Hybrid Page Layout Analysis via Tab-Stop Detection

A new hybrid page layout analysis algorithm is proposed, which uses bottom-up methods to form an initial data-type hypothesis and locate the tab-stops that were used when the page was formatted. The detected tab-stops, are used to deduce the column layout of the page. The column layout is then applied in a top-down manner to impose structure and reading-order on the detected regions. The complete C++ source code implementation is available as part of the Tesseract open source OCR engine at http://code.google.com/p/tesseract-ocr.

1. Introduction

Physical Page layout analysis, one of the first steps of OCR, divides an image into areas of text and non-text, as well as splitting multi-column text into columns. This paper does not address logical layout analysis, which detects headers, footers, body text, numbered lists, and segmentation into articles.