Image analysis – Image transformation or preprocessing – Selecting a portion of an image
Reexamination Certificate
1998-11-13
2001-01-16
Couso, Yon J. (Department: 2723)
Image analysis
Image transformation or preprocessing
Selecting a portion of an image
C382S173000, C382S295000
Reexamination Certificate
active
06175662
ABSTRACT:
BACKGROUND OF THE INVENTION
The present invention relates to a region extraction method for extracting a required region from an image signal, and an information processing apparatus.
Recent copying machines have many intelligent functions, i.e., functions of laying out a plurality of original images on a single sheet, copying images on the two surfaces of a sheet, and the like. Furthermore, owing to perfection of an ADF (Auto Document Feeder), documents can be automatically processed at higher speed. Especially, to copy a plurality of original images on a single recording sheet in a given layout, it is important to automatically discriminate the directions of images. For example, when the user wants to output two each of 20 original images on a single recording sheet in a given layout, i.e., to obtain 10 copies using the ADF, he or she need not adjust all the originals to their natural directions as long as the directions of original images can be automatically discriminated.
In a copying machine that discriminates the direction of an input original in this way, a character region is extracted from the read original image, and is subjected to OCR processing to discriminate its direction. In general, in order to extract a required region from an image signal, the image signal is stored in a memory directly (as a multi-valued signal) or after it is converted into a binary signal, and is subjected to signal processing such as filtering and the like or processing such as edge tracking and the like on the memory, thus extracting a required region, and separating and analyzing regions.
However, the above-mentioned method poses the following problems.
First, a memory for storing the entire image signal is required for region extraction. Although image data is converted into binary data for the purpose of region extraction, a large-capacity memory is required to store the entire image data. In this manner, the large-capacity memory dedicated to only region extraction disturbs cost and size reductions of the apparatus.
Second, region extraction cannot be started before the entire image signal is stored, thus producing a processing time delay.
SUMMARY OF THE INVENTION
The present invention has been made in consideration of the above-mentioned problems, and has as its object to provide a method and apparatus capable of extracting a required region from an image signal at high speed using a small memory capacity without waiting until the entire image signal is stored in a memory and without storing unnecessary image regions in the memory.
In order to achieve the above object, an information processing apparatus according to the present invention comprises:
extraction means for receiving image data in units of lines, and extracting a portion satisfying a predetermined condition from the input line;
generation means for generating a coupled region by coupling portions, which are extracted by the extraction means and separated by not more than a predetermined distance, to each other for a plurality of lines of the image data;
discrimination means for discriminating whether or not the coupled region generated by the generation means includes a specific image; and
holding means for holding region information representing the coupled region which is discriminated by the discrimination means to include the specific image, and holding a band including the coupled region which is discriminated to be a region of the specific image in storage means for storing the image data in units of bands.
In order to achieve the above object, a region extraction method according to the present invention comprises:
the extraction step of receiving image data in units of lines, and extracting a portion satisfying a predetermined condition from the input line;
the generation step of generating a coupled region by coupling portions, which are extracted in the extraction step and separated by not more than a predetermined distance, to each other for a plurality of lines of the image data;
the discrimination step of discriminating whether or not the coupled region generated in the generation step includes a specific image; and
the holding step of holding region information representing the coupled region which is discriminated in the discrimination step to include the specific image, and holding a band including the coupled region which is discriminated to be a region of the specific image in storage means for storing the image data in units of bands.
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: 5077811 (1991-12-01), Onda
patent: 5461459 (1995-10-01), Muramatsu et al.
patent: 5978519 (1999-11-01), Bollman et al.
patent: 0 712 088 (1996-05-01), None
patent: 0 725 359 (1996-08-01), None
Canon Kabushiki Kaisha
Couso Yon J.
Fitzpatrick ,Cella, Harper & Scinto
LandOfFree
Region extraction method and apparatus does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Region extraction method and apparatus, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Region extraction method and apparatus will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2523559