著者
田中 孝昌 外山 史 宮道 壽一 東海林 健二
出版者
The Institute of Image Information and Television Engineers
雑誌
映像情報メディア学会誌 : 映像情報メディア = The journal of the Institute of Image Information and Television Engineers (ISSN:13426907)
巻号頁・発行日
vol.64, no.12, pp.1933-1939, 2010-12-01
被引用文献数
7

Today, the demand is increasing for comic contents on cellular phones and speech software for the visually impaired. When speech software reads aloud a comic character's speech, it is useful for both the visually impaired and unimpaired to have the character's voice injected with his/her feeling, which is inferred from types of speech balloons. As a result, comic contents come to life. In this research, a method has been developed to detect speech balloons on comic pages and then classify them into four types. In this method, speech balloon candidates are extracted based on speech text information detected by AdaBoost, and then speech balloons are selected and classified using SVM. Experimental results show that the proposed method successfully detected and classified 86 percent of 2844 speech balloons.
著者
田中 孝昌 外山 史 宮道 壽一 東海林 健二
出版者
一般社団法人 映像情報メディア学会
雑誌
映像情報メディア学会誌 (ISSN:13426907)
巻号頁・発行日
vol.64, no.12, pp.1933-1939, 2010-12-01 (Released:2011-03-01)
参考文献数
13
被引用文献数
7 1

Today, the demand is increasing for comic contents on cellular phones and speech software for the visually impaired. When speech software reads aloud a comic character's speech, it is useful for both the visually impaired and unimpaired to have the character's voice injected with his/her feeling, which is inferred from types of speech balloons. As a result, comic contents come to life. In this research, a method has been developed to detect speech balloons on comic pages and then classify them into four types. In this method, speech balloon candidates are extracted based on speech text information detected by AdaBoost, and then speech balloons are selected and classified using SVM. Experimental results show that the proposed method successfully detected and classified 86 percent of 2844 speech balloons.
著者
遠藤 友基 外山 史 千葉 親文 森 博志 東海林 健二
出版者
一般社団法人情報処理学会
雑誌
研究報告バイオ情報学(BIO) (ISSN:09196072)
巻号頁・発行日
vol.2015, no.6, pp.1-6, 2015-03-13

本論文では,次世代シーケンサから得られた大量のデータに対して,大規模なゲノムのアセンブリが可能となるように,消費メモリ量の少ない de novo アセンブリアルゴリズムを提案する.実験では,E. coli K-12 strain MG1655 及びヒトの 14 番染色体から得られたリードに対してアセンブリを行った.その結果,本手法は E. coli に対しては従来手法の約 20%,ヒト 14 番染色体に対しては他手法の約 60% の消費メモリ量で de novo アセンブリが可能であることを確認した.In this paper, we propose an algorithm for de novo assembly with lower memory. In our experiments using the E. coli K-12 strain MG 1655, the average maximum memory consumption of the proposed method was approximately 20% of that of the popular assemblers. Moreover, in the experiments using human chromosome 14, the average amount of memory of our method was approximately 60% of that of the popular assemblers.
著者
田中 健 外山 史 東海林 健二
出版者
一般社団法人情報処理学会
雑誌
情報処理学会研究報告音楽情報科学(MUS) (ISSN:09196072)
巻号頁・発行日
vol.2001, no.82, pp.43-48, 2001-08-04
被引用文献数
2

本論文では、作曲を、データベースにある曲のリズムと音高パターンの最適な組合わせを見つける最適化問題とみなし、これを遺伝的アルゴリズム(GA )を用いて解く手法を提案する。データベースには、起承転結のような構造の分かりやすい曲(童謡、唱歌など)を格納した。そして、別々の曲のリズムと音高パターンを小節ごとに組み合わせてできた曲をGA の評価対象とした。提案した手法により曲を生成した実験結果を示す。In this paper, we regard an automatic composition as an optimization problem which finds an optimum combination of rhythm and pitch transition patterns in the database. We selected the pieces of music that are simple in structure from the children's songs, the ministry of education songs, etc., and we stored them into the database. The fitness function of a GA evaluates the composed pieces of music that are sequences of the combination of rhythm patterns and pitch transition ones taken from the database in each measure. The pieces of music composed by the proposed method are shown.