Recognizing Text Elements for SVG Comic Compression and Its Novel Applications

Abstract

SVG (scalable vector graphics) has become the standard format for 2D graphics in HTML5. Although some image-to-SVG conversion systems had been proposed, the sizes of files they produced are still large. In [1], we proposed a new system to convert raster comic images into vector SVG files. The compression ratio is better than the previous methods. However, these methods do not process text in raster images. In this paper, we improve our system to recognize text elements in the comic and use these text elements to provide better compression and novel applications. The proposed method uses SCW (sliding concentric windows) and SVM (support vector machine) to identify text regions. Then, OCR (optical character recognition) is applied to recognize text elements in those regions. Instead of encoding the text regions as vectors, the text elements are embedded in the SVG file along with their coordinate values. Experimental results show that we can reduce the file sizes to about 52% of the original SVG files. Using these text elements, we can translate comics into other languages to provide multilingual services easily. Text/content-based image search can be supported efficiently. It can also provide a novel application system for story teller.

Semi-automatic Text and Graphics Extraction of Manga Using Eye Tracking Information

“…Text analysis in manga images opens up several interesting applications such as image compression [13] and content retargeting to different mobile reading devices [14]. Despite the growing interest, text extraction from manga image remains a challenging problem because mangas are a mixture of text, graphics and graphic sounds with strong relationships [15].…”

Toward speech text recognition for comic books

“…In another paper [11], a method to recognize text elements in comic was proposed. The proposed method uses a sliding concentric windows (SCW) and support vector machine (SVM) based approach to identify text regions.…”

Digital Comics Image Indexing Based on Deep Learning

“…First, bottom-up approaches based on binary segmentation, connected component extraction and labeling were proposed by Ponsard et al [24]. Su et al used Sliding Concentric Windows for text/graphic separation and then mathematical morphology and an SVM classifier to classify text from non-text components [37]. An adaptive binarisation process based on minimum connected component thresholding followed by a text/graphic separation based on contrast ratio and text line grouping was proposed by our team in 2013 [38].…”