N
Naoi Satoshi
Researcher at Fujitsu
Publications - 56
Citations - 534
Naoi Satoshi is an academic researcher from Fujitsu. The author has contributed to research in topics: Character (mathematics) & Pixel. The author has an hindex of 11, co-authored 56 publications receiving 527 citations.
Papers
More filters
Patent
Image processing apparatus
TL;DR: In this paper, an image processing apparatus for extracting the specified objects has a background image extract unit for extracting a background; a first average background extract unit which extracts an image that includes a plurality of stationary and moving objects each having a speed not higher than a predetermined first speed and also the background, and a second average background extraction unit which includes the stationary and running objects each with a speed at least a predetermined second speed and the background.
Patent
Apparatus for searching document images using a result of character recognition
TL;DR: In this paper, a document image search apparatus generates a text by performing the character recognition of a document and determining a re-process scope, and then generates character strings from the candidate character lattice and adds the character strings to the text.
Patent
Title extracting apparatus for extracting title from document image and method thereof
Yutaka Katsuyama,Naoi Satoshi +1 more
TL;DR: In this paper, the authors proposed a method to extract a title rectangle from the inside of a table, which is then used as a keyword for the character recognition process by using the characters extracted from the title rectangle as keywords.
Patent
Address recognition apparatus and method
Misako Suwa,Naoi Satoshi +1 more
TL;DR: In this article, a key character is extracted by recognizing characters for each of the separated characters, and patterns delimited by the key character are collectively retrieved by comparing a feature vector of the entire pattern delimited with a feature vectors of the place-name word.
Patent
Handwritten character recognition apparatus and method using a clustering algorithm
TL;DR: For a plurality of handwritten characters extracted from an input image, a character category for each character is first determined by a character recognition process as discussed by the authors, and according to a clustering process, similarity levels of character-forms among extracted characters are determined, and based on the determination result, the character category determination result from the first character classification process is modified.