CN109389033A - A kind of novel pupil method for rapidly positioning - Google Patents
A kind of novel pupil method for rapidly positioning Download PDFInfo
- Publication number
- CN109389033A CN109389033A CN201810987673.9A CN201810987673A CN109389033A CN 109389033 A CN109389033 A CN 109389033A CN 201810987673 A CN201810987673 A CN 201810987673A CN 109389033 A CN109389033 A CN 109389033A
- Authority
- CN
- China
- Prior art keywords
- connected region
- region
- pupil
- pixels
- circumscribed circle
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/18—Eye characteristics, e.g. of the iris
- G06V40/19—Sensors therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Ophthalmology & Optometry (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of novel pupil method for rapidly positioning, comprising the following steps: (1) connected region in the iris image after binaryzation is marked；(2) number of pixels of each connected region is calculated；(3) using the point on the four direction of each connected region outermost, the window for making minimum circumscribed circle to the region is limited, and calculation window area；(4) selection number of pixels threshold value carries out preliminary screening to connected region；(5) number of pixels of connected region and the ratio of connected region minimum circumscribed circle window area are calculated, using the maximum connected region of ratio as the connected region of pupil.The invention proposes a kind of improved Iris-orientation Algorithm, the accuracy rate and efficiency of iris recognition under non-ideality are effectively improved.The advantage for searching for largest connected region, which is that, automatically removes noise spot according to the gray feature of pupil, and when avoiding the fitting of iris inner boundary, the extraction of invalid marginal point is strayed into bring error with what is illegally put.
Description
Technical field
The present invention relates to field of image processings, more particularly to a kind of novel pupil method for rapidly positioning.
Background technique
With the fast development of society and science and technology, the safety of information shows unprecedented importance.Traditional identity
Discrimination method such as identity tag article and identity tag knowledge are just gradually being known by biological characteristic due to its intrinsic defect and loophole
Replaced other technology.The biometrics identification technology of several classics currently used for identity identification specifically includes that recognition of face, sound
Sound identification, fingerprint recognition, personal recognition, iris recognition etc..The feature that wherein iris recognition technology has by iris is stable, anti-fake
Property non-contact characteristic high, that outstanding biological nature and the acquisition and detection mode such as be not easy to steal, identify it in numerous identity
Show one's talent in technology, and become mostly important, safe, accurate authentication techniques, has broad application prospects and again
The academic research wanted.It is most suggested early in the eighties in 19th century using the imagination that iris carries out identity identification, experienced nearest two
The development of more than ten years, iris recognition technology just have the development of leap and are widely applied.The use of iris recognition technology also makes
The security level for obtaining application scenes is greatly improved.One complete iris authentication system includes iris image
Acquisition, four pretreatment, feature extraction and match cognization parts.Wherein iris preprocessing is the pass in iris recognition
Key link and foundation, the quality of pre-processed results directly affects subsequent all operations, and then influences the knowledge of whole system
Other performance.
In the pretreatment stage of iris recognition, the positioning of pupil be the beginning of whole flow process, efficiency and accuracy for
Subsequent processing and identification play a significant role, and especially under conditions of iris image acquiring condition is bad, how quickly to remove
It is heterogeneous, pupil is accurately positioned and is very important a ring.
In the prior art, empirical value is mostly used to remove the iris image of binaryzation the Pupil diameter aspect of heterogeneous image
Noise spot.It is low that this will lead to effect of the localization method of iris authentication system when encountering more heterogeneous iris images.
Summary of the invention
In view of the above shortcomings of the prior art, the present invention provides a kind of novel pupil method for rapidly positioning, Neng Gou
In the preprocessing process of iris recognition, avoid usually requiring to remove noise spot to the iris image after binaryzation using priori knowledge
Process, position to fast and stable pupil region, and then determine iris inner and outer boundary, improve the standard of Algorithm of Iris Recognition on the whole
True property and efficiency.
