Download presentation
Presentation is loading. Please wait.
Published byPhillip Robbins Modified over 9 years ago
2
A Brief Survey on Face Recognition Systems Amir Omidvarnia March 2007
3
Outline Introduction Face Recognition Concepts 2D Face recognition Systems An Example 3D Face Recognition Suggestions
4
Introduction What is face recognition? Applications Security applications Security applications Image search engine Image search engine
5
Requirements Accurate Efficient Light invariant Rotation invariant
6
Applications of Face Recognition Desire to locate specific individuals Criminals Criminals TERRORISTS TERRORISTS Missing Children Missing Children Surveillance Surveillance
7
Face Recognition Concepts Enrollment An initial feature set is constructed from the relevant physical traits of the user.
8
Face Recognition Concepts Verification Extracted feature set from each person is compared with the enrollment feature set. If the resulting score value is above a predefined threshold, the user is considered to be authenticated.
9
Face Recognition Concepts Identification In contrast to the verification use case, with identification the (claimed) identity of the user is not known in advance, but shall be determined based on sample images of the user's face and a set (population) of feature sets with known identities.
10
An Example: FaceVACS Architecture Face Localization Eye Localization Image Quality Check Normalization Preprocessing Feature Extraction Construction of the Reference Set Comparison
11
Face Recognition Concepts The Facial Identification Record (FIR) In the result of processing the raw samples (images), e.g. during enrollment, feature sets are created. In the context of FaceVACS-SDK we use the term FIR for these feature sets.
12
Face Recognition Concepts Enrollment and Verification
13
Face Recognition Concepts FAR, FRR and EER FAR (False Acceptance Rate) is the probability that a sample falsely matches the presented FIR. FRR (False Rejection Rate) is the probability that a sample of the right person is falsely rejected. The value of FAR and FRR at the point where the plots cross is called the Equal Error Rate (EER).
14
Face Recognition Concepts FAR, FRR and EER
15
Face Recognition Systems Feature-Based Appearance-Based Model-Based
16
Feature-Based Algorithms Geometric Features Texture Skin color Multiple features
17
Appearance-Based Algorithms Eigenface Fisherface SVM Neural Networks Hidden Markov Models
18
Model-Based Algorithms Face Bunch Graph Predefined face templates Deformable templates
19
An Example Sample Image
20
An Example Eye location found by the algorithm
21
An Example After Normalization
22
An Example After Preprocessing
23
An Example Extracting local features
24
An Example Forming the reference set of the image
25
Image Database Effective Factors in combining FIRs Influence and arrangement of lighting conditions Sample Quality Orientation of Samples Adornment Face Angle Face Appearance
26
3D Face Recognition
28
Suggestions A comprehensive Survey on 2D Face Recognition Algorithms Face Detection Face Detection Face Segmentation Face Segmentation Feature Extraction Feature Extraction Facial Models Facial Models Texture Analysis Texture Analysis Towards 3D Face Recognition Combining other Biometrics such as Iris Recognition Towards Multimodal Systems
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.