CN101866420A - Image preprocessing method for optical volume holographic iris recognition - Google Patents
Image preprocessing method for optical volume holographic iris recognition Download PDFInfo
- Publication number
- CN101866420A CN101866420A CN 201010191412 CN201010191412A CN101866420A CN 101866420 A CN101866420 A CN 101866420A CN 201010191412 CN201010191412 CN 201010191412 CN 201010191412 A CN201010191412 A CN 201010191412A CN 101866420 A CN101866420 A CN 101866420A
- Authority
- CN
- China
- Prior art keywords
- iris
- image
- radius
- pixel
- region
- 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.)
- Granted
Links
Images
Abstract
The invention relates to the technical field of iris recognition, in particular to an image preprocessing method for optical volume holographic iris recognition, which is used for processing an acquired iris image. The method comprises the following steps of: (11) positioning an iris area of the acquired iris image and determining an inner edge and an outer edge of an iris and an upper eyelid and a lower eyelid of a human eye; (12) after determining the iris area, performing feature extraction and encoding on the iris; and (13) performing optical volume holographic recognition and secondary encoding on encoded data. The method is used in preprocessing procedure of the optical volume holographic iris recognition, and due to the method, the technology for the optical volume holographic iris recognition is applied in the field of the iris recognition. The technology for the optical volume holographic iris recognition is the application of the optical volume holographic iris recognition to the iris recognition and also has the function of parallelly recognizing the iris. The image preprocessing method for the optical volume holographic iris recognition has the advantages of quickly positioning the iris, reducing the amount of calculation, improving the calculation accuracy, and simultaneously improving the iris recognition ratio.
Description
Technical field
The present invention relates to the iris recognition technology field, particularly a kind of image preprocessing method that is used for optical volume holographic iris identification.
Background technology
Iris recognition has pin-point accuracy, is not easy advantages such as forgery, non-infringement, the biological identification technology that is considered to have most prospect.Since iris recognition has begun business-like process,, reach its maturity in that algorithm field is technical through years of development.The optical volume holographic image recognition technology can allow iris recognition have and discern several iris images simultaneously so that iris recognition technology has further development in the application that reaches the iris recognition field, improves the ability that iris recognition is handled a large amount of iris images.
Iris image identification the pre-treatment process comprised location, feature extraction and coding.The method of at present reliable Iris Location mainly contains the method that calculus method and edge extracting combine with Hough transformation; Feature extracting method has methods such as gabor small echo and log-gabor filtering.
But prior art is not applied to the iris recognition field to the optical volume holographic image recognition technology.
Summary of the invention
The invention provides a kind of image preprocessing method that is used for optical volume holographic iris identification, to solve the technical matters that prior art is not applied to the optical volume holographic image recognition technology iris recognition field.
The technical solution used in the present invention is as follows:
A kind of image preprocessing method that is used for optical volume holographic iris identification is handled the iris image of gathering, and described method comprises:
(11) iris image of gathering is carried out the location of iris region, determine palpebra inferior on iris outer edge and the human eye;
(12) determine iris region after, iris is carried out feature extraction and coding;
(13) data behind the coding are carried out optical volume holographic identification secondary coding.
As a kind of preferred version, the concrete steps of described step (11) are as follows:
At first carry out iris outer edge location, concrete steps are as follows:
(211) iris image of gathering is scaled;
(212) carry out morphologic filtering;
(213) be near minimum value and position near the center of image for according to image binaryzation according to brightness;
(214), determine the region of search and the search radius of iris outward flange and inward flange according to the size of pupil region and the statistical relationship between the iris radius;
(215) image after the morphologic filtering described in (212) is used canny operator extraction edge, obtain outline map, and the marginal point beyond the iris outward flange region of search removed, all possible radius is carried out Hough transformation, choose three brightness largest peaks among the Hough transformation figure that each possibility radius obtains as the best Hough of candidate peak;
(216) in the best Hough of all candidates peak, choose the peak point that meets minimum basis for estimation;
(217) after finding the outward flange radius, outline map described in (215) is amplified, and the marginal point beyond the iris inward flange region of search removed, all possible radius is carried out Hough transformation, choose three brightness largest peaks among the Hough transformation figure that each possibility radius obtains as the best Hough of candidate peak, in the best Hough of all candidates peaks, choose the peak point that meets minimum basis for estimation;
Carry out palpebra inferior location on the human eye, concrete steps are as follows:
(221) adopt Hough transformation to carry out the circle search, nearest circular arc is the upper eyelid from the pupil center of circle;
(222) image is carried out 180 degree rotations;
(223) adopt Hough transformation to carry out the circle search, nearest circular arc is a palpebra inferior from the pupil center of circle
(224) obtain positioning result;
As further preferred version, described step (216) and (217) described basis for estimation are judged according to following mode:
The brightness of determining i peak value of j possibility radius is I
Ij, this peak value is D to the distance of pupil center
Ij, the high-high brightness of all peak values is I
Max, be D to the bee-line of pupil center
Min, the basis for estimation S at i peak then
IjFor:
P wherein
IBe the weight of luminance standard, p
DIt is the weight of criterion distance.Preferred in the present invention p
I=0.3, p
D=0.7.
