April 26, 2007
Using Computer Vision in Real Applications: Two Success Stories
Gerard Medioni
This classic paper has been recognized as the best machine-vision paper of the decade.
Editor's Note: We're privleged to present this paper entitled "Using Computer Vision in Real Applications: Two Success Stories" by Dr. Gerard Medioni. Written nearly a decade ago and first presented at the International Association of Pattern Recognition Workshop on Application of Computer Vision in November 1996, Dr. Medioni's paper was recently honored as the the most influential machine vision paper of the decade. We'd like to thank Dr. Medioni, who is currently chair of the Department of Computer Science at the University of Southern California, for sharing this paper. Please note that this is an early, uncorrected version of the paper that does not include references. Nor are all illustrations that accompany this paper available.
Abstract
We present two systems which are used today in industrial applications. While they are very different, and the two domains have no overlap, they share the properties that the problems they address were considered very hard to solve, and the requirements were very constraining, especially complete automation. We present first a system which automatically registers two sets of halftone color separations used to produce color pictures. The challenges involve accuracy, speed of processing, and consistency with human operators. The second system substitutes, in real-time, a given billboard in a video stream, by another, synthetically generated billboard. The challenges involve realtime performance and photorealism. For each of the two systems, we provide some background, describe the requirements and the issues, then the implemented solution.
1 Introduction
|
2 Alignment of Four Color Separations
|
3 1.2 Requirements and Challenges
|
4 Implemented Solution
|
5 2 Billboard Replacer
|
6 2.2 Requirements and Challenges
Next Page
more
