T
Takuma Akagi
Researcher at Toshiba
Publications - 19
Citations - 92
Takuma Akagi is an academic researcher from Toshiba. The author has contributed to research in topics: Word recognition & Character (mathematics). The author has an hindex of 6, co-authored 18 publications receiving 92 citations.
Papers
More filters
Proceedings ArticleDOI
An Analytic Word Recognition Algorithm Using a Posteriori Probability
TL;DR: In this research, a new evaluation function is proposed, which is an improvement of "a posteriori" probability ratio, which shows 9.1% improvement on handwritten word recognition.
Patent
Information processing apparatus having learning function for character dictionary
Akihiko Nakao,Bunpei Irie,Shunji Ariyoshi,Hideo Horiuchi,Takuma Akagi,Yasuhiro Aoki,Tomoyuki Hamamura,Masaya Maeda +7 more
TL;DR: In this article, a search processing section searches information stored in an address database, using a first character series, e.g., a postal code input through an input device as a search key, for a second character series corresponding to an address.
Patent
Pattern recognition method, and storage medium which stores pattern recognition program
TL;DR: In this article, a pattern recognition method is applied to processing of causing an information processing apparatus to recognize a pattern in a plurality of steps, which can be recognized candidates of each step.
Patent
Addressee recognizing apparatus
Masaya Maeda,Bunpei Irie,Hideo Horiuchi,Shunji Ariyoshi,Akihiko Nakao,Takuma Akagi,Yasuhiro Aoki,Tomoyuki Hamamura +7 more
TL;DR: In this article, an addressee recognizing apparatus is used to determine whether the description format for each of the extracted candidates matches the description formats for the sender area stored in the database.
Patent
Image compression method and image compression device
TL;DR: In an image compression device, an image input section performs image input processing to input an image having characteristics which are recognition objects, and a conversion processing section performs conversion processing to convert a pixel value of each pixel forming the image into the pixel value suitable for coding while retaining the characteristics which were the recognition objects in the image input by the image processing as discussed by the authors.