Slide 1

Overview of Visit
Morning: Image Database Retrieval
Gatekeeper: Face detection and recognition
Complex Feature Image Database Retrieval (Tieu)
Flexible Template Retrieval (Yu)
Interlude
Video/Audio Source Separation (Fisher)
Mathematical Expression Recognition (Matsakis)
Lunch
Visit Prof. Brooks lab

Overview of Visit - 2
Afternoon: Variable Viewpoint Reality
Real-time 3D reconstruction of people (Snow)
Automatic camera calibration (Snow + Lee)
Tracking of articulate human models (Lee + Winn)
Modeling of human dynamics (Viola + Fisher)

Gatekeeper:
  Receptionist
      & Security
Greet guests
Direct people to their destinations
Recognize employees
Turn back unauthorized visitors

Gatekeeper in action …

Gatekeeper is a
  constant observer…

Detecting faces is very difficult

Detecting and Recognizing Faces
Key Difficulty: Variation in Pose
State of the art:  generalized templates
Neural Networks / Deformable Templates / etc.
Templates have difficulty with pose variation…
Rotation, scale, complex deformation
Must reduce the dependence on relative pose.
Approach: Detecting people as a statistical   distribution of multi-scale features

Statistical Distribution
of Multi-scale Features

Slide 10

Discrimination via Cross Entropy

Motivation: Finding vehicles in clutter

Can also be used for segmentation…

Slide 14

Slide 15

Slide 16

Slide 17

Slide 18

Slide 19

Slide 20

Slide 21

Slide 22

Slide 23

Detection Results

Pruning the density estimator

Key facial features
- determined automatically
- located automatically

Another key feature

New Face Recognition Algorithm
Measure the occurrence and location of “key” facial features.
Facial identity depends both on the types of features and their location.
Relation to Active Search…
Match measure is a histogram of multiscale features
Like color histogram,  Active Search can be used...

Presentation on Image Database Technology