Loading presentation...

Present Remotely

Send the link below via email or IM

Copy

Present to your audience

Start remote presentation

  • Invited audience members will follow you as you navigate and present
  • People invited to a presentation do not need a Prezi account
  • This link expires 10 minutes after you close the presentation
  • A maximum of 30 users can follow your presentation
  • Learn more about this feature in our knowledge base article

Do you really want to delete this prezi?

Neither you, nor the coeditors you shared it with will be able to recover it again.

DeleteCancel

Make your likes visible on Facebook?

Connect your Facebook account to Prezi and let your likes appear on your timeline.
You can change this under Settings & Account at any time.

No, thanks

A Smart Classroom Supervision System (Second Presentation)

Fall project based on image processing knowledge using c++ and OpenCV.
by

Marwa MEDDEB

on 28 September 2012

Comments (0)

Please log in to add your comment.

Report abuse

Transcript of A Smart Classroom Supervision System (Second Presentation)

A Smart Classroom Supervision System Fall Project 2012
Marwa MEDDEB Supervisors:
Jean-Luc DUGELAY
Xuran ZHAO Background subtraction Techniques Objectives
Techniques
Experimental Results
Conclusion & Future Work Face detection Face recognition Background Subtraction Face detection Face recognition Experimental results Static images
Difference (Empty & Full classroom)
Thresholding (Background & Foreground)
Morphological transformations (Smooth & Dilate)
Foreground reconstruction Objectives Reduce False detection Identify present persons Localize the faces Detect faces positions
Mark the faces
Count the persons


Crop and rotate the face
Save the faces for next step Testing & Coding Limits Tests Tests & Interpretations ...
Computing the Database features

Computing the test feature

Identify the closest feature Database LBP features ok ok Error in background subtraction

No detection

Wrong identification

Small amount of data for training and test

Test images of low resolution Bad performance in face recognition
No detection in particular cases

No false detection
Fast computations Interpretation Conclusion & Future work Collect more data of good quality
More performance tests
Making a real time detection
Prepare a user-machine interface http://clickdamage.com/sourcecode/index.php

http://makematics.com/research/viola-jones/

http://opencv.willowgarage.com/wiki/FaceDetection

http://www.face-rec.org/algorithms/ References Thank you for your attention A Smart Classroom Supervision System 1 2 3 4 6 8 9 10 11 12 13 14 15 Face recognition Local Binary Pattern approach 5 Face detection Haar features
An integral image
AdaBoost machine learning
A cascade classifier 7 September 28, 2012
Full transcript