<?xml version="1.0" standalone="yes"?>
<Paper uid="P05-3016">
  <Title>Portable Translator Capable of Recognizing Characters on Signboard and Menu Captured by Built-in Camera</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Our world contains many signboards whose phrases provide useful information. These include destinations and notices in transportation facilities, names of buildings and shops, explanations at sightseeing spots, and the names and prices of dishes in restaurants. They are often written in just the mother tongue of the host country and are not always accompanied by pictures. Therefore, tourists must be provided with translations.</Paragraph>
    <Paragraph position="1"> Electronic dictionaries might be helpful in translating words written in European characters, because key-input is easy. However, some character sets such as Japanese and Chinese are hard to input if the user doesn't know the readings such as kana and pinyin. This is a significant barrier to any translation service. Therefore, it is essential to replace keyword entry with some other input approach that supports the user when character readings are not known.</Paragraph>
    <Paragraph position="2"> One solution is the use of optical character recognition (OCR) (Watanabe et al., 1998; Haritaoglu, 2001; Yang et al., 2002). The basic idea is the connection of OCR and machine translation (MT) (Watanabe et al., 1998) and implementation with personal data assistant (PDA) has been proposed (Haritaoglu, 2001; Yang et al., 2002). These are based on the document OCR which first tries to extract character regions; performance is weak due to the variation in lighting conditions. Although the system we propose also uses OCR, it is characterized by the use of a more robust OCR technology that doesn't first extract character regions, by language processing to offset the OCR shortcomings, and by the use of the client-server architecture and the high speed mobile network (the third generation (3G) network).</Paragraph>
  </Section>
class="xml-element"></Paper>