To achieve the goals above, the invention is realized by the following technical scheme:
A kind of novel pupil method for rapidly positioning, comprising the following steps:
(1) connected region in the iris image after binaryzation is marked:
A. foreground image is marked after binaryzation with 1, and background image is labeled as 0；
B. original image is traversed, when encountering foreground image, judges whether foreground image p (i, j) is labeled, wherein p is
Original image, i, j respectively represent the footmark of row and column；If pixel p (i, j) is not labeled, its coordinate value is saved to queue
In, and the pixel is marked in the respective coordinates position of label matrix；
C. the eight neighborhood of p (i, j) is scanned for, when encountering new not labeled foreground pixel point, is then sat
Scale value is fallen in lines, and is marked in label matrix；Wherein new foreground pixel point coordinate is p (i+1, j)；
D. after the completion of eight neighborhood search label, p (i, j) is fallen out, column head is p (i+1, j) at this time, carries out step c again
The eight neighborhood search and marking operation；
E. after the completion of a connected component labeling, label counting adds 1, empties queue, carries out time of step b~d again
Operation is gone through, new connected region is marked；
(2) number of pixels of each connected region is calculated: after step (1) completes the label of connected region, to each
Number of pixels in a connected region adds up；
(3) using the point on the four direction of each connected region outermost, make the window of minimum circumscribed circle to the region
It limits, and calculation window area:
A. the point on the positive and negative 45 degree of angles of four direction of each connected region outermost is found, and with least square method to this
Make the window of a minimum circumscribed circle in region；
B. above-mentioned window area is calculated, i.e., the number of pixel is cumulative in the window, and using the minimum circumscribed circle as sentencing
This connected region of breaking whether be pupil region important evidence；
(4) selection number of pixels threshold value carries out preliminary screening to connected region: according to step (3) different connections calculated
The number of pixels of the circumscribed circle in region selects number of pixels threshold value to carry out preliminary screening to connected region, reduces the screening of pupil
Range；
(5) number of pixels of connected region and the ratio of connected region minimum circumscribed circle window area are calculated, most by ratio
Connected region of the big connected region as pupil: pupil is approximate circle region, and the connected region window of selection is circumscribed circle；
If calculating the ratio of the sum of number of pixels of different connected regions minimum circumscribed circle window area corresponding with connected region, show
Maximum ratio so will be obtained with round immediate pupil, can determine that the maximum connected region of ratio is pupil region；
Before being fitted to pupil boundary, Canny operator extraction edge is used first, then the marginal point of extraction is used minimum
Two methods for multiplying fitting are accurately positioned pupil boundary and provide the center of circle (x, y) and the radius r of inner circle.
The beneficial effects of the present invention are: effectively improving unreasonably the invention proposes a kind of improved Iris-orientation Algorithm
The accuracy rate and efficiency of iris recognition in the case of thinking.The advantage for searching for largest connected region is that gray feature according to pupil
Noise spot is automatically removed, when avoiding the fitting of iris inner boundary, the extraction of invalid marginal point is strayed into bring with what is illegally put
Error.The present invention can in the preprocessing process of iris recognition, avoid usually require using priori knowledge to binaryzation after
Iris image removes the process of noise spot, positions to fast and stable pupil region, and then determine iris inner and outer boundary, mentions on the whole
The accuracy and efficiency of high Algorithm of Iris Recognition.
Detailed description of the invention
In conjunction with attached drawing, and by reference to following detailed description, it will more easily have more complete understanding to the present invention
And its adjoint advantage and feature is more easily to understand, in which:
Fig. 1 is flow chart of the invention；
Fig. 2 is the iris image provided in the embodiment of the present invention；
Fig. 3 is the iris image in the embodiment of the present invention after binaryzation；
Fig. 4 is the result figure of connected component labeling in the embodiment of the present invention；
Fig. 5 is the result figure of pupil region in the embodiment of the present invention；
Fig. 6 is the result figure of Pupil diameter in the embodiment of the present invention.
Specific embodiment
The following further describes the present invention with reference to the drawings.