As a kind of preferred version,
The positioning result that above-mentioned steps (224) obtains is checked if the standard of not meeting thinks that then original iris image shooting quality is not good, the prompting of iris image acquiring is carried out in output again, the described concrete steps that positioning result is checked are as follows:
(41) among the compute location result pupil with interior mean flow rate, if be higher than preset threshold then export the prompting of carrying out iris image acquiring again, otherwise execution in step (42);
(42) calculate mean flow rate in the annulus of the outer certain radius of pupil region, if be lower than preset threshold then export the prompting of carrying out iris image acquiring again, otherwise execution in step (43);
(43) check whether iris outward flange center and inward flange off-centring surpass threshold value, if surpass threshold value then export the prompting of carrying out iris image acquiring again, otherwise execution in step (44);
(44) area that palpebra inferior covers in the calculating accounts for the number percent of iris annulus area, surpasses threshold value and then exports the prompting of carrying out iris image acquiring again.
As a kind of preferred version, the concrete steps of described step (12) are as follows:
(51) eyelid part about people's eye pattern is got up as the noise region mark, and with its deletion;
(52) use affined transformation that iris region and noise region are transformed into rectangle;
(53) image of step (52) is done Fourier transform, use log-gabor filtering to carry out feature extraction at frequency domain;
(54) do inverse fourier transform, the real part of getting image carries out binaryzation, and with the noise region deletion, gets feature coding to the end;
As a kind of preferred version, the concrete steps of described step (13) are as follows:
(61) each pixel of the image that step (12) coding is obtained is mapped among the secondary coding figure, and mapping method is that the corresponding width of a pixel on the former figure is 1 pixel, highly is the zone more than 1 pixel, and this zone is called the secondary pixel.The secondary pixel is arranged in the middle of image from the two ends up and down of image.Keep about 1/3 zone line of secondary coding figure not have the secondary pixel after having arranged all pixels.；
(62) line-spacing with the image that obtains in the step (61) expands to more than 1 pixel.
As further preferred version:
Each pixel of the image that described step (61) obtains step (12) coding, being mapped to width is 1 pixel, highly is the zone of 10～15 pixels;
Described step (62) expands the line-spacing of the image that obtains in the step (61) to 15～20 pixels.
The present invention is used for the pre-treatment process of optical volume holographic iris identification, has realized the optical volume holographic image recognition technology is applied to the iris recognition field.The optical volume holographic iris recognition technology is that optical volume holographic image is identified in the application in the iris recognition, has the function of parallel identification iris.The characteristics that the present invention is directed to optical volume holographic image identification are carried out pre-treatment to iris image, have the function of general iris recognition pre-treatment, meet the requirement of optical volume holographic image identification simultaneously again.Adopt disposal route of the present invention, realize the quick location of iris, reduce calculated amount, improve accuracy in computation, improve the iris recognition rate simultaneously.
Description of drawings
Fig. 1 is the people's eye pattern behind the morphologic filtering;
Fig. 2 is the pupil approximate region;
Fig. 3 is the outline map after limiting;
Fig. 4 is for carrying out the Hough transformation figure behind the Hough transformation to Fig. 3;
Fig. 5 is the iris-encoding synoptic diagram;
Fig. 6 is original eye image;
Fig. 7 is for adopting the Iris Location of the present invention to Fig. 6 image;
Fig. 8 is the Iris Location process flow diagram;
Fig. 9 is the output map behind the secondary coding.
Embodiment
Below in conjunction with the drawings and specific embodiments the present invention is described in more detail.
The present invention need finish three functions: the location of iris region, iris feature extraction and coding, optical volume holographic identification secondary coding.
1. iris outer edge and the upward location of palpebra inferior
Iris Location algorithm of the present invention adopts morphologic filtering and hough conversion to combine, and the quantity that reduces marginal point by coarse positioning reduces operation time to reach, and improves the purpose of arithmetic speed.Iris Location has comprised the location of iris outer edge and last palpebra inferior.
Iris outer edge location is as Fig. 1～shown in Figure 4.As shown in Figure 1, before carrying out the hough conversion, at first image is dwindled according to a certain percentage, use morphologic filtering to remove the unnecessary details (reflective spot in eyelashes, the pupil then, the reflective spot of skin, iris textures etc.), morphologic filtering need carry out earlier that image is opened and then carry out image and close, and these operations all need a structural elements usually to finish.Here adopt circular structural element, suitably select the radius of this structural element, just can remove the following detailed structure of certain size in the image, the edge of these structures can be weakened, brightness meeting and near pixel are close, can not become the edge when edge extracting.
Then as shown in Figure 2, be near minimum value and position according to brightness near the center of image, find the approximate region of pupil for according to image binaryzation.Pupil region brightness is near minimum value, and is not positioned at four corners (brightness of four corners is generally very low, also near minimum value) of eye image, as long as meet this two conditions through after the morphologic filtering, can guarantee it is the approximate region of pupil.
According to pupil region and size and the statistical relationship between the iris radius (radius of pupil is 0.1～0.8 of an iris radius, iris region is positioned at full figure 1/3 center and 1/3 horizontal center longitudinally), so just can roughly determine outer peripheral region of search of iris and search radius.The pupil region that obtains is done following processing: obtain the approximate centre of the average horizontal ordinate (being center of gravity) of pupil region, obtain each pixel in the pupil region then from the ultimate range of pupil center roughly radius as pupil as pupil
According to Daugman professor's result of study, the radius of pupil is 0.1～0.8 of an iris radius.So, there is the big roughly radius of above-mentioned pupil to obtain the roughly radius of iris, a plurality of integers in this scope are exactly a plurality of possible radiuses.
After finding the outward flange radius, image is amplified, find the region of search and the search radius of inward flange according to outward flange.This is in order to allow search have identical precision during outer edge.The radius ratio outward flange of inward flange is little, so adopt bigger ratio when searching inward flange.The general ratio that adopts the iris image that to gather to be enlarged into twice.The approximate range of inside radius is exactly the approximate range of pupil.With this roughly be worth 0.5 as may inward flange the lower limit of radius, 1.5 times as the upper limit, adopts the method search inward flange identical with the search outward flange.
Image after the morphologic filtering is used canny operator extraction edge, all possible radius is carried out Hough transformation, choose three brightness largest peaks among the Hough transformation figure that each possibility radius obtains as the best Hough of candidate peak;
Suppose to have 10 possible radiuses, then can carry out 10 times Hough transformation, use a different radius at every turn, obtain 3 peak values the brightest, always have 3 * 10=30 peak value.Among these 30 peak values, find out only peak value then according to following basis for estimation.
Basis for estimation:
Have a hough conversion figure by each possible radius of hough conversion, be called one deck.Can obtain a series of peak point like this.Judge that the iris edge is easy to make mistakes if only rely on high-high brightness.The restrictive condition that adds the implantation site in the screening peak point will effectively improve the accuracy of location.The brightness at i peak of j layer is I
Ij, be D to the distance of Fig. 2 bright pixel central area
Ij, the high-high brightness at all peaks is I
Max, be D to the bee-line of Fig. 2 bright pixel central area
MinThe basis for estimation at i peak is:
P wherein
IBe the weight of luminance standard, p
DIt is the weight of criterion distance.P in the work of this paper
I=0.3, p
D=0.7.Look for S
IjMinimum value can determine the circular center of circle and radius, thereby the location of finishing the edge.
Need not check to also have the radius of not judging in above-mentioned process, because the possible range of radius is known, all integer radiuses in this scope all will be done Hough transformation.
The detection of last palpebra inferior also is to use the hough conversion to carry out circular search, and different with the detection of iris outer edge is the standard of judging best Hough peak.Hough transformation can be known the center of circle and the radius of a circle, so said method at definite iris inward flange, has promptly just drawn the center of circle of pupil during pupil.Owing to also have the radian texture close with eyelid on the eyelid, so the position is a main criterion: nearest circular arc is an eyelid from the pupil center of circle in eyelid detects.
The inspection that also will position at last.Check that index has 4:
A) among the compute location result pupil with interior mean flow rate, if be higher than preset threshold then show that the pupil radius is looked for too greatly or eyelid has covered the pupil subregion;
B) calculate mean flow rate in the annulus of the outer certain radius of pupil region, if be lower than preset threshold then show that the pupil radius looks for too for a short time, the annulus of above-mentioned certain radius is generally the annulus of 1.0 times～1.3 times of pupil radiuses;
C) if the pupil location is correct, but iris outward flange center and inward flange off-centring surpass threshold value, then show outward flange location mistake;
D) area that palpebra inferior covers in the calculating accounts for the number percent of iris annulus area, and it is excessive to show then that above threshold value eyelid location mistake or eyelid cover iris region.
If these 4 indexs have one defective, will obtain locating the result of failure, prompting will be gathered iris image again and be positioned.
2. iris feature extracts and coding
Algorithm flow chart is as shown in Figure 5:
(51) eyelid part about people's eye pattern is got up as the noise region mark, and with its deletion;
(52) use affined transformation that iris region and noise region are transformed into rectangle, as described in (51), noise region is an eyelid part up and down.The meaning of (51) noise token being got up is to generate a binary image with former figure same size, and to be illustrated in the pixel of same position among the former figure be noise to white pixel on this figure.(52) use the radiation conversion former figure and above-mentioned noise binary picture need be transformed into rectangle respectively in;
(53) image of step (52) is done fast fourier transform, use log-gabor filtering to carry out feature extraction at frequency domain;
(54) do inverse fourier transform, the real part of getting image carries out binaryzation, and with the noise region deletion, gets feature coding to the end;
The part that eyelid in the iris image hides is removed, the iris portion that the location is found is carried out affined transformation and is obtained Imp then, simultaneously the eyelid part is also done affined transformation, generate the mask of a correspondence, then Imp is carried out log-Gabor filtering, and get its real part and carry out binaryzation, do with computing obtaining iris-encoding then with mask.
3. optical volume holographic is discerned secondary coding
The iris-encoding that feature extraction is obtained carries out secondary coding.Picture size behind the secondary coding is by the SLM resolution decision in the volume holographic image identification light path.Here claim that the input picture before the secondary coding is imin, the output image behind the secondary coding is imout.The pixel count of imout is bigger than imin's.A width among the corresponding imout of a pixel among the imin is 1 pixel, highly is the zone of 10 pixels, and this zone is called the secondary pixel.Width is the striped of 10 pixels so the delegation's correspondence among the imin just becomes up and down in imout.At the characteristics of optical volume holographic image identification, reduce vertically harassing between the pixel, the fringe spacing among the imout is 15 pixels, and the pixel among the imin is aligned to the two ends up and down of imout, the pixel of imin is not arranged in the centre of imout.
Experimental results show that above-mentioned secondary coding method harassing between in optical volume holographic image identification, can lowering between the pixel, improve discrimination.Adopt the iris database CASI of the Chinese Academy of Sciences version2 device1 in 37 people's iris image as experimental subjects.Discern with the optical volume holographic image recognition methods, the image recognition rate of no secondary coding is 91%, and the discrimination behind the secondary coding is 100%.As shown in Figure 6, be original eye image, employing figure source be CASI database version2 device1 0055 0055_005.bmp; Fig. 7 carries out the design sketch of Iris Location for adopting the present invention.
