DocumentCode :
796025
Title :
On the sensitivity of the Hough transform for object recognition
Author :
Grimson, W. Eric L ; Huttenlocher, Daniel P.
Author_Institution :
MIT Artificial Intelligence Lab., Cambridge, MA, USA
Volume :
12
Issue :
3
fYear :
1990
fDate :
3/1/1990 12:00:00 AM
Firstpage :
255
Lastpage :
274
Abstract :
Object recognition from sensory data involves, in part, determining the pose of a model with respect to a scene. A common method for finding an object´s pose is the generalized Hough transform, which accumulates evidence for possible coordinate transformations in a parameter space whose axes are the quantized transformation parameters. Large clusters of similar transformations in that space are taken as evidence of a correct match. A theoretical analysis of the behavior of such methods is presented. The authors derive bounds on the set of transformations consistent with each pairing of data and model features, in the presence of noise and occlusion in the image. Bounds are provided on the likelihood of false peaks in the parameter space, as a function of noise, occlusion, and tessellation effects. It is argued that haphazardly applying such methods to complex recognition tasks is risky, as the probability of false positives can be very high
Keywords :
pattern recognition; picture processing; sensitivity; transforms; Hough transform; coordinate transformations; false peak likelihood bound; false positives; noise; object recognition; occlusion; pattern recognition; picture processing; sensitivity; sensory data; tessellation effects; Artificial intelligence; Clustering methods; Contracts; Helium; Image recognition; Laboratories; Layout; Object recognition; Robot kinematics; Robot vision systems;
fLanguage :
English
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
Publisher :
ieee
ISSN :
0162-8828
Type :
jour
DOI :
10.1109/34.49052
Filename :
49052
Link To Document :
بازگشت