RI | Research | Projects | Object Recognition Using Statistical Modeling

Text only version of this site

Object Recognition Using Statistical Modeling Heads: Henry Schneiderman and Takeo Kanade Contact: Henry Schneiderman (hws@ux1.sp.cs.cmu.edu) Mailing address: Carnegie Mellon University Robotics Institute 5000 Forbes Avenue Pittsburgh, PA 15213 Associated center: VASC Associated lab/group: Face Group For more information, see this project's homepage.

This page last updated - January 1999.

Project Description

We are developing a human face detector and an automobile detector. Our method for both off these problems is based on a statistical decision model involving the statistics of over 100,000 patterns. We gather statistics of two probability distributions: the joint distribution of pattern and location on the object, P(pattern, x, y | object), and the joint distribution of pattern and location for the rest of world, P(pattern, x, y | non-object). Since pattern, x, and y take on a finite set of values, we collect each set of statistics by using a multidimensional histogram. We collect the histogram P(pattern, x, y | object) from a representative set of images of the object. Similarly, we collect P(pattern, x, y | non-object) from a representative set of images that do not contain the object. We then use these probability distributions to classify image regions as "object" or "non-object" by applying Bayes decision rule. With this approach, we have developed the most accurate frontal face detector currently in existence.

Personnel [Past Members]

	Name	Title	Email Address
	Takeo Kanade	U.A. and Helen Whitaker University Prof., RI/CS	tk@cs.cmu.edu
	Henry Schneiderman	Adjunct Faculty (Adjunct)	hws@ux1.sp.cs.cmu.edu

Publications

Note: This list may not be comprehensive. It contains only those publications in the RI publications database. Entries are listed in reverse chronological order.

• Geometric Context from a Single Image
  D. Hoiem, A.A. Efros, and M. Hebert
  International Conference of Computer Vision (ICCV), IEEE, Vol. 1, October, 2005, pp. 654 - 661. [Abstract]
  Download: pdf [8387 KB] copyrighted

• Feature-Centric Evaluation for Efficient Cascaded Object Detection
  H. Schneiderman
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, June, 2004. [Abstract]
  Download: pdf [469 KB] copyrighted

• Learning a Restricted Bayesian Network for Object Detection
  H. Schneiderman
  IEEE Conference on Computer Vision and Pattern Recognition, IEEE, June, 2004. [Abstract]
  Download: pdf [567 KB] copyrighted

• Object-Based Image Retrieval using the Statistical Structure of Images
  D. Hoiem, R. Sukthankar, H. Schneiderman, and L. Huston
  IEEE Conference on Computer Vision and Pattern Recognition, Vol. 2, June, 2004, pp. 490 - 497. [Abstract]
  Download: pdf [561 KB] copyrighted

• Learning Statistical Structure for Object Detection
  H. Schneiderman
  Computer Analysis of Images and Patterns (CAIP), 2003, Springer-Verlag, August, 2003. [Abstract]
  Download: pdf [320 KB] copyrighted

• Object Detection Using the Statistics of Parts
  H. Schneiderman and T. Kanade
  International Journal of Computer Vision, 2002. [Abstract]
  Download: pdf [3828 KB] copyrighted

• A histogram-based method for detection of faces and cars
  H. Schneiderman and T. Kanade
  Proceedings of the 2000 International Conference on Image Processing (ICIP '00), Vol. 3, September, 2000, pp. 504 - 507. [Abstract]
  Download: pdf [437 KB] copyrighted

• A Statistical Model for 3D Object Detection Applied to Faces and Cars
  H. Schneiderman and T. Kanade
  IEEE Conference on Computer Vision and Pattern Recognition, IEEE, June, 2000. [Abstract]
  Download: pdf [474 KB], ps.gz [1662 KB] copyrighted

• A Statistical Approach to 3D Object Detection Applied to Faces and Cars
  H. Schneiderman
  doctoral dissertation, tech. report CMU-RI-TR-00-06, Robotics Institute, Carnegie Mellon University, May, 2000. [Abstract]
  Download: pdf [1947 KB], ps.gz [5938 KB] copyrighted

• Probabilistic Modeling of Local Appearance and Spatial Relationships for Object Recognition
  H. Schneiderman and T. Kanade
  Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR '98), July, 1998, pp. 45-51. [Abstract]
  Download: pdf [255 KB], ps.gz [787 KB] copyrighted