Face Recognition: Evaluation Report for FaceIt Identification and Surveillance - PowerPoint PPT Presentation

1 / 17
About This Presentation
Title:

Face Recognition: Evaluation Report for FaceIt Identification and Surveillance

Description:

Distance(Low resolution Image) 13. Overall Test (Small DB,Large Variations, High Frontal Lighting) 14. Example of Captured images ... – PowerPoint PPT presentation

Number of Views:81
Avg rating:3.0/5.0
Slides: 18
Provided by: ece4
Category:

less

Transcript and Presenter's Notes

Title: Face Recognition: Evaluation Report for FaceIt Identification and Surveillance


1
Face Recognition Evaluation Report for FaceIt
Identification and Surveillance
Jingu Heo The department of Electrical Computer
Engineering The University of Tennessee,
Knoxville
2
FaceIt Identification Template
2. Select a Subject
1. Create Gallery
3.Matching
3
Overall Test with FERET and IRIS DB
4
Detailed Tests- Expression Illumination
5
Detailed Tests Age
6
Detailed Tests -Pose
7
Detailed Tests Head Size
8095
90110
100120
125150
150180
1012
2024
3036
4048
5065
6072
7085
256384 pixels Actual Size
8
Detailed Tests Head Size
Auto aligning Fails
Auto aligning -gt At least 20 pixels between the
eyes
7085
8095
150180
125150
100120
90110
1012
6072
3036
2024
5065
4048
9
Detailed Tests Head Size
Head size Test (Gallery(ba)-200, Subject(Cropped
ba)-200)
10
Summary of FaceIt Identification Results
11
FaceIt Surveillance Template
1. Create Gallery
2. Capture faces from Video
3. Matching
12
FaceIt Surveillance Test
  • Overall Test - IRIS, FERET
  • 758 captured faces / 13 individuals
  • Distance 23ft from the camera
  • Detailed Test IRIS, FERET
  • Facial Variations (Small or Large)
  • Database size(Small or Large)
  • Different Illumination
  • Distance(Low resolution Image)

13
Overall Test (Small DB,Large Variations,
HighFrontal Lighting)
14
Example of Captured images
15
Detailed Tests DB size and Variations
16
Detailed Tests Lighting and Distance
17
Conclusion
  • Some faces which has more distinctive features
    are more easily recognized than others.
  • Mixed variations(AgePose Illumination
    Expressions) affects more than single variation
  • Face size is not big problem as long as the
    features are clear.
  • Small DB, small variation, high and additional
    frontal lighting and frontal faces give us the
    best reliability.

Write a Comment
User Comments (0)
About PowerShow.com