Image analysis – Image segmentation – Separating document regions using preprinted guides or markings
Reexamination Certificate
1999-01-12
2001-08-14
Johns, Andrew W. (Department: 2621)
Image analysis
Image segmentation
Separating document regions using preprinted guides or markings
Reexamination Certificate
active
06275609
ABSTRACT:
BACKGROUND OF THE INVENTION
This invention relates to an image processing apparatus and method for performing image processing such as character recognition based upon an input image.
There is increasing use of software that makes it possible to perform optical character recognition (OCR) by personal computer so that image data inclusive of document image data entered by an image reading device such as an image scanner or facsimile machine can be recognized. An example of such OCR software known in the art is OmniPage Pro 6.0J, which Caere Corporation made available for sale in November of 1996. This is OCR software for Windows 3.1 or Windows 95 and supports documents in both the English and Japanese languages.
By running this OCR software on a personal computer to apply character recognition processing to image data that includes document image data, text included in the image data can be converted to character codes. That is, the entirety of the original image data inclusive of text is split into areas such as a text area, image area, table area and line-drawing area. By applying character recognition processing to the image data within the text and table areas, textual portions contained in the image data can be converted to character code data. The other areas can be left in the form of bitmap image data. Then, as by using the Rich Text Format, a file holding the layout of the text and image areas and the format information is generated.
More specifically, original image data containing text captured by the image reading device is displayed on the monitor of a personal computer. At such time the left half, for example, of the display screen is used to display the image that has been read.
Next, the personal computer performs processing to partition the image into prescribed areas and causes the monitor to display a document image in which each area (block) is enclosed by a border.
Next, the personal computer subjects textual areas and table areas to character recognition and causes text data, which results from this character recognition, to be displayed on the other half of the monitor screen, e.g., the right half. The text being displayed in the window that displays the text data generally is capable of being edited. This editing is different from ordinary editing. That is, when a character being displayed in the text window is clicked on using a mouse, the corresponding character image and character candidates from second-ranked candidates onward resulting from character recognition are displayed. By selecting a character candidate, the user can change the character currently being displayed, namely the first-ranked candidate, to the selected character. This function is an editor (referred to as an OCR editor) that makes possible revisions specific to OCR.
After character recognition processing is completed, the text can be preserved in a Rich Text Format (RTF) file. At such time, image areas other than text areas can also be preserved in the RTF file. These areas are preserved in a data structure representing a layout almost the same as the layout of the original image containing the text. If an RTF file having this data structure is read into document processing software such as Microsoft Word, for example, a document file in which textual portions have been converted to character codes can be edited on a screen displayed in a layout almost the same as that of the original image.
With the OCR software described above, however, the original image is displayed on the display screen only one page at a time. The image of the page desired to be edited is displayed on the left half of the screen, and the text window is displayed on the right half of the screen. As a consequence, the user edits the text while observing a display in which one page of an image of interest is displayed on both the left and right sides of the screen.
This editing operation is not troublesome if the document image that has been read in consists of one page. However, in a case where a plurality of pages are to be subjected to OCR processing, particularly a case where editing is performed while making cross reference to a plurality of pages, the fact that these pages cannot be observed on the screen simultaneously places an excessive burden upon the user and results considerable inconvenience. Problems also arise in terms of the ease with which pages can be moved and copied on a per-page basis.
SUMMARY OF THE INVENTION
Accordingly, an object of the present invention is to provide an image processing apparatus and method featuring easier manipulation and editing of input images.
According to the present invention, the foregoing object is attained by providing an image processing apparatus comprising: area partitioning means for splitting an input image into a plurality of block areas and generating a data block with regard to each block image, the data block having a prescribed structure inclusive of attribute data conforming to the type of block image; and symbol display means for assigning, to each of the plurality of block images in dependence upon the attribute data, any symbol from among a plurality of predetermined symbols, and displaying the assigned symbols in at-a-glance form.
The apparatus preferably further comprises reproducing means which, when any symbol among the symbols displayed by the symbol display means has been selected, is for reproducing the block image that corresponds to the selected symbol based upon data contained in the data block that corresponds to this block image.
The symbol display means preferably displays, in at-a-glance form, an input-image symbol that contains the symbols assigned to respective ones of the plurality of block images and that represents overall composition of the input image.
The symbol display means preferably displays the input-image symbol for each individual page of the input image.
The symbol display means preferably lays out the symbols, which have been assigned to respective ones of the plurality of block images, in the input-image symbol in conformity with placement of the plurality of block images in the input image.
Further, according to the present invention, the foregoing object is attained by providing an image processing method comprising: an area partitioning step of splitting an input image into a plurality of block areas and generating a data block with regard to each block image, the data block having a prescribed structure inclusive of attribute data conforming to the type of block image; and a symbol display step of assigning, to each of the plurality of block images in dependence upon the attribute data, any symbol from among a plurality of predetermined symbols, and displaying the assigned symbols in at-a-glance form.
Note, that the symbol are assigned from among the plurality of predetermined symbols in the above apparatus and method. However, the symbol may be created by performing prescribed image processing. For example, the symbol may be created by performing image-reduction for each of the plurality of block images. More particularly, following methods can be applied. That is, a reduced image may be created by selecting every 5 lines, to length and width directions of the block image, among the block image or using a prescribed image-reduction function provided with an operation system like Windows. Preferably, when the image-reduction processing are performed, a user may select desired rate.
Other features and advantages of the present invention will be apparent from the following description taken in conjunction with the accompanying drawings, in which like reference characters designate the same or similar parts throughout the figures thereof.
REFERENCES:
patent: 5105468 (1992-04-01), Guyon et al.
patent: 5491758 (1996-02-01), Bellegarda et al.
patent: 5680479 (1997-10-01), Wang et al.
patent: 5926567 (1999-07-01), Collins
patent: 6-68301 (1994-06-01), None
Azarian Seyed.
Canon Kabushiki Kaisha
Fitzpatrick ,Cella, Harper & Scinto
Johns Andrew W.
LandOfFree
Image processing apparatus and method does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Image processing apparatus and method, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Image processing apparatus and method will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2436321