As shown in figures 1 to 6, the novel pupil method for rapidly positioning of one kind of the present invention, comprising the following steps:
(1) to Fig. 2 of input Otsu method binaryzation, Fig. 3 is obtained, then connected region is carried out to Fig. 3 and is marked, is marked
The method of note is as follows:
A. foreground image is marked after binaryzation with 1, and background image is labeled as 0；
B. original image is traversed, when encountering foreground image, judges that (wherein p is original image, i, j to foreground image p (i, j)
Respectively represent the footmark of row and column) whether it is labeled, if pixel p (i, j) is not labeled, its coordinate value is saved to queue
In, and the pixel is marked in the respective coordinates position of label matrix；
C. the eight neighborhood of p (i, j) is scanned for, when encountering new not labeled foreground pixel point, is then sat
Scale value is fallen in lines, and is marked in label matrix, and new foreground point coordinate is p (i+1, j)；
D. after the completion of eight neighborhood search label, p (i, j) is fallen out, column head is p (i+1, j) at this time, carries out such as step again
The search of eight neighborhood described in c and marking operation；
E. after the completion of a connected component labeling, label counting adds 1, empties queue, carries out the traversal of step b-d again
Deng operation, new connected region is marked；
After the completion of step a to e, obtaining different connected regions as shown in Figure 4 is indicated, is outlined with different red blocks
Part, although some red blocks are bigger, as shown in figure 3, human eye is not easy caused by observation in practice because eyelashes region is long and narrow.
(2) number of pixels of each connected region is calculated, i.e., after the label of step (1) completion connected region, to each
Number of pixels in a connected region adds up；
(3) using the point on the positive and negative 45 degree of angles of four direction of each connected region outermost, which is made minimum outer
It connects round window to limit, and calculation window area:
A. the point on the positive and negative 45 degree of angles of four direction of each connected region outermost is found, and with least square method to this
Make the window of a minimum circumscribed circle in region；
B. above-mentioned window area is calculated, i.e., the number of pixel is cumulative in the window, and using the minimum circumscribed circle as sentencing
This connected region of breaking whether be pupil region important evidence；
(4) according to the number of pixels of the circumscribed circle of step (3) different connected regions calculated, number of pixels threshold value is selected
Preliminary screening is carried out to connected region, reduces the screening range of pupil.In the example shown in Fig. 2, threshold value 2500, this threshold value
The 25% of number of pixels in about largest connected region；
(5) pupil is approximate circle region, and the connected region window that we select is circumscribed circle；If calculating different connections
The ratio of the sum of the number of pixels in region minimum circumscribed circle window area corresponding with connected region, it is clear that immediate with circle
Pupil will obtain maximum ratio, can determine the maximum connected region of ratio be pupil region, as a result as shown in figure 5,
Before being fitted to pupil boundary, Canny operator extraction edge is used first, and minimum two then is used to the marginal point of extraction
The method for multiplying fitting is accurately positioned pupil boundary and provides the center of circle (x, y) and the radius r of inner circle；The result of Pupil diameter such as Fig. 6
It is shown.
The present invention is not limited to above-mentioned preferred forms, anyone can show that other are various under the inspiration of the present invention
The invention of form, however, make any variation in its shape or structure, it is all that there is skill identical or similar to the present application
Art scheme, is within the scope of the present invention.
Claims (1)
1. a kind of novel pupil method for rapidly positioning, which comprises the following steps:
(1) connected region in the iris image after binaryzation is marked:
A. foreground image is marked after binaryzation with 1, and background image is labeled as 0；
B. original image is traversed, when encountering foreground image, judges whether foreground image p (i, j) is labeled, wherein p is original image
Picture, i, j respectively represent the footmark of row and column；If pixel p (i, j) is not labeled, its coordinate value is saved into queue, and
The pixel is marked in the respective coordinates position of label matrix；
C. the eight neighborhood of p (i, j) is scanned for, when encountering new not labeled foreground pixel point, then by its coordinate value
Fall in lines, and is marked in label matrix；Wherein new foreground pixel point coordinate is p (i+1, j)；
D. after the completion of eight neighborhood search label, p (i, j) is fallen out, column head is p (i+1, j) at this time, is carried out described in step c again
Eight neighborhood search and marking operation；
E. after the completion of a connected component labeling, label counting adds 1, empties queue, carries out the traversal behaviour of step b~d again
Make, marks new connected region；
(2) number of pixels of each connected region is calculated: after step (1) completes the label of connected region, to each company
Number of pixels in logical region adds up；
(3) using the point on the four direction of each connected region outermost, the window for making minimum circumscribed circle to the region is limited,
And calculation window area:
A. the point on the positive and negative 45 degree of angles of four direction of each connected region outermost is found, and with least square method to the region
Make the window of a minimum circumscribed circle；
B. above-mentioned window area is calculated, i.e., the number of pixel is cumulative in the window, and using the minimum circumscribed circle as judging this
Connected region whether be pupil region important evidence；
(4) selection number of pixels threshold value carries out preliminary screening to connected region: according to step (3) different connected regions calculated
Circumscribed circle number of pixels, select number of pixels threshold value to connected region carry out preliminary screening, reduce the screening range of pupil；
(5) number of pixels of connected region and the ratio of connected region minimum circumscribed circle window area are calculated, ratio is maximum
Connected region of the connected region as pupil: pupil is approximate circle region, and the connected region window of selection is circumscribed circle；If
Calculate the ratio of the sum of number of pixels of different connected regions minimum circumscribed circle window area corresponding with connected region, it is clear that with
Round immediate pupil will obtain maximum ratio, can determine that the maximum connected region of ratio is pupil region；Right
Before pupil boundary is fitted, Canny operator extraction edge is used first, and least square then is used to the marginal point of extraction
The method of fitting is accurately positioned pupil boundary and provides the center of circle (x, y) and the radius r of inner circle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810987673.9A CN109389033B (en) | 2018-08-28 | 2018-08-28 | Novel pupil rapid positioning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810987673.9A CN109389033B (en) | 2018-08-28 | 2018-08-28 | Novel pupil rapid positioning method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109389033A true CN109389033A (en) | 2019-02-26 |
| CN109389033B CN109389033B (en) | 2022-02-11 |
Family
ID=65418431
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810987673.9A Active CN109389033B (en) | 2018-08-28 | 2018-08-28 | Novel pupil rapid positioning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109389033B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109854964A (en) * | 2019-03-29 | 2019-06-07 | 沈阳天眼智云信息科技有限公司 | Steam leakage positioning system and method based on binocular vision |
| CN111476795A (en) * | 2020-02-27 | 2020-07-31 | 浙江工业大学 | Binary icon notation method based on breadth-first search |
| CN112162629A (en) * | 2020-09-11 | 2021-01-01 | 天津科技大学 | Real-time pupil positioning method based on circumscribed rectangle |
| CN112434675A (en) * | 2021-01-26 | 2021-03-02 | 西南石油大学 | Pupil positioning method for global self-adaptive optimization parameters |
| CN115601825A (en) * | 2022-10-25 | 2023-01-13 | 扬州市职业大学(扬州开放大学)（Cn） | Method for evaluating reading capability based on visual positioning technology |
| CN116740068A (en) * | 2023-08-15 | 2023-09-12 | 贵州毅丹恒瑞医药科技有限公司 | Intelligent navigation system for cataract surgery |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080273763A1 (en) * | 2007-04-26 | 2008-11-06 | Stmicroelectronics Rousset Sas | Method and device for locating a human iris in an eye image |
