Character string extraction from newspaper headlines with a background design by recognizing a combination of connected components

Abstract

In this paper we propose a new method of extracting a character string from images with a background design. In Japanese newspaper headlines, it is common for character components to be placed independent of background components. In view of this, we represent a character string candidate as a consistent combination of connected components, and we calculate its character string resemblance value. In this case, a character string resemblance value of a combination of connected components depends upon its character recognition result and the area of the rectangular area occupied by it. We then extract the combination of connected components that has the maximum character string resemblance value. We applied this method to 142 headline images. The results show that the method accurately extracted a character string from various kinds of images with a background design and the method has a favorable processing speed.

Restoration of Decorative Headline Images for Document Retrieval

“…However, conventional OCRs cannot recognize the characters, because headlines are often printed in reverse and with background textures. To deal with such decorative images, a preprocess that restores "normal images [3,4,5] and recognition algorithm that is not affected by the decorations [6] have been proposed. We think the former is superior in that it can be easily incorporated into existing systems.…”