Invited Speakers

Jin Hyung Kim

Scene Text Recognition : An informal comparison of KAIST Approaches with Google Goggles App on difficult images

Three approaches for scene text recognition will be presented in this talk: color-based, edge-based, and part-based approaches. Although features of color, edge and part-relationship are utilized in all of the three approaches, there are differences on the main focus in each of these approaches. The color-based approach focuses on image segmentation mainly based on color, while the edge-based approach focuses on edge following to extract text objects. The part-based approach is an attempt to directly pin point existence of character parts in image. Each of the three approaches has merits and demerits. The text extraction results of these approaches will be compare with Google Goggles on some representative images known 'difficult' in the community. So, one may feel how these approaches behave in difficult images.

---

Yoshifumi Masunaga

Social Computing and the Development of WikiBOK

"Social computing" is a keyword in contemporary society. However, if we ask anew what the term social computing means, we realize that its definition has not necessarily been clarified. This presentation first investigates when questions are raised about "social computing." Then we investigate what social computing means, and a formal model of social computing is described in contrast with the traditional computing scheme. Whether the Wikipedia article on social computing that states "social computing is a general term for an area of computer science ..." is correct or not is also discussed.
Collective intelligence is the heart of the concept of social computing. This presentation then reports on the WikiBOK project. This project aims to develop a body of knowledge (BOK) of "social informatics" as a collective intelligence. In contrast to a BOK for a mature discipline such as computer science, the formulation of a BOK for a new discipline, such as social informatics, life science, and sustainability science, is difficult because academics in such a new discipline cannot present it in its entirety par avance. Therefore, a bottom-up and open collaborative approach based on collective intelligence seems promising, and contrasts strongly with the traditional style in which a BOK is formulated by the authorities in the field in a top-down manner. We report on the design and implementation of WikiBOK which is a wiki-based system for open collaboration on the Web. The current status of the construction of a Social Informatics BOK (SIBOK) using WikiBOK is also presented.