Fig. 8 is the Iris Location process flow diagram, and the left side is a positioning flow, and the right is the design sketch of corresponding step.The method that Iris Location adopts morphology and hough conversion to combine is sought the outer edge and the last palpebra inferior of iris.Earlier iris image is carried out morphologic filtering and obtain positioning image Imr, remove unwanted details such as reflective spot and eyelashes, and then carry out binaryzation, find out the approximate region that near picture centre low brightness area is pupil, find out this regional barycenter C and its horizontal vertical width of this area measure then and get the approximate diameter d of both mean values again as pupil.Imr is scaled, and choosing then with C is the center, and diameter is the target area of the border circular areas of 3d as iris outward flange location.Use this part regional edge of canny operator extraction Imr, other parts mask earlier, obtain Imo, choose certain radius region of search with d as reference then and use the hough conversion to seek the outward flange of iris to Imo.Can reduce the quantity of marginal point with Imo as the object of hough conversion, reduce the time of computing, shield other noises simultaneously, increase the accuracy of location.Finding the amplification that Imo is suitable in proportion afterwards of iris outward flange, is to carry out the hough conversion with reference to delimiting certain scope as iris inward flange search radius then with d, seeks the iris inward flange.Doing the search precision that can guarantee inward flange like this is consistent with outward flange.The certain zone of Imo the first half is intercepted for reference according to iris outside radius, the certain multiple with iris outward flange radius is that search radius uses the hough conversion to seek the upper eyelid then.With Imo Rotate 180 degree, intercept out a zone of containing eyelid and make the search palpebra inferior that uses the same method then.Fig. 9 is the output map imout behind the secondary coding.
During specific coding, using matlab to write the algorithm compilation of source code becomes dynamic link libraries to call the processing iris image for C++, with CASI database version2 37 human iris's images in the device1 file be experimental subjects, carry out doing optical volume holographic iris identification after the image pre-treatment, discrimination is 100%, and average every width of cloth figure processing time is 3.6 seconds.
Claims (7)
1. an image preprocessing method that is used for optical volume holographic iris identification is handled the iris image of gathering, and it is characterized in that described method comprises:
(11) iris image of gathering is carried out the location of iris region, determine palpebra inferior on iris outer edge and the human eye;
(12) determine iris region after, iris is carried out feature extraction and coding;
(13) data behind the coding are carried out optical volume holographic identification secondary coding.
2. method according to claim 1 is characterized in that, the concrete steps of described step (11) are as follows:
At first carry out iris outer edge location, concrete steps are as follows:
(211) iris image of gathering is scaled;
(212) carry out morphologic filtering;
(213) be near minimum value and position near the center of image for according to image binaryzation according to brightness;
(214), determine the region of search and the search radius of iris outward flange and inward flange according to the size of pupil region and the statistical relationship between the iris radius;
(215) image after the morphologic filtering described in (212) is used canny operator extraction edge, obtain outline map, and the marginal point beyond the iris outward flange region of search removed, all possible radius is carried out Hough transformation, choose three brightness largest peaks among the Hough transformation figure that each possibility radius obtains as the best Hough of candidate peak;
(216) in the best Hough of all candidates peak, choose the peak point that meets minimum basis for estimation;
(217) after finding the outward flange radius, outline map described in (215) is amplified, and the marginal point beyond the iris inward flange region of search removed, all possible radius is carried out Hough transformation, choose three brightness largest peaks among the Hough transformation figure that each possibility radius obtains as the best Hough of candidate peak, in the best Hough of all candidates peaks, choose the peak point that meets minimum basis for estimation;
Carry out palpebra inferior location on the human eye, concrete steps are as follows:
(221) adopt Hough transformation to carry out the circle search, nearest circular arc is the upper eyelid from the pupil center of circle;
(222) image is carried out 180 degree rotations;
(223) adopt Hough transformation to carry out the circle search, nearest circular arc is a palpebra inferior from the pupil center of circle
(224) obtain positioning result.
3. method according to claim 2 is characterized in that, described step (216) and (217) described basis for estimation are judged according to following mode:
The brightness of determining i peak value of j possibility radius is I
Ij, this peak value is D to the distance of pupil center
Ij, the high-high brightness of all peak values is I
Max, be D to the bee-line of pupil center
Min, the basis for estimation S at i peak then
IjFor:
P wherein
IBe the weight of luminance standard, p
DIt is the weight of criterion distance.
4. according to claim 2 or 3 described methods, it is characterized in that, the positioning result that above-mentioned steps (224) obtains is checked, if the standard of not meeting, think that then original iris image shooting quality is not good, the prompting of iris image acquiring is carried out in output again, and the described concrete steps that positioning result is checked are as follows:
(41) among the compute location result pupil with interior mean flow rate, if be higher than preset threshold then export the prompting of carrying out iris image acquiring again, otherwise execution in step (42);
(42) calculate mean flow rate in the annulus of the outer certain radius of pupil region, if be lower than preset threshold then export the prompting of carrying out iris image acquiring again, otherwise execution in step (43);
(43) check whether iris outward flange center and inward flange off-centring surpass threshold value, if surpass threshold value then export the prompting of carrying out iris image acquiring again, otherwise execution in step (44);
(44) area that palpebra inferior covers in the calculating accounts for the number percent of iris annulus area, surpasses threshold value and then exports the prompting of carrying out iris image acquiring again.
5. method according to claim 1 is characterized in that, the concrete steps of described step (12) are as follows:
(51) eyelid part about people's eye pattern is got up as the noise region mark, and with its deletion;
(52) use affined transformation that iris region and noise region are transformed into rectangle;
(53) image of step (52) is done fast fourier transform, use log-gabor filtering to carry out feature extraction at frequency domain;
(54) do inverse fourier transform, the real part of getting image carries out binaryzation, and with the noise region deletion, gets feature coding to the end;
6. method according to claim 1 is characterized in that, the concrete steps of described step (13) are as follows:
(61) each pixel of the image that step (12) coding is obtained is mapped among the secondary coding figure, and mapping method is that the corresponding width of a pixel on the former figure is 1 pixel, highly is the zone more than 1 pixel, and this zone is called the secondary pixel.The secondary pixel is arranged in the middle of image from the two ends up and down of image.Keep about 1/3 zone line of secondary coding figure not have the secondary pixel after having arranged all pixels.；
(62) line-spacing with the image that obtains in the step (61) expands to more than 1 pixel.
7. method according to claim 6 is characterized in that:
Each pixel of the image that described step (61) obtains step (12) coding, being mapped to width is 1 pixel, highly is the zone of 10～15 pixels;
Described step (62) expands the line-spacing of the image that obtains in the step (61) to 15～20 pixels.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201010191412.XA CN101866420B (en) | 2010-05-28 | 2010-05-28 | Image preprocessing method for optical volume holographic iris recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201010191412.XA CN101866420B (en) | 2010-05-28 | 2010-05-28 | Image preprocessing method for optical volume holographic iris recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101866420A true CN101866420A (en) | 2010-10-20 |
| CN101866420B CN101866420B (en) | 2014-06-04 |
Family
ID=42958141
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201010191412.XA Expired - Fee Related CN101866420B (en) | 2010-05-28 | 2010-05-28 | Image preprocessing method for optical volume holographic iris recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101866420B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107533643A (en) * | 2015-04-08 | 2018-01-02 | 韦夫弗朗特生物测定技术有限公司 | Multi-biological CMA |
| CN107844736A (en) * | 2016-09-19 | 2018-03-27 | 北京眼神科技有限公司 | iris locating method and device |
| CN109190447A (en) * | 2018-07-06 | 2019-01-11 | 深圳虹识技术有限公司 | A kind of iris identification method and equipment based on chip |
| CN110276229A (en) * | 2018-03-14 | 2019-09-24 | 京东方科技集团股份有限公司 | Target object regional center localization method and device |
| CN110680275A (en) * | 2019-10-21 | 2020-01-14 | 徐明娜 | Binocular multispectral pupil light reflex quantitative measuring instrument |
| WO2020019286A1 (en) * | 2018-07-27 | 2020-01-30 | 高雄医学大学 | Blepharoptosis detection method and system |
| CN113287298A (en) * | 2019-01-30 | 2021-08-20 | Jvc建伍株式会社 | Image processing device, image processing method, and image processing program |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2005109311A2 (en) * | 2004-04-26 | 2005-11-17 | Graphic Security Systems Corporation | System and method for decoding digital encoded images |
| CN101416407A (en) * | 2003-08-04 | 2009-04-22 | 霍洛威夫公司 | Enhanced holographic communications apparatus and method |
-
2010
- 2010-05-28 CN CN201010191412.XA patent/CN101866420B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101416407A (en) * | 2003-08-04 | 2009-04-22 | 霍洛威夫公司 | Enhanced holographic communications apparatus and method |
| WO2005109311A2 (en) * | 2004-04-26 | 2005-11-17 | Graphic Security Systems Corporation | System and method for decoding digital encoded images |
Non-Patent Citations (3)
| Title |
|---|
| 《中国激光》 20020430 周雁 等 基于体全息图像库的模式识别算法 第29卷, 第4期 2 * |
| 《光电工程》 20070531 黄欢 等 基于光学体全息和小波包分解的虹膜识别实现 第34卷, 第5期 2 * |
| 《压电与声光》 20090228 孟凡伟 等 基于小波变换的体全息相关识别系统 第31卷, 第1期 2 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107533643A (en) * | 2015-04-08 | 2018-01-02 | 韦夫弗朗特生物测定技术有限公司 | Multi-biological CMA |
| CN107844736A (en) * | 2016-09-19 | 2018-03-27 | 北京眼神科技有限公司 | iris locating method and device |
| CN107844736B (en) * | 2016-09-19 | 2021-01-01 | 北京眼神科技有限公司 | Iris positioning method and device |
| CN110276229A (en) * | 2018-03-14 | 2019-09-24 | 京东方科技集团股份有限公司 | Target object regional center localization method and device |
| CN109190447A (en) * | 2018-07-06 | 2019-01-11 | 深圳虹识技术有限公司 | A kind of iris identification method and equipment based on chip |
| WO2020019286A1 (en) * | 2018-07-27 | 2020-01-30 | 高雄医学大学 | Blepharoptosis detection method and system |
| CN113287298A (en) * | 2019-01-30 | 2021-08-20 | Jvc建伍株式会社 | Image processing device, image processing method, and image processing program |
| CN113287298B (en) * | 2019-01-30 | 2023-05-02 | Jvc建伍株式会社 | Image processing device, image processing method, and storage medium |
| CN110680275A (en) * | 2019-10-21 | 2020-01-14 | 徐明娜 | Binocular multispectral pupil light reflex quantitative measuring instrument |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101866420B (en) | 2014-06-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9235762B2 (en) | Iris data extraction | |
| CN101866420A (en) | Image preprocessing method for optical volume holographic iris recognition | |
| JP5107045B2 (en) | Method for identifying a pixel representing an iris in an image acquired for the eye | |
| Guan et al. | Accurate segmentation of partially overlapping cervical cells based on dynamic sparse contour searching and GVF snake model | |
| Frucci et al. | WIRE: Watershed based iris recognition | |
| JP2009523265A (en) | Method for extracting iris features in an image | |
| Abate et al. | BIRD: Watershed based iris detection for mobile devices | |
| CN1885314A (en) | Pre-processing method for iris image | |
| JP2007188504A (en) | Method for filtering pixel intensity in image | |
| Panchal et al. | An algorithm for retinal feature extraction using hybrid approach | |
| AlShemmary | Towards accurate pupil detection based on morphology and Hough transform | |
| Xu et al. | Improving the performance of iris recogniton system using eyelids and eyelashes detection and iris image enhancement | |
| KR101523765B1 (en) | Enhanced Method for Detecting Iris from Smartphone Images in Real-Time | |
| KR20030066512A (en) | Iris Recognition System Robust to noises | |
| CN105631816B (en) | A kind of iris image noise classification detection method | |
| CN106778499A (en) | A kind of method of quick positioning people's eye iris during iris capturing | |
| CN110516565A (en) | A kind of sea ship recognition methods based on Zernike and SVM | |
| CN108230306A (en) | Eyeground color picture blood vessel and arteriovenous recognition methods | |
| Ahmed et al. | Retina based biometric authentication using phase congruency | |
| Soares et al. | Exudates dynamic detection in retinal fundus images based on the noise map distribution | |
| Frucci et al. | Idem: Iris detection on mobile devices | |
| Nigam et al. | Iris classification based on its quality | |
| Zaim et al. | A robust and accurate segmentation of iris images using optimal partitioning | |
| WO2015103953A1 (en) | Method and device for extracting iris image image under condition of non-uniform illumination | |
| Luangruangrong et al. | Optic disc localization in complicated environment of retinal image using circular-like estimation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20140604 Termination date: 20200528 |