Training an attentional cascade

Details Training an attentional cascade Training an attentional cascade

2004-07-22

2008-10-21

Starks, Jr., Wilbert L (Department: 2129)

Data processing: artificial intelligence

Neural network

Structure

C706S045000

Reexamination Certificate

active

07440930

ABSTRACT:
Methods and apparatus, including computer program products, implementing techniques for training an attentional cascade. An attentional cascade is an ordered sequence of detector functions, where the detector functions are functions that examine a target image and return a positive result if the target image resembles an object of interest and a negative result if the target image does not resemble the object of interest. A positive result from one detector function leads to consideration of the target image by the next detector function, and a negative result from any detector function leads to rejection of the target image. The techniques include training each detector function in the attentional cascade in sequence starting with the first detector function. Training a detector function includes selecting a counter-example set. Selecting a counter-example set includes selecting only images that are at least a minimum difference from an example set.

REFERENCES:
patent: 6770441 (2004-08-01), Dickinson et al.
patent: 6858394 (2005-02-01), Chee et al.
patent: 7020337 (2006-03-01), Viola et al.
patent: 7024033 (2006-04-01), Li et al.
patent: 7033754 (2006-04-01), Chee et al.
patent: 7050607 (2006-05-01), Li et al.
patent: 7194114 (2007-03-01), Schneiderman
Second International Workshop on Statistical and Computational Theories of Vision—Modeling, Learning, Computing, and Sampling, “Robust Real-Time Object Detection” Abstract, Vancouver,Canada, Jul. 31, 2001 (pp. 1-20).
Accepted Conference on Computer Vision and Pattern Recognition 2001, “Rapid Object Detection Using a Boosted Cascade of Simple Features,” 2001 (pp. 1-9).
“Model-Based Matching by Linear Combinations of Prototypes,” 1995, (pp. 1-9).
Wu et al., “Learning A Rare Event Detection Cascase by Direct Feature Selection,” Abstract, College of Computing and GVU Center, Georgia Institute of Technology, 2003, (pp. 1-8).
Andrew King, “A Survey of Methods for Face Detection,” 2003, (pp. 1-32).
Yen-Yu Lin, et al., “Fast Object Detection with Occlusions,” Inst. Of Information Science, Academia Sinica, Nankang, Taipei, Taiwan, 2004 (pp. 402-413).
R. Xiao et al., “Boosting Chain Learning for Object Detection,” IEEE Computer Society, Proceedings of the Ninth IEEE International Conference on Computer Vision, (ICCV 2003) 2-Volume Set 0-7695-1950-4/03, 7 pages.

Affiliated with

Also associated with

Rating

Training an attentional cascade does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Training an attentional cascade, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Training an attentional cascade will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-4005535