Abstract
Depending on the task, there are huge differences in the difficulties of parallel image processing. The recipe we apply to many images is as follows. Use Aritifical Color to either recognize the target or recognize and remove the background, we then use edge-preseving smoothing on the resulting image, use our "nonlinear disrimination Fourier processing method "to identify and locate the target in the scene, and finally, use the subset that found the target to provide a prototype that suggests the targets’ pose and scale. In this paper, I will illustrate each step.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsAuthor information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Caulfield, H.J. (2009). Invited Talk: What Can We Learn from an Image?. In: Dolev, S., Oltean, M. (eds) Optical SuperComputing. OSC 2009. Lecture Notes in Computer Science, vol 5882. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-10442-8_1
Download citation
DOI: https://doi.org/10.1007/978-3-642-10442-8_1
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-10441-1
Online ISBN: 978-3-642-10442-8
eBook Packages: Computer ScienceComputer Science (R0)