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

Recognizing Key Facial Points

Exploration in facial keypoint detection - https://github.com/WillahScott/facial-keypoint-detection
by

Guillermo Monge

on 26 April 2016

Comments (0)

Please log in to add your comment.

Report abuse

Transcript of Recognizing Key Facial Points

Recognizing Key Facial Points
Goal
Identify the location of key facial features in an image
Challenges
Our Approach
Raw Data
No preprocessing
Convolutional Neural Net
Preprocessing
Neural Nets
Logistic Regression
Random Forest
Bayes Classifiers
Decision Trees
Average Ensembling
Ensemble Methods
Haar Classifier
Face Detection
Noise Filtering
Dimensionality Reduction
Image Processing
PCA
GMM
EigenFaces
Edge Detection
Noise Reduction
Finding Contours
GitHub REPO
Conclusions
This was a fun ride :)
Thank you!

our results
Sobel Filters
Laplace Transform
Gaussian Blur
Histogram of Oriented Gradients
Data
Scripts
Data
Preprocessed
Models
Submissions
Tools
Explorations
Preprocessors
Modelers
Environments
Base
OpenCV
Theano + Lasagne
Watershed algorithm
Region Adjacency Graph
95%
150 components
96%
93%
96.2%
?
90%
Significant improvements in execution and memory with careful data typing
Preprocessing improvements with SOME of the models (i.e. Logistic Regression)
Complex models (CNN) beyond our resource ability
Improvements
:

+ Exploit model dependence
+ Focus on simple preprocessors
Full transcript