| CN107844736A (en) * | 2016-09-19 | 2018-03-27 | 北京眼神科技有限公司 | iris locating method and device |
| CN108171201A (en) * | 2018-01-17 | 2018-06-15 | 山东大学 | Eyelashes rapid detection method based on gray scale morphology |
-
2018
- 2018-08-28 CN CN201810987673.9A patent/CN109389033B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080273763A1 (en) * | 2007-04-26 | 2008-11-06 | Stmicroelectronics Rousset Sas | Method and device for locating a human iris in an eye image |
| CN107844736A (en) * | 2016-09-19 | 2018-03-27 | 北京眼神科技有限公司 | iris locating method and device |
| CN108171201A (en) * | 2018-01-17 | 2018-06-15 | 山东大学 | Eyelashes rapid detection method based on gray scale morphology |
Non-Patent Citations (1)
| Title |
|---|
| 张仁彦等: "一种基于区域标记的虹膜内边缘定位新算法", 《海军工程大学学报》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109854964A (en) * | 2019-03-29 | 2019-06-07 | 沈阳天眼智云信息科技有限公司 | Steam leakage positioning system and method based on binocular vision |
| CN109854964B (en) * | 2019-03-29 | 2021-03-19 | 沈阳天眼智云信息科技有限公司 | Steam leakage positioning system and method based on binocular vision |
| CN111476795A (en) * | 2020-02-27 | 2020-07-31 | 浙江工业大学 | Binary icon notation method based on breadth-first search |
| CN112162629A (en) * | 2020-09-11 | 2021-01-01 | 天津科技大学 | Real-time pupil positioning method based on circumscribed rectangle |
| CN112434675A (en) * | 2021-01-26 | 2021-03-02 | 西南石油大学 | Pupil positioning method for global self-adaptive optimization parameters |
| CN115601825A (en) * | 2022-10-25 | 2023-01-13 | 扬州市职业大学(扬州开放大学)（Cn） | Method for evaluating reading capability based on visual positioning technology |
| CN115601825B (en) * | 2022-10-25 | 2023-09-19 | 扬州市职业大学(扬州开放大学) | Method for evaluating reading ability based on visual positioning technology |
| CN116740068A (en) * | 2023-08-15 | 2023-09-12 | 贵州毅丹恒瑞医药科技有限公司 | Intelligent navigation system for cataract surgery |
| CN116740068B (en) * | 2023-08-15 | 2023-10-10 | 贵州毅丹恒瑞医药科技有限公司 | Intelligent navigation system for cataract surgery |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109389033B (en) | 2022-02-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109389033A (en) | A kind of novel pupil method for rapidly positioning | |
| CN108982508B (en) | Plastic package IC chip defect detection method based on feature template matching and deep learning | |
| CN103870808B (en) | Finger vein identification method | |
| WO2018072233A1 (en) | Method and system for vehicle tag detection and recognition based on selective search algorithm | |
| CN100373397C (en) | Pre-processing method for iris image | |
| CN102704215B (en) | Automatic cutting method of embroidery cloth based on combination of DST file parsing and machine vision | |
| CN106600600A (en) | Wafer defect detection method based on characteristic matching | |
| CN107230203A (en) | Casting defect recognition methods based on human eye vision attention mechanism | |
| CN104700092A (en) | Small-character number identification method based on template and feature matching | |
| CN104951940A (en) | Mobile payment verification method based on palmprint recognition | |
| CN103218605A (en) | Quick eye locating method based on integral projection and edge detection | |
| CN109540925A (en) | Complicated ceramic tile surface defect inspection method based on difference shadow method and local variance measurement operator | |
| CN109409227A (en) | A kind of finger vena plot quality appraisal procedure and its device based on multichannel CNN | |
| CN114549446A (en) | Cylinder sleeve defect mark detection method based on deep learning | |
| WO2013075295A1 (en) | Clothing identification method and system for low-resolution video | |
| Lili et al. | The algorithm of iris image preprocessing | |
| CN109724988A (en) | A kind of pcb board defect positioning method based on multi-template matching | |
| CN106778499B (en) | Method for rapidly positioning human iris in iris acquisition process | |
| CN101425140A (en) | Encephalic angioma image recognizing and detecting method based on framework characteristic | |
| Huang et al. | Retinal vessel segmentation using simple SPCNN model and line connector | |
| CN111899272B (en) | Fundus image blood vessel segmentation method based on coupling neural network and line connector | |
| Su et al. | Iris location based on regional property and iterative searching | |
| CN113723314A (en) | Sugarcane stem node identification method based on YOLOv3 algorithm | |
| CN106372593B (en) | Optic disk area positioning method based on vascular convergence | |
| CN115937085B (en) | Nuclear cataract image processing method based on neural network learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |