accurately positioned iris region；
(4) submodule is normalized, for the iris region after positioning to be launched into the iris image of fixed resolution.
Wherein, the fine positioning submodule includes sequentially connected downsampling unit, first positioning unit and reposition
Unit, the downsampling unit are used to carry out down-sampling to the iris image after cutting, and the first positioning unit is for passing through
Improved Canny edge detection operator and Hough loop truss position iris inside and outside circle, and the reposition unit is used for
It is accurately positioned on iris image with the parameter that first positioning unit positions.
Wherein, the improved Canny edge detection operator is the inhibition that non-maximum is only carried out to vertical direction
Canny edge detection operator.
Wherein, the improved Canny edge detection operator is the side Canny that strong edge detection is carried out only with high threshold
Edge detective operators.
The present embodiment is arranged hot spot point and fills submodule, remains the structural information of iris image well, filled
Positioning can be effectively performed in iris image；The first positioning unit being arranged, by improved Canny edge detection operator and
Hough loop truss positions iris inside and outside circle, convenient for the speed of iris positioned and improve iris；The first time of setting
LBP operator handles submodule, increases the relevance of central point Yu the other neighborhoods of surrounding, can satisfy different scale and frequency
Image texture；Second of LBP operator processing submodule, third time LBP operator processing submodule and the 4th LBP operator being arranged
Submodule is handled, in the case where not influencing the relevance of central point and surrounding neighbors, code length is constantly reduced, it is empty to have saved storage
Between, reduce calculation amount, improve recognition speed, enhance recognition accuracy, has obtained higher robustness, used CASIA
It is as a result as follows when V1.0 iris library is tested:
Embodiment 3
Referring to Fig. 1, Fig. 2, a kind of navigator based on iris recognition starting of the present embodiment, including navigator and and navigator
The iris recognition device of electric signal connection, the navigator include:
Set casing, navigator shell, it is characterised in that: the navigator set casing is set with navigator shell upper and lower surfaces
There is buffer layer, the buffer layer is filled between navigator set casing, navigator shell, four inside the navigator set casing
Corner is equipped with grip block, and the tensioning bullet of parallel arrangement is equipped between each described grip block and navigator set casing inner wall
Spring, navigator set casing two sides vertical section are equipped with several heat release holes, and the heat release hole is arranged in low inside and high outside shape.
Preferably, characterized in that the buffer layer is made of elastic material.
Preferably, characterized in that the tensioning spring both ends are to be fixedly connected.
Preferably, characterized in that the iris recognition device includes:
(1) sampling module, for obtaining, correcting iris image and acquire the information of iris image, due to what is actually obtained
Can slightly have deviation between iris image and the iris image of standard acquisition in the same plane, need to the iris actually obtained
Image carries out plane correction, sets image rectification submodule, the updating formula that described image correction module uses are as follows:
Wherein, I (x, y)AIndicate the iris image actually obtained, I (x, y)BIndicate the iris image of standard acquisition, it is practical
Standard deviation between each pixel point value of the iris image of the iris image and standard acquisition of acquisition；
(2) preprocessing module, for carrying out positioning and normalized to the iris image of acquisition；
Preferably, characterized in that the iris recognition device further include:
(3) feature coding module is extracted and is encoded for the feature to iris image, comprising:
A, first time LBP operator handles submodule: for any point n in iris imagecWith 22 in 5 × 5 windows
A pixel is compared to calculate LBP value, and 22 pixels are with point ncCentered on be distributed in point ncPeriphery, if ncSeat
It is designated as (xc,yc), the calculation formula of LBP value are as follows:
Wherein, 22 pixels are labeled as n0~n21, 1st-LBP (xc,yc) value range be [0,22]；
B, second of LBP operator handles submodule, for reinforcing the point n under the premise of guaranteeing code lengthcWith week
The relevance of neighborhood is enclosed, with point nc8 neighborhood territory pixel points as sub-center point, be denoted as nvc0,nvc1,...,nvc7, use 3
× 3 windows, with the mean value of entire pixels in windowInstead of the value of sub-center point, LBP operator is reused to central point
ncIt is calculated, calculation formula are as follows:
C, third time LBP operator handles submodule, for shortening through second LBP operator processing submodule treated square
The feature coding length of shape image, with point ncCentered on, according to custom function { n in 3 × 3 windowvcj,|nvcj-nc|
=rank4(|nvci-nc|, i=0,1 ..., 7), j=0,1,2,3 } 4 sub-center points of selection are calculated, calculation formula are as follows:
Wherein, rank4(|nvci-nc|, i=0,1 ..., 7) indicate to 7 | nvci-nc| value arranged from small to large
After take preceding 4 numbers, nvcjIndicate the 4 sub-center points chosen；
D, the 4th LBP operator handles submodule: on the basis of treated for third time LBP operator processing submodule
Continue to reduce code length, calculation formula are as follows:
Output indicates the coding of iris image feature after having been calculated；
(4) codes match module, for receive it is described indicate iris image feature coding and by its in database
Feature coding is compared, and completes the identification to identity.
