1 / 11

Fast Face Detection with Precise Pose Estimation

Fast Face Detection with Precise Pose Estimation. Presented by Mohamed Aly and Jonathan Lee EE148 June 1, 2006. Algorithm. Pose discretization (x, y, scale, tilt) Course to fine tests Edge/flat detectors Pose estimation. Algorithm. Sample result [Fleuret and Geman]:. Training.

leila-quinn
Download Presentation

Fast Face Detection with Precise Pose Estimation

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Fast Face Detection with Precise Pose Estimation Presented by Mohamed Aly and Jonathan Lee EE148 June 1, 2006

  2. Algorithm • Pose discretization • (x, y, scale, tilt) • Course to fine tests • Edge/flat detectors • Pose estimation

  3. Algorithm • Sample result [Fleuret and Geman]:

  4. Training • Iterative • Zero false positives

  5. Training • Generate images … ORL database, normalized

  6. Detection • 32x32 and 64x64 windows 32x32

  7. Detection • Search tree for each 8x8 block …

  8. Detection • Aggregate poses

  9. Results • Reported (C++) • 92% detection • 50% false alarms • 0.48s runtime • Experimental (Matlab) • ~70% detection • 50% false alarms • 1-10 minute runtime

  10. Results

  11. Improvements • Runtime: Matlab vs.C++ • Image quality / normalization • Better features • Aggregation threshold

More Related