Document image summarization without OCR

A system for selecting excerpts directly from imaged text without performing optical character recognition is described. The images are segmented to find text regions, text lines and words, and sentence and paragraph boundaries are identified. A set of word equivalence classes is computed based on the rank blur hit-miss transform. This information is used to identify stop words and keywords. Sentences for presentation as part of a summary are then selected based on keywords and on the location of the sentences. Figure 1 outlines the steps in performing text image summarization. In the next two sections, we describe the image processing and summary image selection techniques used to create a summary. Word images are grouped into equivalence classes based on shape similarity, which can be performed much more quickly than OCR. Stop words are identified based on statistical characteristics of the word equivalence classes in each document. The location of sentence and paragraph boundaries are used, along with statistical informationon the words, to generate summary scores for each sentence.