Wherein, the preprocessing module includes:
(1) hot spot point fills submodule: for being filled to each hot spot point detected in iris image, when filling
The gray scale of hot spot point is calculated using the gray value of four envelope points up and down in the non-spot area adjacent with hot spot point
Value, defining a hot spot point in iris image is P0(x0,y0), four envelopes point is followed successively by P1(x1,y1)、P2(x2,
y2)、P3(x3,y3)、P4(x4,y4), define the gray value calculation formula of hot spot point are as follows:
(2) coarse positioning submodule: connecting with hot spot point filling submodule, for cut to iris image and tentatively fixed
Position pupil position, when cutting centered on the pupil position, 5 times of radius cuts the iris image after filling hot spot
It cuts；
(3) it fine positioning submodule: is connect with coarse positioning submodule, for being accurately positioned iris region；
(4) submodule is normalized, for the iris region after positioning to be launched into the iris image of fixed resolution.
Wherein, the fine positioning submodule includes sequentially connected downsampling unit, first positioning unit and reposition
Unit, the downsampling unit are used to carry out down-sampling to the iris image after cutting, and the first positioning unit is for passing through
Improved Canny edge detection operator and Hough loop truss position iris inside and outside circle, and the reposition unit is used for
It is accurately positioned on iris image with the parameter that first positioning unit positions.
Wherein, the improved Canny edge detection operator is the inhibition that non-maximum is only carried out to vertical direction
Canny edge detection operator.
Wherein, the improved Canny edge detection operator is the side Canny that strong edge detection is carried out only with high threshold
Edge detective operators.
The present embodiment is arranged hot spot point and fills submodule, remains the structural information of iris image well, filled
Positioning can be effectively performed in iris image；The first positioning unit being arranged, by improved Canny edge detection operator and
Hough loop truss positions iris inside and outside circle, convenient for the speed of iris positioned and improve iris；First be arranged
Secondary LBP operator handles submodule, increases the relevance of central point Yu the other neighborhoods of surrounding, can satisfy different scale and frequency
Image texture；Second of LBP operator processing submodule, third time LBP operator processing submodule and the 4th LBP being arranged are calculated
Subprocessing submodule constantly reduces code length in the case where not influencing the relevance of central point and surrounding neighbors, and it is empty to have saved storage
Between, reduce calculation amount, improve recognition speed, enhance recognition accuracy, has obtained higher robustness, used CASIA
It is as a result as follows when V1.0 iris library is tested:
Embodiment 4
Referring to Fig. 1, Fig. 2, a kind of navigator based on iris recognition starting of the present embodiment, including navigator and and navigator
The iris recognition device of electric signal connection, the navigator include:
Set casing, navigator shell, it is characterised in that: the navigator set casing is set with navigator shell upper and lower surfaces
There is buffer layer, the buffer layer is filled between navigator set casing, navigator shell, four inside the navigator set casing
Corner is equipped with grip block, and the tensioning bullet of parallel arrangement is equipped between each described grip block and navigator set casing inner wall
Spring, navigator set casing two sides vertical section are equipped with several heat release holes, and the heat release hole is arranged in low inside and high outside shape.
Preferably, characterized in that the buffer layer is made of elastic material.
Preferably, characterized in that the tensioning spring both ends are to be fixedly connected.
Preferably, characterized in that the iris recognition device includes:
(1) sampling module, for obtaining, correcting iris image and acquire the information of iris image, due to what is actually obtained
Can slightly have deviation between iris image and the iris image of standard acquisition in the same plane, need to the iris actually obtained
Image carries out plane correction, sets image rectification submodule, the updating formula that described image correction module uses are as follows:
Wherein, I (x, y)AIndicate the iris image actually obtained, I (x, y)BIndicate the iris image of standard acquisition, it is practical
Standard deviation between each pixel point value of the iris image of the iris image and standard acquisition of acquisition；
(2) preprocessing module, for carrying out positioning and normalized to the iris image of acquisition；
Preferably, characterized in that the iris recognition device further include:
(3) feature coding module is extracted and is encoded for the feature to iris image, comprising:
A, first time LBP operator handles submodule: for any point n in iris imagecWith 23 in 5 × 5 windows
A pixel is compared to calculate LBP value, and 23 pixels are with point ncCentered on be distributed in point ncPeriphery, if ncSeat
It is designated as (xc,yc), the calculation formula of LBP value are as follows:
Wherein, 23 pixels are labeled as n0~n21, 1st-LBP (xc,yc) value range be [0,23]；
B, second of LBP operator handles submodule, for reinforcing the point n under the premise of guaranteeing code lengthcWith week
The relevance of neighborhood is enclosed, with point nc8 neighborhood territory pixel points as sub-center point, be denoted as nvc0,nvc1,...,nvc7, use 3
× 3 windows, with the mean value of entire pixels in windowInstead of the value of sub-center point, LBP operator is reused to central point
ncIt is calculated, calculation formula are as follows:
C, third time LBP operator handles submodule, for shortening through second LBP operator processing submodule treated square
The feature coding length of shape image, with point ncCentered on, according to custom function { n in 3 × 3 windowvcj,|nvcj-nc|
=rank4(|nvci-nc|, i=0,1 ..., 7), j=0,1,2,3 } 4 sub-center points of selection are calculated, calculation formula are as follows:
Wherein, rank4(|nvci-nc|, i=0,1 ..., 7) indicate to 7 | nvci-nc| value arranged from small to large
After take preceding 4 numbers, nvcjIndicate the 4 sub-center points chosen；
D, the 4th LBP operator handles submodule: on the basis of treated for third time LBP operator processing submodule
Continue to reduce code length, calculation formula are as follows:
Output indicates the coding of iris image feature after having been calculated；
(4) codes match module, for receive it is described indicate iris image feature coding and by its in database
Feature coding is compared, and completes the identification to identity.
Wherein, the preprocessing module includes:
(1) hot spot point fills submodule: for being filled to each hot spot point detected in iris image, when filling
The gray scale of hot spot point is calculated using the gray value of four envelope points up and down in the non-spot area adjacent with hot spot point
Value, defining a hot spot point in iris image is P0(x0,y0), four envelopes point is followed successively by P1(x1,y1)、P2(x2,
y2)、P3(x3,y3)、P4(x4,y4), define the gray value calculation formula of hot spot point are as follows:
(2) coarse positioning submodule: connecting with hot spot point filling submodule, for cut to iris image and tentatively fixed
Position pupil position, when cutting centered on the pupil position, 5 times of radius cuts the iris image after filling hot spot
It cuts；
(3) it fine positioning submodule: is connect with coarse positioning submodule, for being accurately positioned iris region；
(4) submodule is normalized, for the iris region after positioning to be launched into the iris image of fixed resolution.
Wherein, the fine positioning submodule includes sequentially connected downsampling unit, first positioning unit and reposition
Unit, the downsampling unit are used to carry out down-sampling to the iris image after cutting, and the first positioning unit is for passing through
Improved Canny edge detection operator and Hough loop truss position iris inside and outside circle, and the reposition unit is used for
It is accurately positioned on iris image with the parameter that first positioning unit positions.
Wherein, the improved Canny edge detection operator is the inhibition that non-maximum is only carried out to vertical direction
Canny edge detection operator.
Wherein, the improved Canny edge detection operator is the side Canny that strong edge detection is carried out only with high threshold
Edge detective operators.
The present embodiment is arranged hot spot point and fills submodule, remains the structural information of iris image well, filled
Positioning can be effectively performed in iris image；The first positioning unit being arranged, by improved Canny edge detection operator and
Hough loop truss positions iris inside and outside circle, convenient for the speed of iris positioned and improve iris；The first time of setting
LBP operator handles submodule, increases the relevance of central point Yu the other neighborhoods of surrounding, can satisfy different scale and frequency
Image texture；Second of LBP operator processing submodule, third time LBP operator processing submodule and the 4th LBP operator being arranged
Submodule is handled, in the case where not influencing the relevance of central point and surrounding neighbors, code length is constantly reduced, it is empty to have saved storage
Between, reduce calculation amount, improve recognition speed, enhance recognition accuracy, has obtained higher robustness, used CASIA
It is as a result as follows when V1.0 iris library is tested:
Embodiment 5
Referring to Fig. 1, Fig. 2, a kind of navigator based on iris recognition starting of the present embodiment, including navigator and and navigator
The iris recognition device of electric signal connection, the navigator include:
Set casing, navigator shell, it is characterised in that: the navigator set casing is set with navigator shell upper and lower surfaces
There is buffer layer, the buffer layer is filled between navigator set casing, navigator shell, four inside the navigator set casing
Corner is equipped with grip block, and the tensioning bullet of parallel arrangement is equipped between each described grip block and navigator set casing inner wall
Spring, navigator set casing two sides vertical section are equipped with several heat release holes, and the heat release hole is arranged in low inside and high outside shape.
Preferably, characterized in that the buffer layer is made of elastic material.
Preferably, characterized in that the tensioning spring both ends are to be fixedly connected.
Preferably, characterized in that the iris recognition device includes:
(1) sampling module, for obtaining, correcting iris image and acquire the information of iris image, due to what is actually obtained
Can slightly have deviation between iris image and the iris image of standard acquisition in the same plane, need to the iris actually obtained
Image carries out plane correction, sets image rectification submodule, the updating formula that described image correction module uses are as follows:
Wherein, I (x, y)AIndicate the iris image actually obtained, I (x, y)BIndicate the iris image of standard acquisition, it is practical
Standard deviation between each pixel point value of the iris image of the iris image and standard acquisition of acquisition；
(2) preprocessing module, for carrying out positioning and normalized to the iris image of acquisition；
Preferably, characterized in that the iris recognition device further include:
(3) feature coding module is extracted and is encoded for the feature to iris image, comprising:
A, first time LBP operator handles submodule: for any point n in iris imagecWith 24 in 5 × 5 windows
A pixel is compared to calculate LBP value, and 24 pixels are with point ncCentered on be distributed in point ncPeriphery, if ncSeat
It is designated as (xc,yc), the calculation formula of LBP value are as follows:
Wherein, 24 pixels are labeled as n0~n21, 1st-LBP (xc,yc) value range be [0,24]；
B, second of LBP operator handles submodule, for reinforcing the point n under the premise of guaranteeing code lengthcWith week
The relevance of neighborhood is enclosed, with point nc8 neighborhood territory pixel points as sub-center point, be denoted as nvc0,nvc1,...,nvc7, use 3
× 3 windows, with the mean value of entire pixels in windowInstead of the value of sub-center point, LBP operator is reused to central point
ncIt is calculated, calculation formula are as follows:
C, third time LBP operator handles submodule, for shortening through second LBP operator processing submodule treated square
The feature coding length of shape image, with point ncCentered on, according to custom function { n in 3 × 3 windowvcj,|nvcj-nc|
=rank4(|nvci-nc|, i=0,1 ..., 7), j=0,1,2,3 } 4 sub-center points of selection are calculated, calculation formula are as follows:
Wherein, rank4(|nvci-nc|, i=0,1 ..., 7) indicate to 7 | nvci-nc| value arranged from small to large
After take preceding 4 numbers, nvcjIndicate the 4 sub-center points chosen；
D, the 4th LBP operator handles submodule: on the basis of treated for third time LBP operator processing submodule
Continue to reduce code length, calculation formula are as follows:
Output indicates the coding of iris image feature after having been calculated；
(4) codes match module, for receive it is described indicate iris image feature coding and by its in database
Feature coding is compared, and completes the identification to identity.
