Shape from focus using multilayer feedforward neural networks

The conventional shape-from-focus (SFF) methods have inaccuracies because of piecewise constant approximation of the focused image surface (FIS). We propose a scheme for SFF based on representation of three-dimensional (3-D) FIS in terms of neural network weights. The neural networks are trained to...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on image processing 2001-11, Vol.10 (11), p.1670-1675
Main Authors: Asif, M., Tae-Sun Choi
Format: Article
Language:English
Subjects:
Applied sciences
Approximation
Artificial intelligence
Cameras
Computational efficiency
Computer science
control theory
systems
Connectionism. Neural networks
Exact sciences and technology
Feedforward
Feedforward neural networks
Focusing
Geometry
Image processing
Information, signal and communications theory
Lagrangian functions
Mathematical analysis
Multi-layer neural network
Multilayers
Neural networks
Pattern recognition. Digital image processing. Computational geometry
Polynomials
Representations
Shape measurement
Signal processing
Telecommunications and information theory
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The conventional shape-from-focus (SFF) methods have inaccuracies because of piecewise constant approximation of the focused image surface (FIS). We propose a scheme for SFF based on representation of three-dimensional (3-D) FIS in terms of neural network weights. The neural networks are trained to learn the shape of the FIS that maximizes the focus measure.
ISSN:1057-7149
1941-0042
DOI:10.1109/83.967395