COPYRIGHT:  Copyright 1999, IEE
   RECORD NO.:  6163794 INSPEC Abstract No: B1999-03-6135-170; C1999-03-
                5260B-214
       AUTHOR:  Sipe, M.A.; Casasent, D.
  CORP SOURCE:  Dept. of Electr. & Comput. Eng., Carnegie Mellon Univ., 
                Pittsburgh, PA, USA
        TITLE:  Global feature space neural network for active computer 
                vision
       SOURCE:  Neural Computing & Applications, vol.7, no.3, p. 195-
                215
         ISSN:  0941-0643
        CODEN:  NCAPF5
PLACE OF PUBL:  UK
     LANGUAGE:  English
    PUBLISHER:  Springer-Verlag
         YEAR:  1998
 COPYRIGHT NO:  0941-0643/98/$2.00+0.20
    TREATMENT:  A Application; P Practical
  RECORD TYPE:  Journal Paper
     ABSTRACT:  We advance new active computer vision algorithms based on 
                the Feature Space Trajectory (FST) representations of 
                objects and a neural network processor for computation of 
                distances in global feature space. Our algorithms classify 
                rigid objects and estimate their pose from intensity images. 
                They also indicate how to automatically re-position the 
                sensor if the class or pose of an object is ambiguous from a 
                given viewpoint and they incorporate data from multiple 
                object views in the final object classification. An FST in a 
                global eigenfeature space is used to represent 3D distorted 
                views of an object. Assuming that an observed feature vector 
                consists of Gaussian noise added to a point on the FST, we 
                derive a probability density function for the observation 
                conditioned on the class and poise of the object, Bayesian 
                estimation and hypothesis testing theory are then used to 
                derive approximations to the maximum a posteriori 
                probability pose estimate and the minimum probability of 
                error classifier. Confidence measures for the class and pose 
                estimates, derived using Bayes theory, determine when 
                additional observations are required, as well as where the 
                sensor should be positioned to provide the most useful 
                information (51 Refs.)
  DESCRIPTORS:  active vision; feature extraction; Gaussian noise; 
                image classification; neural net architecture
  IDENTIFIERS:  global feature space neural network; active computer vision; 
                feature space trajectory; neural network processor; object 
                classification; eigenfeature space; Gaussian noise; Bayesian 
                estimation; hypothesis testing theory; maximum a posteriori 
                probability pose estimate; minimum probability; error 
                classifier; Bayes theory
  CLASS CODES:  B6135; C5260B (Computer vision and image processing 
                techniques); C1250M; C1230D (Neural nets); C5290 (Neural 
                computing techniques)