Wherein, the preprocessing module includes:
(1) hot spot point fills submodule: for being filled to each hot spot point detected in iris image, when filling
The gray scale of hot spot point is calculated using the gray value of four envelope points up and down in the non-spot area adjacent with hot spot point
Value, defining a hot spot point in iris image is P0(x0,y0), four envelopes point is followed successively by P1(x1,y1)、P2(x2,
y2)、P3(x3,y3)、P4(x4,y4), define the gray value calculation formula of hot spot point are as follows:
(2) coarse positioning submodule: connecting with hot spot point filling submodule, for cut to iris image and tentatively fixed
Position pupil position, when cutting centered on the pupil position, 5 times of radius cuts the iris image after filling hot spot
It cuts；
(3) it fine positioning submodule: is connect with coarse positioning submodule, for being accurately positioned iris region；
(4) submodule is normalized, for the iris region after positioning to be launched into the iris image of fixed resolution.
Wherein, the fine positioning submodule includes sequentially connected downsampling unit, first positioning unit and reposition
Unit, the downsampling unit are used to carry out down-sampling to the iris image after cutting, and the first positioning unit is for passing through
Improved Canny edge detection operator and Hough loop truss position iris inside and outside circle, and the reposition unit is used for
It is accurately positioned on iris image with the parameter that first positioning unit positions.
Wherein, the improved Canny edge detection operator is the inhibition that non-maximum is only carried out to vertical direction
Canny edge detection operator.
Wherein, the improved Canny edge detection operator is the side Canny that strong edge detection is carried out only with high threshold
Edge detective operators.
The present embodiment is arranged hot spot point and fills submodule, remains the structural information of iris image well, filled
Positioning can be effectively performed in iris image；The first positioning unit being arranged, by improved Canny edge detection operator and
Hough loop truss positions iris inside and outside circle, convenient for the speed of iris positioned and improve iris；The first time of setting
LBP operator handles submodule, increases the relevance of central point Yu the other neighborhoods of surrounding, can satisfy different scale and frequency
Image texture；Second of LBP operator processing submodule, third time LBP operator processing submodule and the 4th LBP operator being arranged
Submodule is handled, in the case where not influencing the relevance of central point and surrounding neighbors, code length is constantly reduced, it is empty to have saved storage
Between, reduce calculation amount, improve recognition speed, enhance recognition accuracy, has obtained higher robustness, used CASIA
It is as a result as follows when V1.0 iris library is tested:
Finally it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than the present invention is protected
The limitation of range is protected, although explaining in detail referring to preferred embodiment to the present invention, those skilled in the art are answered
Work as understanding, it can be with modification or equivalent replacement of the technical solution of the present invention are made, without departing from the reality of technical solution of the present invention
Matter and range.
Claims (5)
1. a kind of navigator based on iris recognition starting, including navigator and the iris recognition being connect with navigator electric signal
Device, the navigator include:
Set casing, navigator shell, it is characterised in that: the navigator set casing is equipped with navigator shell upper and lower surfaces to be subtracted
Layer is shaken, the buffer layer is filled between navigator set casing, navigator shell, four turnings inside the navigator set casing
Place is equipped with grip block, and the tensioning spring of parallel arrangement, institute are equipped between each described grip block and navigator set casing inner wall
Navigator set casing two sides vertical section is stated equipped with several heat release holes, the heat release hole is arranged in low inside and high outside shape；
The buffer layer is made of elastic material；
The tensioning spring both ends are to be fixedly connected；
The iris recognition device includes:
(1) sampling module, for obtaining, correcting iris image and acquire the information of iris image, due to the iris actually obtained
Can slightly have deviation between image and the iris image of standard acquisition in the same plane, need to the iris image actually obtained
Plane correction is carried out, image rectification submodule, the updating formula that described image correction module uses are set are as follows:
Wherein, I (x, y)AIndicate the iris image actually obtained, I (x, y)BIndicate the iris image of standard acquisition,
Indicate the standard deviation between each pixel point value of the iris image of the iris image actually obtained and standard acquisition；
(2) preprocessing module, for carrying out positioning and normalized to the iris image of acquisition comprising hot spot point filling
Module, hot spot point filling submodule is for being filled each hot spot point detected in iris image, benefit when filling
The gray value of hot spot point is calculated with the gray value of four envelope points up and down in the non-spot area adjacent with hot spot point,
Defining a hot spot point in iris image is P0(x0,y0), four envelopes point is followed successively by P1(x1,y1)、P2(x2,y2)、P3
(x3,y3)、P4(x4,y4), define the gray value calculation formula of hot spot point are as follows:
The iris recognition device further include:
(3) feature coding module is extracted and is encoded for the feature to iris image, comprising:
A, first time LBP operator handles submodule: for any point n in iris imagecWith K pixel in 5 × 5 windows
Point is compared to calculate LBP value, and the K pixel is with point ncCentered on be distributed in point ncPeriphery, if ncCoordinate be (xc,
yc), the calculation formula of LBP value are as follows:
Wherein, the K pixel is labeled as n0~nK, the value range of K is [20,24], 1st-LBP (xc,yc) value model
It encloses for [0, K]；
B, second of LBP operator handles submodule, for reinforcing the point n under the premise of guaranteeing code lengthcWith surrounding neighbors
Relevance, with point nc8 neighborhood territory pixel points as sub-center point, be denoted as nvc0,nvc1,...,nvc7, using 3 × 3 windows,
With the mean value of entire pixels in windowInstead of the value of sub-center point, LBP operator is reused to central point ncIt carries out
It calculates, calculation formula are as follows:
C, third time LBP operator handles submodule, for shortening through second LBP operator processing submodule treated iris figure
The feature coding length of picture, with point ncCentered on, according to custom function { n in 3 × 3 windowvcj,|nvcj-nc|=
rank4(|nvci-nc|, i=0,1 ..., 7), j=0,1,2,3 } 4 sub-center points of selection are calculated, calculation formula are as follows:
Wherein, rank4(|nvci-nc|, i=0,1 ..., 7) indicate to 7 | nvci-nc| value carry out from small to large arrange after take
Preceding 4 numbers, nvcjIndicate the 4 sub-center points chosen；
D, the 4th LBP operator handles submodule: for continuing on the basis of treated in third time LBP operator processing submodule
Reduce code length, calculation formula are as follows:
Output indicates the coding of iris image feature after having been calculated；
(4) codes match module, for receiving the coding for indicating iris image feature and by itself and the feature in database
Coding is compared, and completes the identification to identity.
2. a kind of navigator based on iris recognition starting according to claim 1, characterized in that the preprocessing module
Further include:
(1) coarse positioning submodule: connecting with hot spot point filling submodule, for cut simultaneously Primary Location pupil to iris image
Hole site, when cutting centered on the pupil position, 5 times of radius cuts the iris image after filling hot spot；
(2) it fine positioning submodule: is connect with coarse positioning submodule, for being accurately positioned iris region；
(3) submodule is normalized, for the iris region after being accurately positioned to be launched into the iris image of fixed resolution.
3. a kind of navigator based on iris recognition starting according to claim 2, characterized in that the fine positioning submodule
Block includes sequentially connected downsampling unit, first positioning unit and repositions unit, and the downsampling unit is used for cutting
Iris image after cutting carries out down-sampling, the first positioning unit be used for through improved Canny edge detection operator and
Hough loop truss positions iris inside and outside circle, the parameter for repositioning unit and being used to position with first positioning unit
It is accurately positioned on iris image.
4. a kind of navigator based on iris recognition starting according to claim 3, characterized in that described improved
Canny edge detection operator is the Canny edge detection operator that the inhibition of non-maximum is only carried out to vertical direction.
