基于红外光的脸部识别.ppt

#1,U of H,COSC 6397,Face Recognition in the Infrared Spectrum,Prof. Ioannis Pavlidis,#2,Primary Applications,Biometric Identification Passwords/PINs. Tokens (like ID cards). You can be your own password. Surveillance Off-the-shelf facial recognition system that identifies humans as they pass through a cameras field of view.,#3,Novel Applications,Wearable Recognition Systems Adapt to a specific user and be more intimately and actively involved in the users activities. Face recognition software can help you remember the name of the person you are looking at. Useful for Alzheimers patients.,Smart Systems Key goal is to give machines perceptual abilities that allow them to function naturally with people. Critical for a variety of human-machine interfaces.,#4,Why Infrared?,Thermal cameras sense emitted radiation,Visible cameras sense reflected light,Visible light has no effect on images taken in the thermal infrared spectrum. Even images taken in total darkness are clear in the thermal infrared.,#5,Why Infrared? (Contd.),Illumination Invariance Major problem in visible domain. Uniqueness and Repeatability Sense thermal patterns of blood vessels under the skin, which transport warm blood throughout the body. Remain relatively unaffected by aging. Even identical twins have different thermograms. Immune from Forgery Disguises can be easily detected.,#6,Previous Work,Lot of research was done in the visible band but little attention was given in the infrared spectrum. Recent reduction in the cost of infrared cameras and availability of large data sets encouraged active research in infrared face recognition. Low-Level Models Directly analyze the image pixels and impose probabilities on the features. Examples are PCA, ICA, and FDA. Not good in challenging conditions. High-Level Models Synthesize images from 3D templates of known objects and impose probabilities on transformations. Template matching approaches. Computationally expensive. Our Proposal Intermediate model which takes advantage of both Low-Level and High-Level models.,#7,Principal Component Analysis,A D = H x W pixel image of a face, represented as a vector occupies a single point in D2-dimensional image space. Images of faces being similar in overall configuration, will not be randomly distributed in this huge image space. Therefore, they can be described by a low dimensional subspace. Main idea of PCA (cutler96): To find vectors that best account for variation of face images in entire image space. These vectors are called eigen vectors. Construct a face space and project the images into this face space (eigenfaces).,#8,Eigenfaces Approach - Training,Training set of images represented by 1,2,3,M The average training set is defined by = (1/M) Mi=1 i Each face differs from the average by vector i = i A covariance matrix is constructed as: C = AAT, where A=1,M Finding eigenvectors of N2 x N2 matrix is intractable. Hence, find only M meaningful eigenvectors. M is typically the size of the database.,#9,Eigenfaces Approach - Training,Consider eigenvectors vi of ATA such that ATAvi = ivi Pre-multiplying by A, AAT(Avi) = i(Avi) The eigenfaces are ui = Avi A face image can be projected into this face space by k = UT(k ); k=1,M,#10,Eigenfaces Approach - Testing,The test image, , is projected into the face space to obtain a vector, : = UT( ) The distance of to each face class is defined by k2 = |-k|2; k = 1,M A distance threshold,c, is half the largest distance between any two face classes: c = maxj,k |j-k|; j,k = 1,M,#11,Eigenfaces Approach - Testing,Find the distance, , between the original image, , and its reconstructed image from the eigenface space, f, 2 = | f |2 , where f = U * + Recognition process: IF cthen input image is not a face image; IF <c AND kc for all k then input image contains an unknown face; IF <c AND k*=mink k < c then input image contains the face of individual k*,#12,Limitations of Eigenfaces Approach,Variations in lighting conditions Different lighting conditions for enrolment and query. Bright light causing image saturation. Differences in pose Head orientation 2D feature distances appear to distort. Expression Change in feature location and shape.,#13,IR Face Recognition Training Phase,Compute Offline,#14,IR Face Recognition Test Phase,#15,Segmentation,Noise in the background may effect the performance of a face recognition system. Remove the background. Use thermal information on face to compute the features.,Adaptive Fuzzy Segmentation (kakadiaris02) Fuzzy affinity is assigned to spels w.r.t. target object spel. Affinity is computed as weighted sum of the temperature and the temperature gradient in the neighborhood of the target spel. Minimal user interaction because of dynamically assigned weights.,#16,Segmentation (Contd.),Fuzzy affinity is calculated by:,Spatial Adjacency,Temperature Homogeneity,Temperature Gradient,Weights,Spatial Adjacency:,#17,Segmentation (Contd.),Temperature homogeneity p1,c1) and f(x;p2,c2) in D:,#31,Hypothesis Pruning,Applying a high-level classifier on entire database is computationally very expensive. Pruning of hypotheses can be achieved by using Bessel parameters (anuj01). Helps in short listing best matches. Bessel parameters for images in database can be computed offline which helps in saving a lot of computation time.,#32,Hypothesis Pruning (Contd.),Define a probability mass function on the database A:,(p(j)obs,c(j)obs) observed Bessel parameters for test image I(j) (p(j),s,c(j),s) estimated Bessel parameters which can be computed offline,Images in database A with P1(|I) greater than a specific threshold value are short listed as best matches.,(D=0.3 for Equinox dataset),#33,Hypothesis Pruning (Contd.),Shortlist the subjects of A with P1(/I) greater than a specific threshold:,Elements of A,Exact Match,Pruned Hypothesis,#34,Pruning Algorithm,Images with this value greater than a threshold are shortlisted,#35,Classification,Bayesian target recognition (anuj00) searches for the target hypothesis with largest posterior probability given by:,Likelihood,Aprori,Likelihood:,Apriori is same for all images in database (for database of n images, it is 1/n for each image)., : Variance of test image d : dimension of image (2 in this case),#36,Experiments,Equinox Database: Image frame sequences were acquired at 10 frames/sec while the subject was reciting the vowels a,e,i,o,u.,Sample Images,Experimental Setup,#37,Results ROC Curves,Correct Positive : Test image is in the database and is correctly recognized. False Positive : Test image is not in the database, but is recognized to be an image of the database Negatives : Test images that are not in the database.,#38,Results Precision & Recall,#39,Conclusion,We came up with a face recognition approach which is computationally inexpensive and at the same time good in challenging conditions. The features of all images in database can be computed offline and stored for future use. This saves lot of computation time. We improved the performance of classifier by removing background noise of pruned hypothesis using adaptive fuzzy connectedness based image segmentation.,#40,References,anuj01 A. Srivastava, X. W. Liu, B. Thomasson, and C. Hesher, Spectral Probability Models for IR Images with Applications to IR Face Recognition, in Proceedings 2001 IEEE Workshop on Computer Vision Beyond the Visible Spectrum: Methods and Applications, Kauai, HI, Dec 14. cutler96 R. Cutler, “Face recognition using infrared images and eigenfaces”, website, http:/www.cs.umd.edu/rgc/face/face.htm, 1996. anuj00 A. Srivastava, M. I. Miller, and U. Grenander, “Bayesian automated target recognition, Handbook of Image and Video Processing, Academic Press, pp. 869-881, 2000. kakadiaris02 A. Pednekar, I.A. Kakadiaris, U. Kurkure. Adaptive fuzzy connectedness-based medical image segmentation. In Proc. of the Indian Conf. on Computer Vision, Graphics, and Image Processing (ICVGIP 2002), pp.457-462, Ahmedabad, India, December 16-18 2002.,