Share Email Print

Proceedings Paper

Turbo recognition: a statistical approach to layout analysis
Author(s): Taku A. Tokuyasu; Philip A. Chou
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Turbo recognition (TR) is a communication theory approach to the analysis of rectangular layouts, in the spirit of Document Image Decoding. The TR algorithm, inspired by turbo decoding, is based on a generative model of image production, in which two grammars are used simultaneously to describe structure in orthogonal (horizontal and vertical directions. This enables TR to strictly embody non-local constraints that cannot be taken into account by local statistical methods. This basis in finite state grammars also allows TR to be quickly retargetable to new domains. We illustrate some of the capabilities of TR with two examples involving realistic images. While TR, like turbo decoding, is not guaranteed to recover the statistically optimal solution, we present an experiment that demonstrates its ability to produce optimal or near-optimal results on a simple yet nontrivial example, the recovery of a filled rectangle in the midst of noise. Unlike methods such as stochastic context free grammars and exhaustive search, which are often intractable beyond small images, turbo recognition scales linearly with image size, suggesting TR as an efficient yet near-optimal approach to statistical layout analysis.

Paper Details

Date Published: 21 December 2000
PDF: 7 pages
Proc. SPIE 4307, Document Recognition and Retrieval VIII, (21 December 2000); doi: 10.1117/12.410829
Show Author Affiliations
Taku A. Tokuyasu, Univ. of California/Berkeley (United States)
Philip A. Chou, Microsoft Corp. (United States)

Published in SPIE Proceedings Vol. 4307:
Document Recognition and Retrieval VIII
Paul B. Kantor; Daniel P. Lopresti; Jiangying Zhou, Editor(s)

© SPIE. Terms of Use
Back to Top