5. a kind of navigator based on iris recognition starting according to claim 4, characterized in that described improved
Canny edge detection operator is the Canny edge detection operator that strong edge detection is carried out only with high threshold.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610548382.0A CN106248070B (en) | 2016-07-08 | 2016-07-08 | A kind of navigator based on iris recognition starting |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610548382.0A CN106248070B (en) | 2016-07-08 | 2016-07-08 | A kind of navigator based on iris recognition starting |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106248070A CN106248070A (en) | 2016-12-21 |
| CN106248070B true CN106248070B (en) | 2019-07-23 |
Family
ID=57613867
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610548382.0A Active CN106248070B (en) | 2016-07-08 | 2016-07-08 | A kind of navigator based on iris recognition starting |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106248070B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106934349B (en) * | 2017-02-17 | 2024-01-23 | 深圳市明天生物识别科技有限公司 | Dual-camera imaging and iris acquisition and recognition integrated equipment |
| CN108509865B (en) * | 2018-03-09 | 2021-02-26 | 贵州人和致远数据服务有限责任公司 | Industrial injury information input method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104331954A (en) * | 2014-11-03 | 2015-02-04 | 成都缤果科技有限公司 | Vehicle navigator adopting iris recognition |
| CN205086807U (en) * | 2015-11-10 | 2016-03-16 | 德文能源股份有限公司 | Audio -visual navigator of antidetonation formula car |
| CN105550658A (en) * | 2015-12-24 | 2016-05-04 | 蔡叶荷 | Face comparison method based on high-dimensional LBP (Local Binary Patterns) and convolutional neural network feature fusion |
| CN105740833A (en) * | 2016-02-03 | 2016-07-06 | 北京工业大学 | Human body behavior identification method based on depth sequence |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007323126A (en) * | 2006-05-30 | 2007-12-13 | Kyocera Corp | Input device and input operation method |
-
2016
- 2016-07-08 CN CN201610548382.0A patent/CN106248070B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104331954A (en) * | 2014-11-03 | 2015-02-04 | 成都缤果科技有限公司 | Vehicle navigator adopting iris recognition |
| CN205086807U (en) * | 2015-11-10 | 2016-03-16 | 德文能源股份有限公司 | Audio -visual navigator of antidetonation formula car |
| CN105550658A (en) * | 2015-12-24 | 2016-05-04 | 蔡叶荷 | Face comparison method based on high-dimensional LBP (Local Binary Patterns) and convolutional neural network feature fusion |
| CN105740833A (en) * | 2016-02-03 | 2016-07-06 | 北京工业大学 | Human body behavior identification method based on depth sequence |
Non-Patent Citations (1)
| Title |
|---|
| 虹膜特征表达与识别算法研究;李欢利;《中国博士学位论文全文数据库 信息科技辑》;20131015(第10期);第6,17-25页 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106248070A (en) | 2016-12-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102136058B (en) | Bar code image identification method | |
| CN107977656A (en) | A kind of pedestrian recognition methods and system again | |
| CN106934795A (en) | The automatic testing method and Forecasting Methodology of a kind of glue into concrete beam cracks | |
| CN103714548A (en) | Infrared image and visible image registration method based on visual attention | |
| CN104134220A (en) | Low-altitude remote sensing image high-precision matching method with consistent image space | |
| CN110287953B (en) | Water level automatic identification method and device | |
| CN103136525A (en) | Hetero-type expanded goal high-accuracy positioning method with generalized Hough transposition | |
| CN105975894B (en) | A kind of one-dimension code recognizer based on auto-adaptable image edge detection and mapping model | |
| CN103400131A (en) | Correction device and method for image identification | |
| CN106248070B (en) | A kind of navigator based on iris recognition starting | |
| Yu et al. | A new algorithm for shoreline extraction from satellite imagery with non-separable wavelet and level set method | |
| CN106776979A (en) | Vector Electronic Map increased quality automatic mode based on remote sensing | |
| CN106204958B (en) | A kind of ATM machine input unit being identified by iris | |
| CN102521559B (en) | 417 bar code identification method based on sub-pixel edge detection | |
| CN105959121B (en) | A kind of mobile terminal with identification verification function | |
| CN106022320B (en) | A kind of automatic control device based on iris recognition | |
| CN116778346B (en) | Pipeline identification method and system based on improved self-attention mechanism | |
| CN109685791A (en) | A kind of corrugated board robust detection algorithm based on more window auto-correlation skin texture detections | |
| CN106206112B (en) | A kind of control switch by iris recognition | |
| CN106006312B (en) | A kind of elevator cage being identified by iris | |
| CN106203348B (en) | A kind of high-tension switch cabinet with identification verification function | |
| CN106204842B (en) | A kind of door lock being identified by iris | |
| CN102682293A (en) | Method and system for identifying salient-point mould number of revolution-solid glass bottle based on images | |
| CN106203345B (en) | Image control device with identity authentication function | |
| CN106228114B (en) | A kind of household electrical appliances device for automatically regulating with identity recognition function |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20190621 Address after: Room 901, No. 6, 600 Lane, Yunling West Road, Putuo District, Shanghai, 2003 Applicant after: Shanghai Industrial Control Safety Innovation Technology Co., Ltd. Address before: No. 32, Zhenhai District, Zhejiang Province, Zhenhai District, Drum Tower East Road, Ningbo, Zhejiang Applicant before: Zhong Linchao |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |