A Caltech Library Service

Unsupervised learning of models for object recognition


Weber, Markus (2000) Unsupervised learning of models for object recognition. Dissertation (Ph.D.), California Institute of Technology. doi:10.7907/ec32-c786.


A method is presented to learn object class models from unlabeled and unsegmented cluttered scenes for the purpose of visual object recognition. The variability across a class of objects is modeled in a principled way, treating objects as flexible constellations of rigid parts (features). Variability is represented by a joint probability density function (pdf) on the shape of the constellation and the output of part detectors. Corresponding "constellation models" can be learned in a completely unsupervised fashion. In a first stage, the learning method automatically identifies distinctive parts in the training set by applying a clustering algorithm to patterns selected by an interest operator. It then learns the statistical shape model using expectation maximization. Mixtures of constellation models can be defined and applied to "discover" object categories in an unsupervised manner. The method achieves very good classification results on human faces, cars, leaves, handwritten letters, and cartoon characters.

Item Type:Thesis (Dissertation (Ph.D.))
Subject Keywords:Computation and Neural Systems
Degree Grantor:California Institute of Technology
Division:Engineering and Applied Science
Major Option:Computation and Neural Systems
Thesis Availability:Public (worldwide access)
Research Advisor(s):
  • Perona, Pietro
Thesis Committee:
  • Unknown, Unknown
Defense Date:1 May 2000
Record Number:CaltechTHESIS:10052010-115540388
Persistent URL:
Default Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:6095
Deposited By: Dan Anguka
Deposited On:05 Oct 2010 20:07
Last Modified:08 Nov 2023 00:44

Thesis Files

PDF - Final Version
See Usage Policy.


Repository Staff Only: item control page