WO2008151471A1 - Procédé de positionnementrobuste et précis de l'oeil dans une image d'arrière-plan compliquée - Google Patents

Procédé de positionnementrobuste et précis de l'oeil dans une image d'arrière-plan compliquée Download PDF

Info

Publication number
WO2008151471A1
WO2008151471A1 PCT/CN2007/001894 CN2007001894W WO2008151471A1 WO 2008151471 A1 WO2008151471 A1 WO 2008151471A1 CN 2007001894 W CN2007001894 W CN 2007001894W WO 2008151471 A1 WO2008151471 A1 WO 2008151471A1
Authority
WO
WIPO (PCT)
Prior art keywords
eye
image
sample
training
classifier
Prior art date
Application number
PCT/CN2007/001894
Other languages
English (en)
Chinese (zh)
Inventor
Xiaoqing Ding
Yong Ma
Chi Fang
Changsong Liu
Liangrui Peng
Original Assignee
Tsinghua University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Tsinghua University filed Critical Tsinghua University
Priority to PCT/CN2007/001894 priority Critical patent/WO2008151471A1/fr
Publication of WO2008151471A1 publication Critical patent/WO2008151471A1/fr

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
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161—Detection; Localisation; Normalisation
    • G06V40/165—Detection; Localisation; Normalisation using facial parts and geometric relationships
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • 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

Definitions

  • the present invention relates to the field of face recognition technology, and in particular to a robust eye accurate positioning method in a complex background image. Background technique
  • Face detection is the determination of the position and size of a face in an image or image sequence. It is currently widely used in systems such as face recognition, video surveillance, and intelligent human-machine interfaces. Face detection, especially face detection in complex backgrounds, is also a difficult problem. This is due to the appearance of the face, the skin color, the expression, the movement in the three-dimensional space, and the external factors such as beard, hair, glasses, and light, which cause great changes in the face pattern, and because the background object is very complicated, it is difficult to Faces are separated.
  • the mainstream method of face detection is based on the detection method of sample statistical learning.
  • Such methods generally introduce the category of "non-human face".
  • the parameters of the "face” category are distinguished from those of the "non-human face” category, and the parameters of the model are obtained instead of the surface layer based on the visual impression. law.
  • This is more reliable in statistics, not only avoids errors caused by incomplete and inaccurate observations, but also increases the range of detection by increasing the training samples to improve the robustness of the detection system;
  • Using a simple to complex multi-layer classifier structure most of the background window is first excluded by a simple classifier, and then the remaining window is further judged by a complex classifier, thereby achieving a faster detection speed.
  • this method does not take into account the fact that the risk of classification error between face and non-face is very unbalanced in the actual image (this is because the prior probability of the face appearing in the image is much lower than that of the non-face) Probability is detected, and the main purpose of face detection is to find the position of the face, so the risk that the face is misclassified into a non-face is much greater than that of the non-face, and only the method based on the minimum classification error rate is used.
  • the present invention proposes a face detection method based on Cost Sensitive AdaBoost (CS-AdaBoost), which minimizes the risk of classification and makes each layer of training.
  • CS-AdaBoost Cost Sensitive AdaBoost
  • the classifier guarantees a very low rejection rate of the face mode while minimizing the false acceptance rate of the non-face class, thereby implementing a complex background image with fewer classifier layers and a simpler classifier structure. More high-performance face detection, which is currently not used in all other literature.
  • the object of the present invention is to realize a face detector capable of robustly locating a face under a complex background image, the face detection method comprising two stages of training and detecting;
  • a robust eye accurate positioning method in a complex background image comprising two stages of training and detecting;
  • a large number of samples are first collected, that is, a manual calibration method is used to collect training samples from the face images, and then the samples are normalized.
  • feature extraction is performed to obtain the feature database of the training samples.
  • the parameters of the classifier are determined experimentally, and the eye positioning classifier is trained.
  • the detection phase for an input face image area / (X, , 0 ⁇ x ⁇ W face , Q ⁇ y ⁇ H face , first estimate the area where the left and right human eyes may exist, and then exhaustively in the two areas Judging all the small windows (defining the small window as a rectangular area sub-image in the input image), extracting features for each small window, and then using the monocular detector to determine, thereby obtaining all human eye candidate positions in the region; The eye candidates combine to use the global properties to select the best combination, and the final position of the eye is obtained, thereby obtaining excellent eye positioning accuracy.
  • the training phase in turn contains the following steps - sample collection and normalization, estimation of the area of the left and right eyes using the projection function, training of the monocular detector, and training of the eye to the detector
  • a manual eye calibration method is used to cut a single eye image from the face image, and a non-eye sample is randomly cut from the non-eye portion of the face image, and the single eye image and the non-eye image are respectively taken as Positive and negative samples are used to train monocular detectors;
  • the eye is sampled from the face image according to the set ratio, and the non-eye pair sample is randomly cut from the face image, and the eye pair image
  • the non-eye-to-eye image is used as a positive example sample and a counter-example sample to train a monocular detector; the sample thus collected includes not only two eyes but also an eyebrow, a nose, etc., which embodies the constraint relationship between the eye and the surrounding organs;
  • the cropping from the face image is performed on the sample in the following proportions: the line connecting the center of the eyeball is taken as the X axis, and the vertical line perpendicular to the center line of the eyeball is taken as the Y axis, and the foot is located
  • the center line of the inner distance of the eyes is ⁇ ; when the distance between the centers of the eyes is set to dist, the horizontal distance between the center of the eye and the outer frame of the eye is %, and the upper and lower frames are each cut.
  • the distance from the foot is ' ⁇
  • ⁇ ( ⁇ , ⁇ ) ⁇ (0( ⁇ , ⁇ )- ⁇ ) + ⁇ ( thus adjusting the mean and variance of the grayscale of the image to the given value and ⁇ ., completes the grayscale normalization of the sample;
  • the training of the monocular detector uses a normalized single eye sample and a non-eye sample microstructure feature library, and a single eye detector is trained by the AdaBoost algorithm; the specific training process is as follows:
  • Class (a) The black area and the white area are bilaterally symmetrical and equal in area, with w indicating the width of each of the areas, and h indicating the height of each of the areas;
  • Class (d) The two black areas are in the first quadrant and the third quadrant respectively.
  • the two white areas are in the second and fourth quadrants respectively.
  • the area of each black area and each white area is equal, and the definition of w and h Same as (a):
  • Each of the microstructure features is obtained by calculating the difference between the grayscale sum of the pixels in the black area and the white area in the image covered by the template, and the position of the template relative to the image and the size of the template can be changed, since each feature extraction is only It involves the calculation of the pixel sum in the rectangular area, and it is convenient to quickly obtain a micro-structure feature of arbitrary scale and arbitrary position by using the integral image of the whole image;
  • g(x,y,w,h) 2JI(x + w-l,y + h-T) + II(x-l,y-V)-II(x + w-l,y- ⁇ )
  • g(x,y,w,h) -II(x-l,y-V)-II(x + 2w-l,y-l)-II(x-i,y + 2h- ⁇ )
  • g(x,y,w,h) II(x + wl,y + hl) + II(xl,yl)-II(x + wl,yV ⁇ -II(xl,y + hl) change number-JJO + w-3,y + /z-3)-H(x + l,:F + l) + //(x + l, ⁇ + 3) + HO; + wl,3 + l) Township x,y
  • the values of w, h can extract the microstructure features of different positions of the sample image, and for the eye/non-eye sample images normalized to 24 ⁇ 12, 42727 features can be obtained, thereby composing the feature quantity of the sample image ⁇ "d 1 ⁇ 42727 '
  • the AdaBoost algorithm selects the best performance single class-based weak classifiers in each iteration to achieve the purpose of feature selection; on the other hand, integrate these weak classifiers into one Strong classifier, and by cascading multiple strong classifiers to get a complete eye detector; specifically, it includes the following components:
  • the simplest tree classifier is constructed as a weak classifier corresponding to each dimension feature:
  • sub is a 24x12 pixel sample, g ;
  • (sub) represents the jth feature extracted from the sample, is the decision threshold corresponding to the jth feature, and the threshold is calculated by counting all collected eye and non-eye samples
  • the j features are such that the FRR of the eye sample satisfies the specified requirements, indicating the decision input of the tree classifier constructed using the jth feature Therefore, each weak classifier only needs to compare the threshold once to complete the decision; a total of 42727 weak classifiers are obtained; (ii) an eye/non-eye strong classifier design based on the AdaBoost algorithm
  • Step 3 Eye training for the classifier
  • the eye trains the classifier using the normalized eye-to-sample and non-eye-pair samples, extracts the feature libraries of the two types of samples, and uses the AdaBoost algorithm to train the eye-pair classifier.
  • the eye uses the same microstructural features and training process as the previous one-eye detector.
  • the AdaBoost algorithm is used to select a weak classifier based on a single feature from a large number of microstructure features to form a strong classifier. Strong classifiers are cascaded together; the specific training process of the eye to the classifier also includes feature extraction, feature selection, training of strong classifiers, and cascade of multi-layer strong classifiers:
  • the normalized eye-to-sample and non-eye-pair samples to extract the high-dimensional microstructure features of the eye-pair and non-eye-pair samples according to the feature extraction method described in step 2.1 above.
  • the feature points that make up the sample are ⁇ ( ), 1 ⁇ y ⁇ 71210;
  • the coordinate area of the sample in the whole image is (x. ⁇ x' ⁇ x Q + 24, ⁇ 0 ⁇ / ⁇ 0 +14) , then; ⁇ and respectively are:
  • each dimension micro-structure feature is as follows: For a sample image of 25x15 pixels, a total of 71210-dimensional microstructure features i ⁇ /), l ⁇ _ / ⁇ 71110 are obtained.
  • the eye also uses a layered structure for the detector.
  • the background window in the image is first excluded by a strong classifier with a simple structure, and then the remaining window is judged by a strong classifier with a complicated structure. Specifically, it includes the following components:
  • the detection phase refers to determining the center position of the eye area of an input face, and includes the following steps:
  • the eye detection stage is for an input face area, and the following steps are used to accurately position the center of the eye: Step 1 Estimate the area where the left and right eyes are located ⁇ ⁇ ;
  • the peak of ( x) is the vertical boundary of the area where the left and right eyes are located. Define this position as ⁇
  • the upper and lower boundaries of ⁇ ⁇ can be counted by the distribution of the eyes in the vertical direction of the face in the sample;
  • ⁇ ⁇ 3 ⁇ 4 e (x, ' x peak ⁇ x ⁇ W face ' 0.05H face ⁇ y ⁇ 0A5H faci! where H face and if /ace are the height and width of the face derived from the sample statistics;
  • Step 2 Using a single-eye detector to detect eye candidates
  • the left and right eye candidates are paired, more features of the candidate surrounding regions are extracted, and then each pair of candidates is verified using the eye pair classifier, and finally from all posterior probabilities based on posterior probabilities
  • the optimal position of the binocular is estimated in the candidate pair, specifically for each pair of eye candidates, including the following processing steps -
  • the image is cut according to the way the eye cuts the sample in step 1.1 of the training phase, and then the size normalization and illumination normalization are performed to obtain an eye of 25 x 15 pixels.
  • the verification steps for each eye candidate pair image are as follows:
  • step 3 (3) (i ii) If judged, the value is incremented by 1, returning to step 3 (3) (ii); otherwise, the eye candidate pair is discarded; if it is judged by all layer strength classifiers, the candidate pair is considered to be a valid candidate pair , output its position and its confidence;
  • the candidate pairs that pass the judgment are sorted according to the confidence level from large to small, and the average position of the first three pairs of candidate pairs with the highest confidence is taken as the eye center position, and the eye position is output.
  • step 2 2) using the training sample set to train the i-th layer eye/non-eye strong classifier using the AdaBoost algorithm described in step 2 (3) (ii);
  • step 2 If the value does not reach the predetermined value, the value increases by 1. Return to step 2 to continue the training; otherwise, stop the training;
  • step 3 (3) (iii) the entire eye uses a hierarchical structure for the verifier, and training the connection of the multi-layer strong classifier includes the following steps:
  • Initialization 1;
  • the training goal for defining each level of strong classifier is on the eye-to-training set? ⁇ 0.1%, on the non-eye-pair training set 3 ⁇ 4i? ⁇ 50% ; defining the entire eye-to-detector in the eye-pair training ? Ei on the target set i ⁇ l%, in the eyes of non-target 3 ⁇ 4i on the training set ⁇ lxl0- 3??;
  • step (b) If 3 ⁇ 4?, F ⁇ R does not reach the predetermined value, the shell lj/value is increased by 1, returning to step (b) to continue the training; otherwise, the training is stopped; the training is to obtain a 9-layer structure from simple to complex strong classifier; These strong classifier cascades form a complete eye-pair detector; to verify the effectiveness of the invention, we performed the following experiment:
  • test set used by the eye positioning algorithm includes the following three parts:
  • Test Set 1 Consisting of a face database of Yale B and Aerolnfo.
  • the Ministry of Public Security consists of 4,353 images of 209 people.
  • the Yale B database consists of 15 people, 165 images, which are characterized by complex illumination changes.
  • the Aerolnfo database provided by China Aerospace Information Co., Ltd., includes 3,740 images of 165 people, characterized by external illumination, The posture of the face changes complexly, and the background is complex, and the quality of the face image is poor.
  • the Ministry of Public Security has a face database of 448 images of 30 people, which is characterized by complex lighting changes, and some people wear glasses and strong Reflective
  • Test Set 2 Consists of the English part of the BANCA Face Database, which includes a total of 6540 images of 82 people. It is characterized by a large change in image background and image quality, including images acquired under controlled, degraded and harsh scenes. In addition, illumination and face pose changes are also complicated, and many people also wear black-rimmed glasses;
  • Test Set 3 The JAFFE database, which includes 213 face images, is characterized by rich facial expression changes; tests performed on collections with such rich sources and changes should truly reflect the performance of a positioning algorithm: Table 1 and others Performance comparison of positioning algorithm under different allowable errors
  • the algorithm has stable performance on different test sets, which is better than the positioning accuracy of the FacelT, and the FacelT is sensitive to the opening and closing of the human eye and the size of the face in the experiment; and zhou [zh ° u ZH ' Geng X Projeeti ° n funeti ° ns fM eye deteetiOT Pattern Re ⁇ gniti ° n ' 2 (m) method, the accuracy of the method in the JAFFE database within 0.10 is 98.6%, and its method The positioning accuracy of the error within 0.25 is only 97.2%.
  • Figure 1 shows the hardware composition of a typical eye positioning system
  • Figure 2 The collection process of training samples
  • Figure 3 Example of a single eye sample and an eye pair sample
  • Figure 4 is a block diagram of the eye positioning system
  • Figure 5 Five microstructure feature templates used
  • Figure 8 cascading structure of multi-level strong classifier
  • Figure 9 The training process of a strong classifier based on the AdaBoost algorithm
  • Figure 10 is a schematic diagram of the eye to template ratio
  • Figure 11 is a face recognition sign-in system based on the algorithm. detailed description
  • Fig. 1 The hardware structure of the entire human eye positioning system is shown in Fig. 1.
  • 101 is a scanner
  • 102 is a camera
  • 103 is a computer.
  • the training process and identification process of the system are shown in Figure 4. The following sections describe the various parts of the system in detail:
  • the input to the system is a single face area image.
  • the face detection portion is not included in the present invention and will not be described in detail.
  • a single eye image is cut out from the face image by a manual calibration method, and a non-eye sample is randomly cut from the non-eye portion of the face image.
  • the single eye image and the non-eye image are used as positive and negative samples, respectively, for training the monocular detector.
  • Some training samples are shown in Figure 3(a).
  • the eye-to-sample is obtained by cropping from the face image according to the scale shown in Fig. 7, and the non-eye pair sample is randomly cut from the face image.
  • the eye-to-image and non-eye-to-image images are used as training positive and negative samples, respectively, for training monocular detectors.
  • Some of the samples collected are shown in Figure 3(b).
  • the samples collected in this way include not only the two eyes but also the eyebrows, the nose and other parts, which embodies the constraint relationship between the eyes and the surrounding organs.
  • the collected sample images of each size are normalized to a specified size.
  • the original sample image be ] MxW
  • the image width be M
  • the height be N
  • the value of the pixel at the y column of the Xth row of the image is F(x, y) ( 0 ⁇ x ⁇ M , 0 ⁇ y ⁇ N
  • the present invention transforms the original sample image into a standard size sample image using back projection and linear interpolation, and the correspondence between the input image and the normalized image [G xW is - .
  • the linear interpolation method for a given (X, , order:
  • Training of a single eye detector uses a normalized single eye sample and a non-eye sample microstructure feature library, and a single eye detector is trained using the AdaBoost algorithm; the specific training process is as follows:
  • the microstructure feature can quickly obtain a micro-structure feature of any scale and arbitrary position in the image by using the integral map of the whole image, it provides a possibility for real-time detection of the eye.
  • the invention uses the five types of microstructure templates in FIG. 6 to extract high-dimensional microstructure features of the human eye mode; and obtains features by calculating the difference between the gray levels of the pixels in the corresponding black and white regions in the image, and expresses the characteristics of the eye mode. .
  • the pixel sum can be quickly calculated by the addition and subtraction of the integral map by 3 times.
  • microstructure features can be calculated by adding and subtracting several times through the corresponding integral image.
  • the present invention uses the AdaBoost algorithm to select features and train classifiers.
  • the AdaBoost algorithm selects the best performance single class-based weak classifier in each iteration to achieve the purpose of feature selection; on the other hand, these weak classifiers are integrated into one strong classifier, and by multiple strong The classifiers are cascaded to get an excellent eye detector.
  • it includes the following components:
  • Weak classifiers must have very high classification speeds, and the entire strong classifier can achieve a sufficiently high classification speed.
  • the present invention constructs the simplest tree classifier for each dimension feature as a weak classifier:
  • sub is a 24x12 pixel sample
  • (sub) represents the jth feature extracted from the sample
  • the present invention combines the AdaBoost algorithm with the weak classifier construction method described above for training eye/non-eye strong classifiers.
  • T is the number of weak classifiers that you want to use
  • ⁇ should increase gradually with the increase of the number of strong classifiers. See Table 1 for specific selection values; The maximum value FmaxCj) and the minimum value Fmin(j) of each feature distribution on the statistical sample set (where _ is the feature number: 1 ⁇ 7 ⁇ 42727);
  • the present invention adopts the confidence that the obtained mode belongs to the eye
  • the training goal for defining each level of strong classifier is i3 ⁇ 4i? ⁇ 0.1% on the eye training set, _ ⁇ 2 ⁇ on the non-eye training set 60%; defines the target Fi?i? ⁇ l% of the entire eye detector on the eye training set, and the target ⁇ SxlO" 4 on the non-eye training set;
  • the present invention pairs left and right eye candidates, extracts more features of the candidate surrounding regions, and then uses the eye pair classifier to verify each pair of candidates, and finally according to the posterior probability.
  • the optimal position of both eyes is estimated for all candidate pairs (as shown in Figures 4 and 5).
  • Eye training for the classifier includes the following steps:
  • microstructure templates in Figure 6 were used to extract high-dimensional microstructure features of both the eye and non-eye pairs. It is also possible to quickly obtain a microstructure feature of arbitrary scale and arbitrary position by using the integral image of the entire image //(X, - ⁇ ⁇ /( ⁇ ', ). Also define the square integral image ⁇ I(x', y' ) -I(x',y'), used to calculate the variance of each rectangular region.
  • any of the above microstructure features can be quickly calculated by adding and subtracting the integral image several times.
  • a total of 71,210 features are obtained, which constitute the feature vector ⁇ (_/) of the sample, 1 ⁇ _/ ⁇ 71210.
  • it is necessary to normalize the gray mean and variance for each 25x15 pixel sample image so firstly calculate the mean of the small window; ⁇ and the variance ⁇ , and then normalize each dimension feature. , in which the sum of the grayscale sums of the pixels in the small window area of 25 X 15 pixels ( ⁇ . ⁇ ' ⁇ + 0 + 24, y Q ⁇ / ⁇ + 14) is
  • an eye-to-detector In order to achieve a fast enough verification speed, an eye-to-detector must adopt a layered structure (as shown in Figure 8).
  • the background window in the image is first excluded by a simple classifier with a simple structure, and then a strong classifier with complex structure is used. Judge the remaining windows.
  • This section still uses the AdaBoost algorithm to select features and train the classifier, as shown in Figure 9. Specifically, it includes the following components - 1 weak classifier construction
  • the weak classifier still uses a tree classifier constructed with one-dimensional features:
  • the CS-AdaBoost algorithm is combined with the weak classifier construction method described above for training eye-to-strong classifiers.
  • T is the number of weak classifiers that you want to use
  • ⁇ should gradually increase with the number of strong classifiers. See Table 2 for specific selection values
  • the present invention uses (l I /(sub)) to obtain the posterior probability that the pattern belongs to the eye pair, here /( S ub) .
  • the entire eye has a hierarchical structure for the validator, as shown in Figure 8.
  • Initialization ⁇ ⁇ 1 ;
  • the training objective for defining each class of strong classifiers is i?i? ⁇ 0.1% on the eye-to-training set, and 3 ⁇ 4 ⁇ 50% on the non-eye-pair training set; defining the entire eye-to-detection ? in ⁇ l% target 3 ⁇ 4 eye on the training set, in the eyes of non-target on the training set ⁇ ⁇ 1 10- 3; j) using the training set of training i-layer strong classifier;
  • step (b) If ⁇ , does not reach the predetermined value, then ⁇ + 1, return to step (b) continue training; otherwise stop training. .
  • the eye detection phase includes the following steps: 1. Estimating the area where the left and right eyes are located ⁇ , ⁇ CL rigl eye uses the mean and variance functions of the vertical projection of the face grayscale image to determine ⁇ , ⁇ and ⁇ , / The boundary line in the horizontal direction is then determined according to the distribution law of the eye in the vertical direction of the face region from the training sample, and ⁇ / ⁇ ⁇ and
  • the peak value of the ratio of the mean function of the vertical direction grayscale projection to the variance function is taken as the vertical boundary line between the left and right eyes, as shown in Fig. 5(b). Define the location of this peak; ⁇ ,
  • the upper and lower boundaries of Q leJieye and Q rlg/lleye can be counted using the distribution of eye positions in the vertical direction in the face sample.
  • Eye detectors are used to detect left and right eye candidate positions in the ⁇ 3 ⁇ 4 and ⁇ regions, respectively, and the confidence of each candidate position is estimated.
  • the specific detection process for eye candidates is as follows -
  • step 3 If judged, then +1 returns to step 3; otherwise, the small window is discarded; if judged by all layer strength classifiers, the small window is considered to contain an eye candidate, and its position and its confidence are output. Otherwise, the small window is discarded and no subsequent processing is performed;
  • the present invention outputs up to the top 20 candidate positions according to the candidate confidence level.
  • the present invention pairs left and right eye candidates, extracts more features of the candidate surrounding regions, and then uses the eye pair classifier to verify each pair of candidates, and finally according to the posterior probability.
  • the best position for both eyes is estimated for all candidate pairs.
  • the processing steps include the following:
  • the image is first cut according to the position of the left and right eye candidates according to the position shown in the template (Fig. 10), and then the size normalization and illumination normalization are performed to obtain an eye candidate pair image of 25 x 15 pixels.
  • step 3 If judged, Bay z' + l, return to step 1; otherwise discard the eye candidate pair; if judged by all layer strong classifiers, then consider the candidate pair as a valid candidate pair, output its position and its confidence Finally, the candidate pairs that pass the judgment are sorted according to the confidence level from large to small, and the average position of the first three pairs of candidate pairs with the highest confidence is taken as the eye center position. Output eye position.
  • the present invention employs a positioning error metric that is independent of the size of the face. Since the center distance of the eyes of the frontal face generally does not change with the expression and the like, and has relative stability, the center distance of the eyes of the artificial calibration is used as a reference.
  • the left and right eye and mouth positions are manually calibrated as P / e , ⁇ and , respectively, and the left and right eye and mouth positions of the automatic positioning are P fe ', ' and , respectively, and the Euclidean distance between 4 and , 4 is the Euclidean distance between the two, d re is the Euclidean distance between P r and P re , d m is P mic; Euclidean distance from P m .
  • the eye positioning error is defined as:
  • Embodiment 1 Face-based identification check-in system (as shown in Figure 11)
  • Face authentication is one of the most friendly authentication methods in biometric authentication technology that has received wide attention recently. It is designed to use face images for computer automatic personal identification to replace traditional passwords, certificates, seals and other authentication methods. It is not easy to forge, not lost, and convenient.
  • the system uses face information to automatically verify the identity of the person.
  • the face detection module used therein is the research result of this paper.
  • the system also participated in the FAT2004 competition organized by ICPR2004.
  • the competition included 13 face recognition algorithms from 11 academic and commercial institutions including Carnegie Mellon University in the United States, Neuroinformatik Institute in Germany, and Surrey University in the United Kingdom.
  • the system submitted by the laboratory won the first place in the three evaluation indicators with a lower error rate of about 50% than the second.
  • the research results of this paper are applied to the eye positioning module of the system submitted by the actual implementation, thus ensuring that the overall performance of the system is at the advanced level in the world.
  • the present invention can accurately and accurately locate an eye in an image with a complex background, and obtains excellent positioning results in experiments, and has a very broad application prospect.
  • PT/CN2007/001894 The above-mentioned embodiments are only preferred embodiments of the present invention, and those common changes and substitutions made by those skilled in the art within the scope of the technical solutions of the present invention should be included in the scope of protection of the present invention. .

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • General Health & Medical Sciences (AREA)
  • Ophthalmology & Optometry (AREA)
  • Geometry (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Image Analysis (AREA)

Abstract

L'invention concerne un procédé de positionnement robuste et précis de l'oeil dans une image d'arrière plan compliquée. Ce procédé adopte une caractéristique de microstructures à haut rendement et à redondance élevée pour exprimer le caractère de distribution par échelonnement à la fois des zones locales et globales du type de l'oeil et adopte l'algorithme AdaBoost pour choisir les caractéristiques de microstructures les plus différentes de façon à former un classifieur solide. Cet algorithme prend également en considération de manière intelligente les caractères locaux et les caractères globaux qui peuvent exprimer ce type de relation de contrainte pour obtenir un effet de positionnement plus robuste.
PCT/CN2007/001894 2007-06-15 2007-06-15 Procédé de positionnementrobuste et précis de l'oeil dans une image d'arrière-plan compliquée WO2008151471A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2007/001894 WO2008151471A1 (fr) 2007-06-15 2007-06-15 Procédé de positionnementrobuste et précis de l'oeil dans une image d'arrière-plan compliquée

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2007/001894 WO2008151471A1 (fr) 2007-06-15 2007-06-15 Procédé de positionnementrobuste et précis de l'oeil dans une image d'arrière-plan compliquée

Publications (1)

Publication Number Publication Date
WO2008151471A1 true WO2008151471A1 (fr) 2008-12-18

Family

ID=40129206

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2007/001894 WO2008151471A1 (fr) 2007-06-15 2007-06-15 Procédé de positionnementrobuste et précis de l'oeil dans une image d'arrière-plan compliquée

Country Status (1)

Country Link
WO (1) WO2008151471A1 (fr)

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102339377A (zh) * 2010-07-21 2012-02-01 比亚迪股份有限公司 一种快速人眼定位方法及装置
CN107330188A (zh) * 2017-06-30 2017-11-07 武汉大学深圳研究院 面向复制对象的多色半色调设备拆分式建模方法及系统
CN108182380A (zh) * 2017-11-30 2018-06-19 天津大学 一种基于机器学习的鱼眼瞳孔智能测量方法
CN109636794A (zh) * 2018-12-14 2019-04-16 辽宁奇辉电子系统工程有限公司 一种基于机器学习的地铁高度调节阀紧固螺母定位方法
CN110706235A (zh) * 2019-08-30 2020-01-17 华南农业大学 一种基于双级级联分割的远红外行人检测方法
CN111523407A (zh) * 2020-04-08 2020-08-11 上海涛润医疗科技有限公司 人脸识别系统及方法以及基于人脸识别的医护记录系统
CN111582008A (zh) * 2019-02-19 2020-08-25 富士通株式会社 训练分类模型的装置和方法及利用分类模型分类的装置
CN112907510A (zh) * 2021-01-15 2021-06-04 中国人民解放军国防科技大学 一种表面缺陷检测方法
CN112966705A (zh) * 2020-11-24 2021-06-15 大禹节水集团股份有限公司 一种基于adaboost对农业灌溉滴灌头质量的在线识别方法
CN113780155A (zh) * 2021-09-07 2021-12-10 合肥工业大学 一种基于新增Haar-like特征的猪脸检测方法
CN116363736A (zh) * 2023-05-31 2023-06-30 山东农业工程学院 基于数字化的大数据用户信息采集方法

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2005008210A2 (fr) * 2003-05-14 2005-01-27 Polcha Michael P Systeme et procede permettant d'effectuer un controle d'acces securise a partir de donnees biometriques modifiees
CN1731418A (zh) * 2005-08-19 2006-02-08 清华大学 复杂背景图像中鲁棒的眼睛精确定位方法

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2005008210A2 (fr) * 2003-05-14 2005-01-27 Polcha Michael P Systeme et procede permettant d'effectuer un controle d'acces securise a partir de donnees biometriques modifiees
CN1731418A (zh) * 2005-08-19 2006-02-08 清华大学 复杂背景图像中鲁棒的眼睛精确定位方法

Cited By (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102339377A (zh) * 2010-07-21 2012-02-01 比亚迪股份有限公司 一种快速人眼定位方法及装置
CN107330188A (zh) * 2017-06-30 2017-11-07 武汉大学深圳研究院 面向复制对象的多色半色调设备拆分式建模方法及系统
CN108182380A (zh) * 2017-11-30 2018-06-19 天津大学 一种基于机器学习的鱼眼瞳孔智能测量方法
CN108182380B (zh) * 2017-11-30 2023-06-06 天津大学 一种基于机器学习的鱼眼瞳孔智能测量方法
CN109636794B (zh) * 2018-12-14 2023-02-28 辽宁奇辉电子系统工程有限公司 一种基于机器学习的地铁高度调节阀紧固螺母定位方法
CN109636794A (zh) * 2018-12-14 2019-04-16 辽宁奇辉电子系统工程有限公司 一种基于机器学习的地铁高度调节阀紧固螺母定位方法
CN111582008A (zh) * 2019-02-19 2020-08-25 富士通株式会社 训练分类模型的装置和方法及利用分类模型分类的装置
CN111582008B (zh) * 2019-02-19 2023-09-08 富士通株式会社 训练分类模型的装置和方法及利用分类模型分类的装置
CN110706235A (zh) * 2019-08-30 2020-01-17 华南农业大学 一种基于双级级联分割的远红外行人检测方法
CN111523407A (zh) * 2020-04-08 2020-08-11 上海涛润医疗科技有限公司 人脸识别系统及方法以及基于人脸识别的医护记录系统
CN112966705A (zh) * 2020-11-24 2021-06-15 大禹节水集团股份有限公司 一种基于adaboost对农业灌溉滴灌头质量的在线识别方法
CN112907510B (zh) * 2021-01-15 2023-07-07 中国人民解放军国防科技大学 一种表面缺陷检测方法
CN112907510A (zh) * 2021-01-15 2021-06-04 中国人民解放军国防科技大学 一种表面缺陷检测方法
CN113780155A (zh) * 2021-09-07 2021-12-10 合肥工业大学 一种基于新增Haar-like特征的猪脸检测方法
CN116363736A (zh) * 2023-05-31 2023-06-30 山东农业工程学院 基于数字化的大数据用户信息采集方法
CN116363736B (zh) * 2023-05-31 2023-08-18 山东农业工程学院 基于数字化的大数据用户信息采集方法

Similar Documents

Publication Publication Date Title
WO2008151471A1 (fr) Procédé de positionnementrobuste et précis de l'oeil dans une image d'arrière-plan compliquée
US20210287026A1 (en) Method and apparatus with liveness verification
WO2020000908A1 (fr) Procédé et dispositif de détection de vivacité de visage
US8320643B2 (en) Face authentication device
US9064145B2 (en) Identity recognition based on multiple feature fusion for an eye image
CN105956572A (zh) 一种基于卷积神经网络的活体人脸检测方法
WO2008151470A1 (fr) Procédé de détection robuste de visage humain dans une image d'arrière-plan compliquée
CN111680588A (zh) 一种基于可见光和红外光的人脸闸机活体检测方法
CN108563999A (zh) 一种面向低质量视频图像的人物身份识别方法与装置
US7869632B2 (en) Automatic trimming method, apparatus and program
CN104504362A (zh) 基于卷积神经网络的人脸检测方法
CN103632132A (zh) 一种基于肤色分割和模板匹配的人脸检测与识别方法
KR101172898B1 (ko) 얼굴 인식 시스템에서의 위조 검출 방법
CN110414299B (zh) 一种基于计算机视觉的猴脸亲缘关系分析方法
TW200910223A (en) Image processing apparatus and image processing method
CN105512630B (zh) 人眼检测与定位方法
WO2021088640A1 (fr) Technologie de reconnaissance faciale basée sur une transformation de nuage gaussien heuristique
WO2022268183A1 (fr) Procédé et système d'authentification de geste aléatoire basés sur une vidéo
RU2316051C2 (ru) Способ и система автоматической проверки присутствия лица живого человека в биометрических системах безопасности
Pathak et al. Multimodal eye biometric system based on contour based E-CNN and multi algorithmic feature extraction using SVBF matching
CN111191549A (zh) 一种两级人脸防伪检测方法
CN110378414A (zh) 基于进化策略的多模态生物特征融合的身份识别方法
Xu et al. A novel multi-view face detection method based on improved real adaboost algorithm
KR102405570B1 (ko) 베이지안 분류를 이용한 입 모양 기반의 발음 인식방법
Zhang et al. Eye Location Based on Adaboost and Random Forests.

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 07721467

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 07721467

Country of ref document: EP

Kind code of ref document: A1