Journal ArticleDOI
Coarse-to-fine adaptive masks for appearance matching of occluded scenes
J. L. Edwards,J. Murase +1 more
- Vol. 10, Iss: 5, pp 232-242
Reads0
Chats0
TLDR
Results are presented which demonstrate that an iterative, coarse-to-fine sum-squared-error method that uses information from hypothesized occlusion events to perform run-time modification of scene- to-template similarity measures is reasonably robust over a large database of color test scenes containing objects at a variety of scales and tolerates minor 3D object rotations and global illumination variations.Abstract:
In this paper, we discuss an appearance-matching approach to the difficult problem of interpreting color scenes containing occluded objects. We have explored the use of an iterative, coarse-to-fine sum-squared-error method that uses information from hypothesized occlusion events to perform run-time modification of scene-to-template similarity measures. These adjustments are performed by using a binary mask to adaptively exclude regions of the template image from the squared-error computation. At each iteration higher resolution scene data as well as information derived from the occluding interactions between multiple object hypotheses are used to adjust these masks. We present results which demonstrate that such a technique is reasonably robust over a large database of color test scenes containing objects at a variety of scales, and tolerates minor 3D object rotations and global illumination variations.read more
Citations
More filters
Book
Template Matching Techniques in Computer Vision: Theory and Practice
TL;DR: This book and the accompanying website, focus on template matching, a subset of object recognition techniques of wide applicability, which has proved to be particularly effective for face recognition applications.
Journal ArticleDOI
Robust active appearance models and their application to medical image analysis
TL;DR: A novel robust AAM (RAAM) matching algorithm that tolerates up to 50% object area covered by gross gray-level disturbances and an objective function is utilized for the selection of a mode combination not representing the gross outliers.
Journal ArticleDOI
A Comparison of Probabilistic, Possibilistic and Evidence Theoretic Fusion Schemes for Active Object Recognition
TL;DR: This work uses an appearance based object representation, namely the parametric eigenspace, but the planning algorithm is actually independent of the details of the specific object recognition environment, so that the probabilistic implementation always outperforms the other approaches.
Journal ArticleDOI
Weighted and robust learning of subspace representations
TL;DR: A weighted version of PCA is presented, which, unlike the standard approach, considers individual pixels and images selectively, depending on the corresponding weights, and a robust PCA method is proposed for obtaining a consistent subspace representation in the presence of outlying pixels in the training images.
Journal ArticleDOI
Representation and Recognition of 3D Free-Form Objects
George Mamic,Mohammed Bennamoun +1 more
TL;DR: This paper describes and analyzes techniques which have been developed for object representation and recognition and proposes a set of specifications, which all object recognition systems should strive to meet.
References
More filters
Book
Introduction to Statistical Pattern Recognition
TL;DR: This completely revised second edition presents an introduction to statistical pattern recognition, which is appropriate as a text for introductory courses in pattern recognition and as a reference book for workers in the field.
Proceedings ArticleDOI
Face recognition using eigenfaces
Matthew Turk,Alex Pentland +1 more
TL;DR: An approach to the detection and identification of human faces is presented, and a working, near-real-time face recognition system which tracks a subject's head and then recognizes the person by comparing characteristics of the face to those of known individuals is described.
Journal ArticleDOI
Face recognition: features versus templates
Roberto Brunelli,Tomaso Poggio +1 more
TL;DR: Two new algorithms for computer recognition of human faces, one based on the computation of a set of geometrical features, such as nose width and length, mouth position, and chin shape, and the second based on almost-gray-level template matching are presented.
Journal ArticleDOI
Visual learning and recognition of 3-D objects from appearance
Hiroshi Murase,Shree K. Nayar +1 more
TL;DR: A near real-time recognition system with 20 complex objects in the database has been developed and a compact representation of object appearance is proposed that is parametrized by pose and illumination.
Journal ArticleDOI
Smart sensing within a pyramid vision machine
TL;DR: A machine is designed, based on a pyramid architecture, that supports smart sensing and related highly efficient processing that achieves high performance at modest cost.
Related Papers (5)
Detectability, uniqueness, and reliability of eigen windows for stable verification of partially occluded objects
K. Ohba,Katsushi Ikeuchi +1 more