Rgb level face detection
This presentation is the property of its rightful owner.
Sponsored Links
1 / 23

RGB Level Face Detection PowerPoint PPT Presentation


  • 83 Views
  • Uploaded on
  • Presentation posted in: General

RGB Level Face Detection. Jian Zhang Miao He Jing Chen May.27th,2002. How to find faces?. Mission Analysis. lots of faces in the images, time-consuming to search the face candidates, some faces got overlapped

Download Presentation

RGB Level Face Detection

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.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -

Presentation Transcript


Rgb level face detection

RGB Level Face Detection

Jian Zhang

Miao He

Jing Chen

May.27th,2002


How to find faces

How to find faces?


Mission analysis

Mission Analysis

  • lots of faces in the images, time-consuming to search the face candidates, some faces got overlapped

  • sidelight instead of diffused light. Influence from shade, complexion, rotation of face, and the inhomogeneity of background

  • 1280*960 high resolution image, slows down the detection speed and more noise


2 step algorithm

2-step Algorithm

  • 1. Skin Toner Masks

  • 2. Support Vector Machine (SVM)


Skin toner masks 1

Skin Toner Masks (1)

  • Mask based on hue in HSV space


Skin toner masks 2

Skin Toner Masks (2)

  • Mask based on RGB statistics


Skin toner masks 3

Skin Toner Masks (3)

  • Mask for red color


Skin toner masks 4

Skin Toner Masks (4)

  • Mask to remove the ground


Skin toner masks 5

Skin Toner Masks (5)

  • Remove small regions


Skin toner masks 6 final mask

Skin Toner Masks (6)—Final Mask


Svm theory 1

SVM Theory(1)

  • Given the training sample {(xi,di)}, i=1…L, find the Lagrange multipliers {αi}, i=1…L, that maximize the objective function

  • Subject to the constraints

    1)

    2) for i=1,2…L

    Where C is a user-specified positive parameter.


Svm theory 2

SVM Theory(2)

  • The discriminate is


Pre processing

Pre-processing

  • In the tradeoff between speed and accuracy, we choose 12-by-12 and 4 gray scale samples.

  • Eliminating the effect of side light.

  • Histogram equalization


Rgb level face detection

Face Samples in RGB,4,3,2 Gray Scale


Training a svm

Training a SVM

  • a large date set, about 1000 face (different scales and positions) and more than 7000 non-face samples.

  • takes more than 30 hours on the ISL lab computer to get one set of training result.

  • From now on,SVM shows its advantage


Teaching and learning process 1

Teaching and Learning Process(1)


Teaching and learning process 2

Teaching and Learning Process(2)


Our improvement

Our improvement

  • Add rotated face into face data set. Thus we can detect these special faces

  • faces concentrate against non-faces

    B is an observation constant. Thusenhance the detection accuracy.


Testing results 1

Testing Results (1)

  • Now we need merge the detection points to give the final decision. Model the three-scale detection as a diversity situation like in wireless communication channels.


Testing results 2

Testing Results (2)

  • maximum-ratio diversity

  • perform dilation to binary image


Final detection

Final Detection


Further implementation

Further Implementation


Acknowledgement

Acknowledgement

  • The authors want to express out thankfulness to Prof. Girod’s excellent instruction. We all learn a lot from this interesting course.

  • We would also like to thank our teaching assistant, Chuo-ling Chang, for his patience and help.


  • Login