CN104751120B - Hand-held mobile iris identification device and its recognition methods based on colour TV camera - Google Patents
Hand-held mobile iris identification device and its recognition methods based on colour TV camera Download PDFInfo
- Publication number
- CN104751120B CN104751120B CN201510094784.3A CN201510094784A CN104751120B CN 104751120 B CN104751120 B CN 104751120B CN 201510094784 A CN201510094784 A CN 201510094784A CN 104751120 B CN104751120 B CN 104751120B
- Authority
- CN
- China
- Prior art keywords
- iris
- image
- camera
- color
- color camera
- 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
Landscapes
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Image Input (AREA)
Abstract
The present invention discloses a kind of hand-held mobile iris identification device based on colour TV camera and its recognition methods, which includes color camera, the infrared chip of sense, infrared light compensating lamp and image processing unit;Infrared light compensating lamp is mounted on before color camera;Feel infrared chip and image processing unit is set in color camera;Infrared chip is felt for changing the infrared effect of sense of color camera, and color camera is enabled to perceive the infrared signal of surrounding;Infrared light compensating lamp when capturing image for making image convert monochromatizing according to algorithm;Image processing unit is used to remove the spot of color image, and color image is converted to black white image.The present invention is low in energy consumption, small in size, easy to carry, and color image can be converted to black white image, be applied to it in Algorithm of Iris Recognition by the blotch removal of color image by it.
Description
Technical field
The present invention relates to a kind of wireless communication device more particularly to a kind of hand-held mobile irises based on colour TV camera
Identification device and its recognition methods.
Background technique
Iris recognition product above market, or be external mostly with black and white camera based on monochromatic 8 bit images
Power supply, or powered by USB port is mounted on irremovable behind a position.
Therefore in view of the above-mentioned problems, it is necessary to design a kind of hand-held mobile iris identification device based on colour TV camera and
Its recognition methods makes up drawbacks described above.
Summary of the invention
The present invention proposes a kind of hand-held mobile iris identification device based on colour TV camera and its recognition methods, function
Consume it is low, it is small in size, it is easy to carry, and color image can be converted to black white image, make it by the blotch removal of color image by it
It is applied in Algorithm of Iris Recognition.
The technical scheme of the present invention is realized as follows:
Hand-held mobile iris identification device based on colour TV camera comprising color camera feels infrared chip, is infrared
Light compensating lamp and image processing unit;Infrared light compensating lamp is mounted on before color camera;Feel infrared chip and image processing unit
It is set in color camera;Infrared chip is felt for changing the infrared effect of sense of color camera, and color camera is enabled to perceive week
The infrared signal enclosed;Infrared light compensating lamp when capturing image for making image convert monochromatizing according to algorithm;Image procossing list
Color image is converted to black white image for removing the spot of color image by member.
Wherein, which is further provided with for providing the power module of operating voltage, and
Power module is electrically connected with color camera.
Wherein, power module is four section dry cells.
Wherein, color camera is equipped with handheld terminal.
The recognition methods of hand-held mobile iris identification device based on colour TV camera comprising following steps: (1) color
When the infrared chip of sense on form and aspect machine senses the infrared signal on periphery, starting color camera is started to work;(2) color camera is opened
When beginning to shoot, the infrared light compensating lamp of the front is started to work, so that color camera image when capturing is in monochrome;(3) for coloured silk
Color image is converted to black and white by image processing unit by the blotch removal of color image by the image that form and aspect machine takes
Image is applied to it in Algorithm of Iris Recognition.
Compared with prior art, the present invention has the advantage that
(1) with now common color camera, by software image modification for monochrome, the sense for changing simultaneously camera is red
Outer effect, before camera add close infrared light compensating lamp, in this way when capturing image will will monochromatizing, in order to remove
The spot problem of color image, just applies some image processing techniques, and colour is converted into black white image, makes common colour
Camera, the image photographed can be applied in Algorithm of Iris Recognition.
(2) low power consumption product is the final trend of product development, and with existing 6748 chip of TM company, this is one
Money low-power consumption, the chip of high property can reach the desired function of product with the common dry cell of 4 sections with this chip,
(3) due to small power consumption, so processing chip is also just fairly small, this is just to make hand-held mobile iris equipment to lay
Basis;Mobile iris terminal can carry mobile phone all of the above function, while can also want other customized function plus client
Energy.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is the structural block diagram of the hand-held mobile iris identification device the present invention is based on colour TV camera.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Referring to Fig.1, a kind of hand-held mobile iris identification device based on colour TV camera comprising color camera, sense
Infrared chip, infrared light compensating lamp and image processing unit;Infrared light compensating lamp is mounted on before color camera;Feel infrared chip and
Image processing unit is set in color camera;Infrared chip is felt for changing the infrared effect of sense of color camera, so that colored
Infrared signal around the perception of phase function;Infrared light compensating lamp when capturing image for making image be converted into list according to algorithm
Color;Image processing unit is used to remove the spot of color image, and color image is converted to black white image.
The infrared effect of sense of the present invention is to play the role of light filling, in this situation in the insufficient situation of night
Under according to algorithm, to carry out unlatching light compensating lamp.
Colour is converted monochromatizing according to following algorithm when color image by the present invention: there are commonly: one, it is famous
Psychology formula Gray=R*0.299+G*0.587+B*0.114;Two, integer arithmetic.And when practical application, it is desirable to avoid low speed
Floating-point operation, so needing to use integer arithmetic.
Coefficient is all 3 precision, they can be scaled 1000 times to realize integer arithmetic algorithm by those skilled in the art:
Gray=(R*299+G*587+B*114+500)/1000.
RGB is usually 8 precision, now 1000 times of scaling, so operation above is the operation of 32 integers;It is subsequent
Division is division of integer, so needing to round up plus 500 to realize.
Rounding procedure used in the present invention does not round up, and has biggish error because rounding up, it should will be with
The error of preceding calculated result counts together, and the method therefore rounding procedure use of the invention truncates, being write as expression formula is:
Gray=(R*19595+G*38469+B*7472) > > 16;The coefficient of 2 to 20 precision:
Gray=(R*1+G*2+B*1) > > 2Gray=(R*2+G*5+B*1) > > 3Gray=(R*4+G*10+B*2) > >
4Gray=(R*9+G*19+B*4) > > 5Gray=(R*19+G*37+B*8) > > 6;
Gray=(R*38+G*75+B*15) > > 7Gray=(R*76+G*150+B*30) > > 8Gray=(R*153+G*300
+ B*59) > > 9Gray=(R*306+G*601+B*117) > > 10Gray=(R*612+G*1202+B*234) > > 11Gray=(R*
1224+G*2405+B*467) > > 12Gray=(R*2449+G*4809+B*934) > > 13Gray=(R*4898+G*9618+B*
1868) > > 14Gra y=(R*9797+G*19235+B*3736) > > 15Gray=(R*19595+G*38469+B*7472) > >
16Gray=(R*39190+G*76939+B*14943) > > 17Gray=(R*78381+G*153878+B*29885) > > 18Gray
=(R*156762+G*307757+B*59769) > > 19Gray=(R*313524+G*615514+B*119538) > > 20.
Table above is examined, these precision are actually the same: 3 and 4,7 and 8,10 and 11,13 and 14,19
With 20;So calculation formula best under 16 bit arithmetics is using 7 precision, than the precision that previous coefficient scales 100 times
Height, and speed is fast:
Gray=(R*38+G*75+B*15) > > 7;
Wherein 2 precision, can shift optimization completely: Gray=(R+ (WORD) G<<1+B)>>2.
Hand-held mobile iris identification device of the present invention is further provided with for providing the power module of operating voltage, and electricity
Source module is electrically connected with color camera.Power module of the present invention is used to power to color camera.
Wherein, power module is four section dry cells.Those skilled in the art according to actual needs, can choose other electricity
Source module is able to achieve and provides the function of operating voltage.
Wherein, color camera is equipped with handheld terminal.The present invention facilitates it to take by the way that handheld terminal is arranged on color camera
Band.
The recognition methods of invention additionally discloses a kind of hand-held mobile iris identification device based on colour TV camera, packet
Include following steps: (1) when the infrared chip of sense on color camera senses the infrared signal on periphery, starting color camera starts work
Make;(2) when color camera starts shooting, the infrared light compensating lamp of the front is started to work, so that color camera image when capturing
In monochrome;(3) image taken for color camera will be color by image processing unit by the blotch removal of color image
Chromatic graph picture is converted to black white image, is applied to it in Algorithm of Iris Recognition.
The method of image processing unit removal color dot image of the present invention are as follows: will be special with the iris in Algorithm of Iris Recognition
Code is unsuitable is deleted for sign, and condition code obtains in the following way.
Iris feature extracts: with 16 Gabor filtering channels are selected, that is, selecting 2 Sang 2 of centre frequency, 4 Sang 2,8 Sang of Sang 2 and 16
2 and 0 °, 45 °, 90 ° and 135 ° four directions, by the symmetry of Gabor filter it is found that thus constituting different directions
With the Gabor filter under frequency.By being handled using formula (3) iris image, to obtain on each channel
Filter result, to express the difference between different texture.
Wherein, Hkj indicates convolution, iris image after I (x, y) expression processing;K indicates that k-th of scale, j indicate j-th of side
To Fkj (x, y) indicates result after convolution.
Feature coding: it after being filtered by using the filter of different frequency scale and direction to iris, obtains
The maximum value institute small echo number of sub-block filtering mould.The present invention encodes feature by using partitioned mode, extracts local phase
Information.
If entire iris image (x, y) is divided several sub-blocks of M × N size, sub-block size and filter template size
Equally;By calculating local phase information value, a plural number is obtained;If this real is more than or equal to 0,
It indicates that this feature code is 1, is otherwise 0;If this plural number imaginary part be more than or equal to 0, then it represents that this feature code be 1, otherwise for
0, therefore, finally obtain iris feature code.
The present invention is during shooting iris image by color camera, due to the change by human eye and color camera
Change, uneven illumination is even etc. while factors influence, it will influence iris recognition effect, reduce the accuracy rate of iris recognition.In order to
Iris information is accurately extracted and acquires, eliminating above-mentioned factor bring influences, be to iris before iris feature extracts progress
Image is pre-processed;The pretreatment of iris image generally comprises Iris Location, image normalization and enhancing.
Iris Location: general using by slightly to the localization method of essence, the first progress to the iris inner boundary center of circle and radius
Then coarse positioning is accurately positioned the outer edge of iris, will finally come out iris region segmentation.
(1) coarse positioning.The pupil color of original iris image is obviously more black than the other parts of eyes, this explanation
The gray value of pupil is comparatively smaller, and is the maximum connected region of area, but iris is wanted with respect to the other parts of eyes
It becomes clear, this shows comparatively the gray value of iris wants larger, and iris is most white, gray value in the eyes of people
Accordingly also it is the largest;Therefore, the mutation of the gray level variation of human eye and the good cyclic character of iris be can use, carried out
The center of circle of the pupil of human eye and radius coarse positioning.
(2) fine positioning.After the center of circle of pupil and radius substantially determine, so that it may special according to the circular configuration of iris
Sign can carry out fine positioning to the outer edge of iris.
Fine positioning is carried out to the inward flange of iris first, ranging formula is as follows:
Wherein, D (x, y) is the gray-scale edges image obtained using Canny operator, G0(r) Gaussian function, r are indicated0It indicates
Pupil radium after coarse positioning, Δ r indicate determining search range;Since the outer edge of iris is ratio for inward flange
It is relatively fuzzy, if being easy for generating the inaccurate phenomenon of positioning, for anti-fastening using fine positioning method identical with inward flange
The generation of the inaccurate phenomenon in position, the present invention replace line integral to position the outer edge of iris using Line Integral, specific to position
Formula is as follows:
Wherein, Δ r indicates search range, R0Value determined according to the general proportions relationship of iris internal-and external diameter, to search
Rope range, D (x, y) are the gray-scale edges image obtained using Canny operator.
It is completed by the positioning of above-mentioned steps iris.
The image normalization of iris: since the iris of different people is not of uniform size, even if same iris is illuminated by the light uneven and pupil
Hole scaling etc. influences, and can cause the variation of iris size, in order to eliminate this detrimental effect, it is necessary to the iris image of positioning
It is normalized, every width original image is adjusted to size identical with original image and corresponding position, to eliminate
Scaling, influence of the rotation and translation for iris recognition.
