Contour Fragments

Contour-Based Learning:

A two-stage, partially supervised learning architecture is proposed:

  1. a rudimentary detector is learned from a very small set of segmented images and applied to a larger training set of unsegmented images;
  2. the second stage bootstraps these detections to learn an improved classifier while explicitly training against clutter



scale matter: 

  • Image patterns of different statistical properties are connected by scale
  • change of viewing distance
  • change of camera resolution
  • Change of statistical/information



  1. Smoothing reduces entropy rate (by small fixed amount)
  2. Subsampling increases entropy rate (can be big)
•Different image patterns reside in different entropy regimes
•Different entropy regimes are connected by scaling
•Different statistical models within a common framework



Mid-Entropy regime


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s


Just another site

Jing's Blog

Just another site

Start from here......







Just another site

Where On Earth Is Waldo?

A Project By Melanie Coles

the Serious Computer Vision Blog

A blog about computer vision and serious stuff

Cauthy's Blog

paper review...

Cornell Computer Vision Seminar Blog

Blog for CS 7670 - Special Topics in Computer Vision


Life through nerd-colored glasses

Luciana Haill

Brainwaves Augmenting Consciousness



Dr Paul Tennent

and the university of nottingham

turn off the lights, please

A bunch of random, thinned and stateless thoughts around the Web

John's Weblog

Just another weblog

I Am That I Am

Chasing tomorrow's sunrise.

%d bloggers like this: