Image processing method and apparatus
AssigneeCanon Kabushiki Kaisha
InventorsXiaoyan Dai, Hidefumi Osawa
Life of this patent
Estimating the term…
Abstract
Disclosed is an image processing apparatus in which vector data from which noise has been removed and amount of data reduced can be generated in ideal fashion with regard to an illustration area selected from a document image. The document image is input to the apparatus and is segmented into a plurality of areas. A clip-art image is selected from these areas and a plurality of clusters are generated with regard to this image area. When a small area included in the plurality of clusters is determined as a noise, the noise is eliminated by combining the small area with a adjacent cluster. After noise is removed, the cluster group eventually obtained is converted to vector data.
Claims20
An image processing method in an image processing apparatus for vectorizing a document image which contains a clip-art image, the method comprising:
- a selection step of segmenting the document image into areas and selecting the clip-art image area;
- a discrimination step of discriminating the type of clip-art image area;
- an area segmentation step of further segmenting the clip-art image area into areas in accordance with the type of clip-art image discriminated;
- and
- a conversion step of converting the clip-art image obtained in said area segmentation step into vector data.
An image processing apparatus for vectorizing a document image which contains a clip-art image, the apparatus comprising:
- selection means for segmenting the document image into areas and selecting the clip-art image area;
- discrimination means for discriminating the type of clip-art image area;
- area segmentation means for further segmenting the clip-art image area into areas in accordance with the type of clip-art image discriminated;
- and
- conversion means for converting the clip-art image obtained by said area segmentation means into vector data.
An image processing apparatus for converting an image into vector data, comprising:
- input means for inputting an image;
- first area segmentation means for segmenting the image into areas;
- extraction means for extracting an illustration area from the areas obtained by segmentation;
- determination means for determining whether the illustration area extracted is a clip-art image;
- second area segmentation means for further segmenting into areas an area that has been determined to be a clip-art image;
- and
- conversion means for converting the clip-art image obtained by area segmentation to vector data.
An image processing method for converting an image into vector data, comprising:
- a first area segmentation step of segmenting the image into areas;
- an extraction step of extracting an illustration area from the areas obtained by segmentation;
- a determination step of determining whether the illustration area extracted is a clip-art image;
- a second area segmentation step of further segmenting into areas an area that has been determined to be a clip-art image;
- and
- a conversion step of converting the clip-art image obtained by area segmentation to vector data.
A program stored on a computer-readable medium for causing a computer to converting an image into vector data, comprising:
- a first area segmentation step of segmenting the image into areas;
- an extraction step of extracting an illustration area from the areas obtained by segmentation;
- a determination step of determining whether the illustration area extracted is a clip-art image;
- a second area segmentation step of further segmenting into areas an area that has been determined to be a clip-art image;
- and
- a conversion step of converting the clip-art image obtained by area segmentation to vector data.
Dependencies are inferred from the claim text.