Document frame recognition system and method
AssigneeRicoh Company, Ltd.
InventorToshifumi Yamaai
Life of this patent
Estimating the term…
Abstract
Frames such as boxes or rectangles are recognized in image document data. A first determination process initially screens frames by applying a first set of criteria to select frame candidates. The first set of criteria includes a comparison of a dimension to a predetermined threshold value. A second determination process then further determines whether or not the selected frame candidates are true frames based upon a second set of criteria. For each frame candidate, a pair of a black pixel rectangle and a white pixel rectangle is determined. The second set of criteria includes at least some information on the black pixel rectangle and the white pixel rectangle.
Claims42
A method of recognizing a frame in a document image, comprising:
- inputting document image data;
- extracting a black pixel rectangle that circumscribes continuous black pixels, the black pixel rectangle defining a parent rectangle;
- determining whether or not the parent rectangle is a frame candidate based upon a predetermined set of first criteria;
- extracting a white pixel rectangle that circumscribes continuous white pixels within the parent rectangle of the frame candidate;
- and
- further determining whether or not the frame candidate is a frame based upon a predetermined set of second criteria, the second criteria including at least a comparison of a certain aspect between the white pixel rectangle and the black pixel rectangle.
A computer readable medium storing a computer program for recognizing a frame in a document image, the computer program providing computer instructions to perform the following steps of:
- inputting document image data;
- extracting a black pixel rectangle that circumscribes continuous black pixels, the black pixel rectangle defining a parent rectangle;
- determining whether or not the parent rectangle is a frame candidate based upon a predetermined set of first criteria;
- extracting a white pixel rectangle that circumscribes continuous white pixels within the parent rectangle of the frame candidate;
- and
- further determining whether or not the frame candidate is a frame based upon a predetermined set of second criteria, the second criteria including at least a comparison of a certain aspect between the white pixel rectangle and the black pixel rectangle.
A system for recognizing a frame in a document image, comprising:
- an input device for inputting document image data;
- a black pixel rectangle extraction device connected to said input device for extracting a black pixel rectangle that circumscribes continuous black pixels, the black pixel rectangle defining a parent rectangle;
- a first determination device connected to said black pixel rectangle extraction device for determining whether or not the parent rectangle is a frame candidate based upon a predetermined set of first criteria;
- a white pixel rectangle extraction device connected to said first determination device for extracting a white pixel rectangle that circumscribes continuous white pixels within the parent rectangle of the frame candidate;
- and
- a second determination device connected to said black pixel rectangle extraction device and said white pixel rectangle extraction device for further determining whether or not the frame candidate is a frame based upon a predetermined set of second criteria, the second criteria including at least a comparison of a certain aspect between the white pixel rectangle and the black pixel rectangle.
A device for recognizing a frame in a document image, comprising:
- an input unit for inputting document image data;
- a black pixel rectangle extraction unit connected to said input unit for extracting a black pixel rectangle that circumscribes continuous black pixels, the black pixel rectangle defining a parent rectangle;
- a first determination unit connected to said black pixel rectangle extraction unit for determining whether or not the parent rectangle is a frame candidate based upon a predetermined set of first criteria;
- a white pixel rectangle extraction unit connected to said first determination unit for extracting a white pixel rectangle that circumscribes continuous white pixels within the parent rectangle of the frame candidate;
- and
- a second determination unit connected to said black pixel rectangle extraction unit and said white pixel rectangle extraction unit for further determining whether or not the frame candidate is a frame based upon a predetermined set of second criteria, the second criteria including at least a comparison of a certain aspect between the white pixel rectangle and the black pixel rectangle.
An apparatus for recognizing a frame in a document image, comprising:
- an input means for inputting document image data;
- a black pixel rectangle extraction means connected to said input means for extracting a black pixel rectangle that circumscribes continuous black pixels, the black pixel rectangle defining a parent rectangle;
- a first determination means connected to said black pixel rectangle extraction means for determining whether or not the parent rectangle is a frame candidate based upon a predetermined set of first criteria;
- a white pixel rectangle extraction means connected to said first determination means for extracting a white pixel rectangle that circumscribes continuous white pixels within the parent rectangle of the frame candidate;
- and
- a second determination means connected to said black pixel rectangle extraction means and said white pixel rectangle extraction means for further determining whether or not the frame candidate is a frame based upon a predetermined set of second criteria, the second criteria including at least a comparison of a certain aspect between the white pixel rectangle and the black pixel rectangle.
Dependencies are inferred from the claim text.