Bringing the grandmother back into the picture: A memory-based view of object recognition
We describe experiments with a versatile pictorial prototype-based learning scheme for 3-D
object recognition. The Generalized Radial Basis Function (GRBF) scheme seems to be …
object recognition. The Generalized Radial Basis Function (GRBF) scheme seems to be …
[PDF][PDF] HyperBF Networks for Real Object Recognition.
R Brunelli, TA Poggio - IJCAI, 1991 - researchgate.net
Even if represented in a way which is invariant to illumination conditions, a 3D object gives
rise to an infinite number of 2D views, depending on its pose. It has been recently shown …
rise to an infinite number of 2D views, depending on its pose. It has been recently shown …
Three-dimensional object recognition using an unsupervised BCM network: The usefulness of distinguishing features
N Intrator, JI Gold - Neural Computation, 1993 - direct.mit.edu
We propose an object recognition scheme based on a method for feature extraction from
gray level images that corresponds to recent statistical theory, called projection pursuit, and …
gray level images that corresponds to recent statistical theory, called projection pursuit, and …
Real-time 3-D object classification using a learning system
R Rimey, P Gouin, C Scofield… - Intelligent Robots and …, 1987 - spiedigitallibrary.org
We describe some experiments in real-time 3-D object classification using a learning system
derived from a general neural model for supervised learning. The primary advantages of the …
derived from a general neural model for supervised learning. The primary advantages of the …
Unsupervised and supervised learning in radial-basis-function networks
Learning in radial basis function (RBF) networks is the topic of this chapter. Whereas
multilayer perceptrons (MLP) are typically trained with backpropagation algorithms, starting …
multilayer perceptrons (MLP) are typically trained with backpropagation algorithms, starting …
[PDF][PDF] Tutorial: Algorithms for 2-dimensional object recognition
A Ashbrook, NA Thacker - Imaging Science and …, 1998 - imageprocessingplace.com
1 Abstract Representation of arbitrary shape for purposes of visual recognition is an
unsolved problem. The task of representation is intimately constrained by the recognition …
unsolved problem. The task of representation is intimately constrained by the recognition …
Higher-order neural networks applied to 2D and 3D object recognition
L Spirkovska, MB Reid - Machine Learning, 1994 - Springer
A higher-order neural network (HONN) can be designed to be invariant to geometric
transformations such as scale, translation, and in-plane rotation. Invariances are built …
transformations such as scale, translation, and in-plane rotation. Invariances are built …
Hausdorff kernel for 3D object acquisition and detection
Learning one class at a time can be seen as an effective solution to classification problems
in which only the positive examples are easily identifiable. A kernel method to accomplish …
in which only the positive examples are easily identifiable. A kernel method to accomplish …
[图书][B] 2D object detection and recognition: models, algorithms, and networks
Y Amit - 2002 - books.google.com
A guide to the computer detection and recognition of 2D objects in gray-level images. Two
important subproblems of computer vision are the detection and recognition of 2D objects in …
important subproblems of computer vision are the detection and recognition of 2D objects in …
Learning and recognizing 3D objects from multiple views in a neural system
M Seibert, AM Waxman - Neural networks for perception, 1992 - Elsevier
Publisher Summary This chapter focuses on learning and recognizing 3D objects from
multiple views in a neural system. In this approach of designing a 3D object recognition …
multiple views in a neural system. In this approach of designing a 3D object recognition …