Image analysis – Image segmentation – Separating document regions using preprinted guides or markings
Reexamination Certificate
1997-12-05
2001-09-11
Au, Amelia M. (Department: 2623)
Image analysis
Image segmentation
Separating document regions using preprinted guides or markings
C382S180000, C358S474000
Reexamination Certificate
active
06289121
ABSTRACT:
FIELD OF THE INVENTION
The current invention is generally related to a method and a system for automatically and or selectively inputting text image such as in a book into a digital character data, and more particularly related to a method and a system for inputting text from a book by automatically turning pages, optically converting text image into character data and determining an end of a specified unit of text.
BACKGROUND OF THE INVENTION
In order to process a large amount of textual information contained in multiple pages, various systems and methods have been implemented for inputting the textual image into a digital memory device. Such voluminous information has been generally contained in books. To input textual information contained in a book, each page has to be scanned, and the scanned image has be converted into digital character data via optical character recognition (OCR). Because pages of books are generally bound, the textual image on each page has to be turned by a human before it is scanned. This page turning process is not only tedious and time-consuming, but also is a source of errors. To substantially eliminate this human intervention, for example, Japanese Patent Hei 6-289672 discloses an automatic page turner or a book page turning device for image-duplicating machines such as photo copiers.
After textual information from a book is scanned, some preliminary processes have to take place prior to converting the scanned textual image via OCR. Japanese Patent Hei 8-37584 discloses various processes for adjusting scanned image depending upon a copying mode as well as a type of binding on an original material. These processes generally improve a certain artifacts caused by the bound material. Japanese Patent Hei 9-166938 discloses a system and a method of substantially eliminating a shadow in an scanned image caused by some depressed area in the center of a bound material when it is placed face down on a flat scanning surface. These improved scanned images are used to generate character data based upon optical character recognition.
To organize and retrieve the above described textual information, one approach is to select a key word and attach the key word to the text. Japanese Patent 6-282571 discloses a method and a system for selecting a key word from text data primarily based upon frequency in occurrence of words. Based upon the selected key word, the text is desirably organized. To retrieve the stored textual information, Japanese Patent Laid Publication 6-168276 discloses a display technique for displaying digitally converted information during a search session.
The above described prior art attempts lack a systematic inputting method and system for identifying a predetermined unit such as an article and a chapter in a bound material. Such an automatic selection mechanism is desired since a portion of textual information is necessary from a single bound volume.
SUMMARY OF THE INVENTION
In order to solve the above and other problems, according to a first aspect of the current invention, a method of inputting text from multiple pages into a digital memory device, including the steps of: a) automatically turning a page; b) scanning text on the page for optically converting the text into a predetermined format of digital data; and c) determining an end of a predetermined unit of the text in the digital data.
According to a second aspect of the current invention, a method of inputting text from multiple pages into a digital memory device, including the steps of: a) automatically turning a page; b) scanning text on the page for optically converting the text into a predetermined format of digital data; c) dividing the digital data into portions; and d) determining a representative word for each of the portions.
According to a third aspect of the current invention, a system for inputting text from multiple pages into a digital memory device, including: a page turner for automatically turning each of the multiple pages, each page having text; a scanner/optical character recognizer located near the page turner for scanning and converting the text on the multiple pages into a predetermined form of digital data; and a searcher operationally connected to the scanner/optical character recognizer for determining an end of a predetermined unit of the text in the digital data.
According to a fourth aspect of the current invention, a system for inputting text from multiple pages into a digital memory device, including: an automatic page turner for automatically turning a page, each page containing text; a scanner/optical character recognizer operationally connected to the automatic page turner for scanning the text for optically converting the text into a predetermined format of digital data; a text divider operationally connected to the scanner/optical character recognizer for dividing the digital data into portions; and a representative word selector operationally connected to the text divider for selecting a representative word for each of the portions.
These and various other advantages and features of novelty which characterize the invention are pointed out with particularity in the claims annexed hereto and forming a part hereof. However, for a better understanding of the invention, its advantages, and the objects obtained by its use, reference should be made to the drawings which form a further part hereof, and to the accompanying descriptive matter, in which there is illustrated and described a preferred embodiment of the invention.
REFERENCES:
patent: 4379283 (1983-04-01), Ito et al.
patent: 4589144 (1986-05-01), Namba
patent: 5159667 (1992-10-01), Borrey et al.
patent: 5325213 (1994-06-01), Takahashi et al.
patent: 5438630 (1995-08-01), Chen et al.
patent: 5550614 (1996-08-01), Motoyama
patent: 5682227 (1997-10-01), Taguchi et al.
patent: 5751446 (1998-05-01), Fujioka
patent: 5848191 (1998-12-01), Chen et al.
patent: 5850476 (1998-12-01), Chen et al.
patent: 5956726 (1999-09-01), Aoyama et al.
patent: 6-168276 (1994-06-01), None
patent: 6-282571 (1994-10-01), None
patent: 6-289672 (1994-10-01), None
patent: 8-37584 (1996-02-01), None
patent: 9-166938 (1997-06-01), None
Abe Yasushi
Kohchi Tsukasa
Oaku Shiori
Saitoh Takashi
Au Amelia M.
Knoble & Yoshida LLC
Miller Martin E
Ricoh & Company, Ltd.
LandOfFree
Method and system for automatically inputting text image does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method and system for automatically inputting text image, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and system for automatically inputting text image will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2449296