Presentation | 2010-10-08 Word Spotting Recognition to the Text Utterance Scene using Continuous DP Matching Takeshi SAITOH, Katsuhiko UCHIDA, Ryosuke KONISHI, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | This paper addresses the word spotting recognition to the text utterance scene which is not proposed in lip reading method until now. Although many researchers have proposed recognition method for a single sound or a word, there is no research for a text. In this paper, we use shape features which proposed in previous research, and apply the spotting recognition using continuous DP matching. We set 29 sentences from newspaper article and select 16 words with high frequency for recognition. With five subjects, we obtained an average recognition rate of 46%. As a result of investigating correlation between a recognition result and utterance time, it was found that there is a tendency for the shorter word is easy to be mistaken. Moreover, we carried out word lip reading with reference patterns, and obtained an average recognition rate of 85%. We confirmed that both recognition results had correlation about a word. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Lip reading / spotting recognition / continuous DP matching / text utterance scene |
Paper # | PRMU2010-98,SP2010-54,WIT2010-42 |
Date of Issue |
Conference Information | |
Committee | WIT |
---|---|
Conference Date | 2010/10/1(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Well-being Information Technology(WIT) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Word Spotting Recognition to the Text Utterance Scene using Continuous DP Matching |
Sub Title (in English) | |
Keyword(1) | Lip reading |
Keyword(2) | spotting recognition |
Keyword(3) | continuous DP matching |
Keyword(4) | text utterance scene |
1st Author's Name | Takeshi SAITOH |
1st Author's Affiliation | Kyushu Institute of Technology() |
2nd Author's Name | Katsuhiko UCHIDA |
2nd Author's Affiliation | Tottori University |
3rd Author's Name | Ryosuke KONISHI |
3rd Author's Affiliation | Tottori University |
Date | 2010-10-08 |
Paper # | PRMU2010-98,SP2010-54,WIT2010-42 |
Volume (vol) | vol.110 |
Number (no) | 221 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |