Now OCR is extending its target from scanned documents to scene images. Please look around and find texts around you --- there may be various texts printed in various fonts. Thinking about scene texts will provide us many interesting  problems, which never happened on the conventional OCR for scanned documents.

First, how about recognition of scene texts? It is a difficult and challenging problem because the font shapes are very different from each other even though they come from the same category.  Reviewing the recent scene text/character recognition technologies will introduce us how we can tackle with this huge shape variations.

Second, how about "non-verbal" information given by a specific font? For example, please recall the logo of a famous gorgeous brand. Is the font used in the log the same as that in a toyshop? The answer is, maybe, "no". This suggests that each font has its own "atmosphere", which is typical "non-verbal" information.

Third, how about "visual perception of scene texts?" Most scene texts are put in the scene for providing some message to people. They, therefore, should be "eye-catching", or, visually salient. Recently, this visual saliency is a hot topic of computer vision and thus it is not bad to examine that scene texts are really salient or not.

Fourth, how about concealing texts? Some scene texts, such as a car license plate, are privacy sensitive and we should conceal them before publishing the image containing them. How can we "damage" them to make them unreadable with less side-effect?

Like the above four problems, we can find many other "new" problems around scene texts. I hope that the participants will enjoy discussion on some practical issues and less practical issues on scene texts for a wider view.