Turbo recognition: a statistical approach to layout analysis

Taku A. Tokuyasu; Philip A. Chou

doi:10.1117/12.410829

21 December 2000 Turbo recognition: a statistical approach to layout analysis

Taku A. Tokuyasu, Philip A. Chou

Proceedings Volume 4307, Document Recognition and Retrieval VIII; (2000) https://doi.org/10.1117/12.410829
Event: Photonics West 2001 - Electronic Imaging, 2001, San Jose, CA, United States

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.

Citation Download Citation

Taku A. Tokuyasu and Philip A. Chou "Turbo recognition: a statistical approach to layout analysis", Proc. SPIE 4307, Document Recognition and Retrieval VIII, (21 December 2000); https://doi.org/10.1117/12.410829

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available