Present invention point centered on the pupil center of circle, the method that the annular region of iris is normalized to rectangular area.First
If the intersection position of the outer edge of iris image is respectively (xi (θ), yi (θ)) and (x0 (θ), y0 (θ)), then by as follows
Every bit in iris image can be all mapped in polar coordinates (r, θ) by formula (3), and such iris is after normalized
R ∈ 0, [] 1, θ ∈ [0,2 π], finally just in polar coordinates (r, θ) plane acquisition 64 × 256 sizes normalization iris figure
Picture.After iris image is normalized by above-mentioned mapping, there is invariance for eliminating scaling, rotation and translation etc..
Due to the influence that the rectangle iris image after normalization is blocked due to eyelid, so that iris image be made to contain noise letter
Breath while iris is normalized, need to carry out respective markers to noise, generate one to eliminate noise jamming effect
A noise shielding template corresponding with normalization iris;In noise shielding template, noise information is marked as 0, iris letter
Breath is marked as 1.
The enhancing of iris image: due to the influence of the factors such as corneal reflection and light source position, the illumination on iris image divides
Cloth is unable to substantially uniformity, to influence subsequent texture analysis effect.Recognition efficiency in order to better improve, feature extraction it
Before first normalized iris image must be enhanced.
The present invention is to the iris image after normalization using the histogram equalization of part.If the gray level of original image is
Rk, histogram equalization use a gamma function as transforming function transformation function, and gamma function is T (r), total pixel in iris image
Number is N, and input histogram is corrected, the distributed function S (r) of image after being changed, the picture that gray level is ri in image
Plain sum, then have:
Image after histogram equalization is the image of width grey level homogeneous distribution, the dynamic model of image gray levels
It encloses and is increased, to realize image enhancement, reduce the influence of inhomogeneous illumination;Iris after pre-processing above
Unfolded image carries out modular character extraction again.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Within mind and principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (5)
1. the hand-held mobile iris identification device based on colour TV camera, which is characterized in that it includes color camera, feels infrared
Chip, infrared light compensating lamp and image processing unit;Infrared light compensating lamp is mounted on before color camera;Feel infrared chip and image
Processing unit is set in color camera;
Infrared chip is felt for changing the infrared effect of sense of color camera, and color camera is enabled to perceive the infrared signal of surrounding;
Infrared light compensating lamp when capturing image for making image convert monochromatizing;
Image processing unit is used to remove the spot of color image, and color image is converted to black white image;It further include to colour
Image is pre-processed:
First to the carry out coarse positioning in the iris inner boundary center of circle and radius, it is then accurately positioned the outer edge of iris, finally will
Iris region segmentation comes out;
According to the circular structural feature of iris, fine positioning is carried out to the outer edge of iris;
Fine positioning is carried out to the inward flange of iris, ranging formula is as follows:
Wherein, D (x, y) is the gray-scale edges image obtained using Canny operator, G0(r) Gaussian function, r are indicated0Indicate thick fixed
Pupil radium behind position, Δ r indicate determining inward flange search range;Replace line integral to the outer edge of iris using Line Integral
It is positioned, ranging formula is as follows:
Wherein, Δ R indicates outer edge search range, R0Value determined according to the proportionate relationship of iris internal-and external diameter, this for search model
It encloses, D (x, y) is the gray-scale edges image obtained using Canny operator.
2. the hand-held mobile iris identification device based on colour TV camera as described in claim 1, which is characterized in that its into
One step is equipped with for providing the power module of operating voltage, and power module is electrically connected with color camera.
3. the hand-held mobile iris identification device based on colour TV camera as claimed in claim 2, which is characterized in that power supply
Module is four section dry cells.
4. the hand-held mobile iris identification device based on colour TV camera as claimed in claim 3, which is characterized in that colored
Camera is equipped with handheld terminal.
5. the recognition methods of the hand-held mobile iris identification device based on colour TV camera, which is characterized in that it includes as follows
Step:
(1) when the infrared chip of sense on color camera senses the infrared signal on periphery, starting color camera is started to work;
(2) when color camera starts shooting, the infrared light compensating lamp of the front is started to work, so that color camera image when capturing
In monochrome;
(3) image taken for color camera, by image processing unit by the blotch removal of color image, by cromogram
As being converted to black white image, it is applied to it in Algorithm of Iris Recognition;
Further include being pre-processed to color image:
First to the carry out coarse positioning in the iris inner boundary center of circle and radius, it is then accurately positioned the outer edge of iris, finally will
Iris region segmentation comes out;
According to the circular structural feature of iris, fine positioning is carried out to the outer edge of iris;
Fine positioning is carried out to the inward flange of iris first, ranging formula is as follows:
Wherein, D (x, y) is the gray-scale edges image obtained using Canny operator, G0(r) Gaussian function, r are indicated0Indicate thick fixed
Pupil radium behind position, Δ r indicate determining inward flange search range;
The outer edge of iris is positioned, ranging formula is as follows:
Wherein, Δ R indicates outer edge search range, R0Value determined according to the proportionate relationship of iris internal-and external diameter, D (x, y) be benefit
The gray-scale edges image obtained with Canny operator.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510094784.3A CN104751120B (en) | 2015-03-03 | 2015-03-03 | Hand-held mobile iris identification device and its recognition methods based on colour TV camera |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510094784.3A CN104751120B (en) | 2015-03-03 | 2015-03-03 | Hand-held mobile iris identification device and its recognition methods based on colour TV camera |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104751120A CN104751120A (en) | 2015-07-01 |
CN104751120B true CN104751120B (en) | 2019-04-05 |
Family
ID=53590777
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510094784.3A Active CN104751120B (en) | 2015-03-03 | 2015-03-03 | Hand-held mobile iris identification device and its recognition methods based on colour TV camera |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104751120B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104794445B (en) * | 2015-04-20 | 2018-03-27 | 北京虹安翔宇信息科技有限公司 | A kind of dynamic human face method for collecting iris based on ARM platforms |
CN105575011A (en) * | 2015-12-14 | 2016-05-11 | 宁波保众应急科技有限公司 | Intelligent iris payment machine |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103945093A (en) * | 2013-01-21 | 2014-07-23 | 上海洪剑智能科技有限公司 | Face recognition visible and near-infrared integrated photographic device based on ARM platform, and method |
-
2015
- 2015-03-03 CN CN201510094784.3A patent/CN104751120B/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103945093A (en) * | 2013-01-21 | 2014-07-23 | 上海洪剑智能科技有限公司 | Face recognition visible and near-infrared integrated photographic device based on ARM platform, and method |
Also Published As
Publication number | Publication date |
---|---|
CN104751120A (en) | 2015-07-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106469302B (en) | A kind of face skin quality detection method based on artificial neural network | |
CN106971165B (en) | A kind of implementation method and device of filter | |
Ribeiro et al. | Recoloring algorithms for colorblind people: A survey | |
KR101887216B1 (en) | Image Reorganization Server and Method | |
CN104282002B (en) | A kind of quick beauty method of digital picture | |
CN105488793B (en) | Image display method and image processing method | |
CN109952594A (en) | Image processing method, device, terminal and storage medium | |
KR20200014842A (en) | Image illumination methods, devices, electronic devices and storage media | |
CN108229279A (en) | Face image processing process, device and electronic equipment | |
CN106326841A (en) | Quick iris recognition algorithm | |
Banić et al. | Smart light random memory sprays Retinex: a fast Retinex implementation for high-quality brightness adjustment and color correction | |
CN102663741B (en) | Method for carrying out visual stereo perception enhancement on color digit image and system thereof | |
CN103268475A (en) | Skin beautifying method based on face and skin color detection | |
CN106408510B (en) | A kind of method and system for the U.S. face masking-out obtaining facial image | |
CN104811684A (en) | Three-dimensional beautification method and device of image | |
CN102867295A (en) | Color correction method for color image | |
CN104751120B (en) | Hand-held mobile iris identification device and its recognition methods based on colour TV camera | |
CN113129390B (en) | Color blindness image re-coloring method and system based on joint significance | |
Hussain et al. | Color constancy for uniform and non-uniform illuminant using image texture | |
CN108154496A (en) | A kind of power equipment appearance suitable for electric operating robot changes recognition methods | |
CN107623845A (en) | A kind of image processing method and device based on priori | |
CN112686800B (en) | Image processing method, device, electronic equipment and storage medium | |
CN105139368B (en) | A kind of mixed type tone mapping method available for machine vision | |
CN109064431B (en) | Picture brightness adjusting method, equipment and storage medium thereof | |
CN107133932A (en) | Retina image preprocessing method and device and computing equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |