Documenti di Didattica
Documenti di Professioni
Documenti di Cultura
Literature Review
Bio = Life, Metrics = To Measure
Biometrics
Physiological
Behavioral
Face Recognition
Iris Recognition
DNA Matching
Fingerprint Recognition
Signature Recognition
Voice Recognition
VERIFICATION -answer the question Is this X? -accomplished by the system performing a one-to-one search
First automatic face recognition system was developed by Kanade in the year 1973
Compare Templates
Declare Matches
Local Features
Hybrid Features
PCA
LDA
HMM
LBP
Hybrid LFA
parametric 3x3 kernel which summarizes the local spatial structure of an image.
Features Faces can be seen as a composition of micro-patterns which are well described by LBP operator Highly Discriminative Invariant to monotonic gray scale transformations. Computational Simplicity
, =
=
( )
Grey value of center pixel ( , ) Grey value of the 8 corresponding pixels s(x) = 1 if x0 s(x) = 2 if x<0
neighborhood of different radius size. Known as the multi-scale operator - LBPP,R The LBPP,R notation refers to P equally spaced pixels on a circle of radius R
a) P=8, R=1
b) P=8, R=2
c) P=16, R=2
Uniform Patterns
Ojala in his work reveals that it is possible to use only a subset
of the 2P LBP patterns to describe textured images. This subset is called uniform patterns or fundamental patterns. A LBP is called uniform if it contains maximal 2 transitions from 0 to 1 and vice versa. Can be used to reduce dimensions of feature vector.
Uniform Patterns
Each of these patterns has its own bin in the histogram.
The rest of the patterns with more than 2 transitions will be
Project Design
Software Model Waterfall Model
Software
REQUIREMENTS
DESIGN
Hardware
Android Smartphone
IMPLEMENTATION
TESTING
MAINTENANCE
Deployment View
Implementation
Development Tools Android SDK
AVD Manager
Dalvik Debug Monitor Server (ddms):
Android Emulator
SQLite3
Training Stage
Test Stage
Face Detection
Integral Part of the Face Recognition Process
Challenges Pose variance, Feature occlusion, Facial expression, Imaging conditions Some common approaches Haar-Cascades Skin Segmentation Template Matching LBP Features can also be used for face Detection.
Face Detection
Approach used for this Project Android.media.FaceDetector class from the Android SDK Face is considered detected if confidence ratio > 0.3 Details obtained with each face detected Distance between the eyes Midpoint between the eyes Faces pose (rotation around X, Y, Z axis)
Image Preprocessing
Histogram Equalization
Face Mask
Application of face mask is to avoid non-face parts in
image.
Example of a face mask -
1-Level Image
LBP8,1
LBP8,2
1-Level Image
LBP8,1u2
LBP8,2u2
Histogram = H(8,1)
Histogram = H(8,2)
Face Identification
In this project, dissimilarity metrics is used to match faces. Common Dissimilarity Metrics
I Input Image, M Match Image(from Database) Histogram Intersection Log Likelihood Classification
, = , =
= =
= = =
, =
= +
, =
+ ,
Testing
Input Images with faces in it are given to the FaceDetector Class Expected Output Faces to be detected in the image. Actual Output Faces detected in the image.
Image is to be converted to
grayscale
Future Work
Non linear illumination transforms and nose alignment
should be considered. Promising method to detect faces should be found. Should find a method to reduce the dimensions of the ultimate feature vector.
References
Kuikui Lu and Lanfang Dong, Using LBP histogram for face recognition on Android platform
Authentication, IEEE International Conference on Automatic Face and Gesture Recognition, 2006.
T. Ahomen, A. Hadid, and M. Pietikainen, Face description with local binary patterns: Application to
face recognition, IEEE Transaction on Pattern Analysis and Machine Intelligence, vol. 28, 2006.
Yann Rodriguez and Sebastien Marcel, Face Authentication Using Adapted Local Binary Pattern
classification with local binary patterns. IEEE Transactions on Pattern Analysis and Machine intelligence 24 (2002) 971987
W. Zhao, R. Chellappa, P. J. Phillips, and A. Rosenfeld, Face recognition: A literature survey, ACM
THANK YOU