CN110781747A - Eyelash occlusion area pre-detection method based on coefficient of variation - Google Patents
Eyelash occlusion area pre-detection method based on coefficient of variation Download PDFInfo
- Publication number
- CN110781747A CN110781747A CN201910899748.2A CN201910899748A CN110781747A CN 110781747 A CN110781747 A CN 110781747A CN 201910899748 A CN201910899748 A CN 201910899748A CN 110781747 A CN110781747 A CN 110781747A
- Authority
- CN
- China
- Prior art keywords
- iris
- area
- block
- eyelashes
- shielded
- 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
- 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
- G06V40/193—Preprocessing; Feature extraction
-
- 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
- G06V40/197—Matching; Classification
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Ophthalmology & Optometry (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method for pre-detecting an eyelash occlusion area based on a coefficient of variation. The method comprises the steps of firstly partitioning upper and lower regions of an iris, then calculating the variation coefficient of the upper and lower blocks which are symmetrical about the center of the iris, judging whether the blocks on the iris are shielded by eyelashes or not by comparing the variation coefficients of the upper and lower blocks, judging whether each block on the iris is shielded by eyelashes or not by comparing the gray distribution difference of the upper and lower blocks of the iris, and carrying out region integration on the blocks on the iris which are shielded by eyelashes to obtain an eyelash shielding region. The method of the invention is used for predetermining the distribution range of eyelashes in the iris area, thus shortening the search range of later-stage eyelash detection, improving the detection efficiency and reducing the false eyelash detection rate.
Description
Technical Field
The invention belongs to the field of biological feature identification and information security, and particularly relates to a method for pre-detecting an eyelash occlusion area based on a coefficient of variation.
Background
The development of the iris recognition technology forms a complete framework system, but the key factor for determining and influencing the iris recognition performance is the acquisition quality of the iris. Under the state that human eyes are naturally opened, due to physiological structure, iris collection is difficult to avoid the influence of eyelash shading, and has diversity, so that eyelash detection is the core problem of iris identification performance limit improvement or iris flooding detection.
At present, the relevant research aiming at eyelash detection is mostly to realize eyelash detection through threshold segmentation or morphological knowledge on the whole iris area. Mask uses the gray difference between eyelashes and surrounding irises to set a threshold value for achieving the purpose of eyelash detection. (mask libor. recognition of Human Iris Patterns for biometrical identification [ D ].2003.) Oedist, etc. by using morphological knowledge, obtain Iris image with histogram having segmentation characteristic through gray-scale opening operation, and detect eyelash through binarization. (Leiye, Luchenhong, Luchaoyang. eyelid and eyelash occlusion detection for iris recognition [ J ] computer aided design and graphics newspaper.) Yangxiang adopts a self-adaptive double-threshold segmentation method to detect eyelashes, and flexibly adjusts the threshold according to the illumination conditions of different images. (study on Yangxingsheng iris image preprocessing and feature coding methods [ D ] 2016), all the methods can realize eyelash detection to a certain extent, but because eyelash regions are not determined in advance, the later search range is too large, the detection efficiency is low, and eyelash false detection is serious.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a method for pre-detecting an eyelash occlusion area based on a coefficient of variation. The method comprises the steps of firstly partitioning upper and lower iris areas, then adopting the coefficient of variation as a criterion, judging whether each iris partition is shielded by eyelashes or not by comparing the gray distribution difference of the upper and lower iris partition areas, and finally performing area integration on the partitions to obtain the eyelash shielding areas.
A method for pre-detecting an eyelash occlusion area based on a coefficient of variation comprises the following steps:
and (1) taking the center of the iris as an origin to perform equal-radian fan-shaped partitioning on the iris area.
And (2) judging whether each iris block is shielded by eyelashes or not, respectively calculating the variation coefficients of the upper and lower blocks which are symmetrical about the center of the iris circle, and if the variation coefficient of the upper block is larger than that of the lower block, and the difference value between the variation coefficient of the upper block and that of the lower block is larger than or equal to a set threshold Thr (Thr is larger than or equal to 0 and smaller than or equal to 0.15), the upper block is shielded by the eyelashes, and if the difference value is not larger than the set threshold Thr, the upper block is not shielded by the eyelashes.
Step (3) dividing the upper half of the iris into block areas I
1And integrating the partitioned areas internally shielded by the eyelashes to obtain an eyelash shielding area.
The method comprises the following specific steps:
dividing the iris into n (n is an even number) blocks by taking the center of the iris as an origin and theta radian (theta is more than or equal to 5 and less than or equal to 20) at intervals, and dividing the block into block areas S
i=[(i-1)×θ,i×θ]I ═ 1,2, …, n; upper half of iris block area I
1Including a block area S
iI1, 2, …, n/2, the inferior semi-iris block region I
2Including a block area S
i,i=n/2+1,n/2+2,…,n。
Step (2), for example, the specific method is as follows:
calculating blocks S on the iris
1With sub-iris blocks symmetrical about the center of the iris
The specific formula of the coefficient of variation of (a) is as follows; f (p, q) represents the pixel value of the pixel point at the p-th row and the q-th column in the block. N is a radical of
1Representing blocks S on the iris
1The number of the pixel points in the display screen,
representing sub-iris patches
The number of internal pixel points;
calculating S
1Mean value of inner gray level mu
1;
Calculating S
1Gray scale standard deviation V within a region
1:
Calculating S
1Coefficient of variation CV within a region
1;
The specific method comprises the following steps:
firstly, judging a block area S
1Whether or not it is shielded by eyelashes, when the area is divided into blocks
1When not shielded by eyelashes, judging the next block area S
2If the first partitioned area is shielded by eyelashes, repeating the steps until the first partitioned area shielded by eyelashes is detected, stopping judging, and marking the first partitioned area as S
T1(ii) a Then judging the block area S
n/2Whether or not it is shielded by eyelashes, when the area is divided into blocks
n/2When not shielded by eyelashes, judging the next block area S
n/2-1 whether it is obstructed by eyelashes, and so on, until the first blocked area obstructed by eyelashes is detected, the decision is stopped and it is marked as S
T2(ii) a Finally, the block area S
T1、S
T2And integrating the partitioned areas between the two to obtain an eyelash shading area.
The invention has the following beneficial effects:
the method solves the problems that the eyelash area is not determined in advance, so that the later searching range is too large, the detection efficiency is low, and the eyelash false detection condition is serious in the prior art. The method of the invention is used for predetermining the distribution range of eyelashes in the iris area, thus shortening the search range of later-stage eyelash detection, improving the detection efficiency and reducing the false eyelash detection rate.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings.
As shown in FIG. 1, the method of the present invention comprises the following steps:
a method for pre-detecting an eyelash occlusion area based on a coefficient of variation comprises the following steps:
taking the center of an iris circle as an origin, and carrying out equal-radian fan-shaped partitioning on the iris area:
dividing the iris into n (n is an even number) blocks by taking the center of the iris as an origin and theta radian (theta is more than or equal to 5 and less than or equal to 20) at intervals, and dividing the block into block areas S
i=[(i-1)×θ,i×θ]I ═ 1,2, …, n; upper half of iris block area I
1Including a block area S
iI1, 2, …, n/2, the inferior semi-iris block region I
2Including a block area S
i,i=n/2+1,n/2+2,…,n。
And (2) judging whether each iris block is shielded by eyelashes or not, respectively calculating the variation coefficients of the upper and lower blocks which are symmetrical about the center of the iris circle, and if the variation coefficient of the upper block is larger than that of the lower block, and the difference value between the variation coefficient of the upper block and that of the lower block is larger than or equal to a set threshold Thr (Thr is larger than or equal to 0 and smaller than or equal to 0.15), the upper block is shielded by the eyelashes, and if the difference value is not larger than the set threshold Thr, the upper block is not shielded by the eyelashes.
For example, the specific method is as follows:
calculating the iris upper partition S1 and the iris lower partition symmetric about the center of the iris
The specific formula of the coefficient of variation of (a) is as follows; f (p, q) represents the pixel value of the pixel point at the p-th row and the q-th column in the block. N is a radical of
1Representing blocks S on the iris
1Number of inner pixels, N
2I
1Representing sub-iris patches
The number of internal pixel points;
calculating S
1Mean value of inner gray level mu
1;
Calculating S
1Gray scale standard deviation V within a region
1:
Calculating S
1Coefficient of variation CV within a region
1;
Step (3) dividing the upper half of the iris into block areas I
1Integrating the blocked areas blocked by the eyelashes to obtain an eyelash blocking area:
firstly, judging a block area S
1Whether or not it is shielded by eyelashes, when the area is divided into blocks
1When not shielded by eyelashes, judging the next block area S
2If the first partitioned area is shielded by eyelashes, repeating the steps until the first partitioned area shielded by eyelashes is detected, stopping judging, and marking the first partitioned area as S
T1(ii) a Then judging the block area S
n/2Whether or not it is shielded by eyelashes, when the area is divided into blocks
n/2When not shielded by eyelashes, judging the next block area S
n/2-1 whether it is obstructed by eyelashes, and so on, until the first blocked area obstructed by eyelashes is detected, the decision is stopped and it is marked as S
T2(ii) a Finally, the block area S
T1、S
T2And integrating the partitioned areas between the two to obtain an eyelash shading area.
Claims (4)
1. A method for pre-detecting an eyelash occlusion area based on a coefficient of variation is characterized by comprising the following steps:
taking the center of an iris circle as an origin, and carrying out equal-radian fan-shaped partitioning on an iris area;
step (2), judging whether each iris upper block is shielded by eyelashes or not, respectively calculating the variation coefficients of the upper and lower blocks which are symmetrical about the center of the iris circle, and if the variation coefficient of the upper block is larger than that of the lower block, and the difference value between the variation coefficient of the upper block and that of the lower block is larger than or equal to a set threshold value Thr, (0-Thr is larger than or equal to 0.15), judging that the upper block is shielded by the eyelashes, and if the difference value is not larger than the set threshold value Thr, judging that the upper block is not shielded by the eyelashes;
step (3) dividing the upper half of the iris into block areasI
1And integrating the partitioned areas internally shielded by the eyelashes to obtain an eyelash shielding area.
2. The method for pre-detecting the eyelash occlusion area based on the coefficient of variation as claimed in claim 1, wherein the step (1) is as follows:
dividing the iris into n (n is an even number) blocks by taking the center of the iris as an origin and theta radian (theta is more than or equal to 5 and less than or equal to 20) at intervals, and dividing the block into block areas S
i=[(i-1)×θ,i×θ]I ═ 1,2, …, n; upper half of iris block area I
1Including a block area S
iI1, 2, …, n/2, the inferior semi-iris block region I
2Including a block area S
i,i=n/2+1,n/2+2,…,n。
3. The method for pre-detecting the eyelash occlusion area based on the coefficient of variation as claimed in claim 2, wherein the step (2) is as follows:
calculating blocks S on the iris
1With sub-iris blocks symmetrical about the center of the iris
The specific formula of the coefficient of variation of (a) is as follows; f (p, q) represents the pixel values of pixel points at the p-th row and the q-th column in the block; n is a radical of
1Representing blocks S on the iris
1Number of inner pixels, N
2I
1Representing sub-iris patches
The number of internal pixel points;
calculating S
1Mean value of inner gray level mu
1;
Calculating S
1Gray scale standard deviation V within a region
1:
Calculating S
1Coefficient of variation CV within a region
1;
4. The method for pre-detecting the eyelash occlusion area based on the coefficient of variation as claimed in claim 3, wherein the specific method of step (3) is as follows:
firstly, judging a block area S
1Whether or not it is shielded by eyelashes, when the area is divided into blocks
1When not shielded by eyelashes, judging the next block area S
2If the first partitioned area is shielded by eyelashes, repeating the steps until the first partitioned area shielded by eyelashes is detected, stopping judging, and marking the first partitioned area as S
T1(ii) a Then judging the block area S
n/2Whether or not it is shielded by eyelashes, when the area is divided into blocks
n/2When not shielded by eyelashes, judging the next block area S
n/2-1Whether the first partitioned area is shielded by the eyelashes or not is determined by analogy until the first partitioned area shielded by the eyelashes is detected, the judgment is stopped, and the first partitioned area is marked as S
T2(ii) a Finally, the block area S
T1、S
T2And integrating the partitioned areas between the two to obtain an eyelash shading area.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910899748.2A CN110781747B (en) | 2019-09-23 | 2019-09-23 | Eyelash occlusion area pre-detection method based on coefficient of variation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910899748.2A CN110781747B (en) | 2019-09-23 | 2019-09-23 | Eyelash occlusion area pre-detection method based on coefficient of variation |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110781747A true CN110781747A (en) | 2020-02-11 |
CN110781747B CN110781747B (en) | 2022-03-01 |
Family
ID=69383685
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910899748.2A Active CN110781747B (en) | 2019-09-23 | 2019-09-23 | Eyelash occlusion area pre-detection method based on coefficient of variation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110781747B (en) |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101154265A (en) * | 2006-09-29 | 2008-04-02 | 中国科学院自动化研究所 | Method for recognizing iris with matched characteristic and graph based on partial bianry mode |
CN101241550A (en) * | 2008-01-19 | 2008-08-13 | 电子科技大学中山学院 | Iris image quality judging method |
CN101447025A (en) * | 2008-12-30 | 2009-06-03 | 东南大学 | Method for identifying iris of large animals |
CN101539991A (en) * | 2008-03-20 | 2009-09-23 | 中国科学院自动化研究所 | Effective image-region detection and segmentation method for iris recognition |
CN105447450A (en) * | 2015-11-12 | 2016-03-30 | 北京天诚盛业科技有限公司 | Method and device for judging left iris and right iris in iris recognition |
CN106250810A (en) * | 2015-06-15 | 2016-12-21 | 摩福公司 | By iris identification, individuality is identified and/or the method for certification |
CN106326825A (en) * | 2015-08-26 | 2017-01-11 | 北京巴塔科技有限公司 | Iris edge positioning method |
CN108171201A (en) * | 2018-01-17 | 2018-06-15 | 山东大学 | Eyelashes rapid detection method based on gray scale morphology |
CN108312964A (en) * | 2018-03-21 | 2018-07-24 | 华南理工大学 | A kind of fatigue driving state identification early warning system and method |
CN110245626A (en) * | 2019-06-19 | 2019-09-17 | 北京万里红科技股份有限公司 | A method of accurately detecting eyelash image in iris image |
-
2019
- 2019-09-23 CN CN201910899748.2A patent/CN110781747B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101154265A (en) * | 2006-09-29 | 2008-04-02 | 中国科学院自动化研究所 | Method for recognizing iris with matched characteristic and graph based on partial bianry mode |
CN101241550A (en) * | 2008-01-19 | 2008-08-13 | 电子科技大学中山学院 | Iris image quality judging method |
CN101539991A (en) * | 2008-03-20 | 2009-09-23 | 中国科学院自动化研究所 | Effective image-region detection and segmentation method for iris recognition |
CN101447025A (en) * | 2008-12-30 | 2009-06-03 | 东南大学 | Method for identifying iris of large animals |
CN106250810A (en) * | 2015-06-15 | 2016-12-21 | 摩福公司 | By iris identification, individuality is identified and/or the method for certification |
CN106326825A (en) * | 2015-08-26 | 2017-01-11 | 北京巴塔科技有限公司 | Iris edge positioning method |
CN105447450A (en) * | 2015-11-12 | 2016-03-30 | 北京天诚盛业科技有限公司 | Method and device for judging left iris and right iris in iris recognition |
CN108171201A (en) * | 2018-01-17 | 2018-06-15 | 山东大学 | Eyelashes rapid detection method based on gray scale morphology |
CN108312964A (en) * | 2018-03-21 | 2018-07-24 | 华南理工大学 | A kind of fatigue driving state identification early warning system and method |
CN110245626A (en) * | 2019-06-19 | 2019-09-17 | 北京万里红科技股份有限公司 | A method of accurately detecting eyelash image in iris image |
Non-Patent Citations (3)
Title |
---|
W. K. KONG AND D. ZHANG: "Accurate iris segmentation based on novel reflection and eyelash detection model", 《PROCEEDINGS OF 2001 INTERNATIONALSYMPOSIUM ON INTELLIGENT MULTIMEDIA, MDEO AND SPEECH PROCESSING》 * |
岳学东 等: "一种新的虹膜图像预处理眼睑定位算法", 《光电工程》 * |
来毅 等: "用于虹膜识别的眼睑及眼睫毛遮挡检测", 《计算机辅助设计与图形学学报》 * |
Also Published As
Publication number | Publication date |
---|---|
CN110781747B (en) | 2022-03-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108121991B (en) | Deep learning ship target detection method based on edge candidate region extraction | |
Poletti et al. | A review of thresholding strategies applied to human chromosome segmentation | |
CN109918971B (en) | Method and device for detecting number of people in monitoring video | |
Zong et al. | U-net based method for automatic hard exudates segmentation in fundus images using inception module and residual connection | |
CN107256558A (en) | The cervical cell image automatic segmentation method and system of a kind of unsupervised formula | |
CN107862677A (en) | The Tunnel Lining Cracks recognition methods of thresholding algorithm and system between a kind of class based on gradient | |
CN109389129A (en) | A kind of image processing method, electronic equipment and storage medium | |
Duan et al. | A WBC segmentation methord based on HSI color space | |
CN109635846A (en) | A kind of multiclass medical image judgment method and system | |
CN106778687A (en) | Method for viewing points detecting based on local evaluation and global optimization | |
CN108960185A (en) | Vehicle target detection method and system based on YOLOv2 | |
CN105513053A (en) | Background modeling method for video analysis | |
CN104036521A (en) | Novel retina eye fundus image segmenting method | |
CN110245626B (en) | Method for accurately detecting eyelash image in iris image | |
CN106203338B (en) | Human eye state method for quickly identifying based on net region segmentation and threshold adaptive | |
CN105975952A (en) | Beard detection method and system in video image | |
Argade et al. | Automatic detection of diabetic retinopathy using image processing and data mining techniques | |
CN103279960B (en) | A kind of image partition method of human body cache based on X-ray backscatter images | |
CN113850792A (en) | Cell classification counting method and system based on computer vision | |
CN117765287A (en) | Image target extraction method combining LWR and density clustering | |
CN108009480A (en) | A kind of image human body behavioral value method of feature based identification | |
CN110781747B (en) | Eyelash occlusion area pre-detection method based on coefficient of variation | |
CN112330706A (en) | Mine personnel safety helmet segmentation method and device | |
Zhou et al. | Automated detection of red lesions using superpixel multichannel multifeature | |
CN115272333B (en) | Cup-disk ratio data storage system |
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 |