Image processing apparatus and image processing method
AssigneeKonica Minolta Business Technologies, Inc.
InventorKenji Matsui
Life of this patent
Estimating the term…
Abstract
The image processing apparatus is provided with a scanner unit that reads a document and generates image data; an edge vicinity pixel detection unit that detects pixels in the vicinity of the edge of the document based on luminance values of the image data generated by the scanner unit; a histogram creation unit that creates a histogram using the luminance values of pixels in a region of the document within a predetermined distance from the pixels in the vicinity of the edge; and a judgment unit that judges whether or not it is possible to separate a document region from a document-external region based on the created histogram.
Claims18
An image processing apparatus, comprising:
- a reader that reads a document and generates image data;
- an edge vicinity pixel detector that detects pixels in the vicinity of an edge of the document based on luminance values of the image data generated by the reader;
- a histogram creating portion that creates a histogram using luminance values of pixels in a region of the document within a predetermined distance from the pixels in the vicinity of the edge and excluding the pixels in the vicinity of the edge;
- a determination portion that determines whether or not it is possible to separate a document region from a document-external region based on the created histogram;
- and
- a selector that selects, based on a result of determination performed by the determination portion, one of a rectangular elimination method, in which a region within a smallest possible rectangle that surrounds the document is taken as the document region and a region other than the document region is taken as the document-external region and eliminated, and an angular elimination method, in which a shape of the document itself is taken as the document region and a region other than the document region is taken as the document-external region and eliminated.
An image processing method, comprising:
- reading a document and generating image data;
- detecting pixels in the vicinity of an edge of the document based on luminance values of the generated image data;
- creating a histogram using luminance values of pixels in a region of the document within a predetermined distance from the pixels in the vicinity of the edge and excluding the pixels in the vicinity of the edge;
- determining whether or not it is possible to separate a document region from a document-external region based on the created histogram;
- and
- selecting, based on a result of the determining, one of a rectangular elimination method, in which a region within a smallest possible rectangle that surrounds the document is taken as the document region and a region other than the document region is taken as the document-external region and eliminated, and an angular elimination method, in which a shape of the document itself is taken as the document region and a region other than the document region is taken as the document-external region and eliminated.
A non-transitory computer-readable recording medium having stored thereon a program that causes a computer to execute the steps of:
- reading a document and generating image data;
- detecting pixels in the vicinity of an edge of the document based on luminance values of the generated image data;
- creating a histogram using luminance values of pixels in a region of the document within a predetermined distance from the pixels in the vicinity of the edge and excluding the pixels in the vicinity of the edge;
- determining whether or not it is possible to separate a document region from a document-external region based on the created histogram;
- and
- selecting, based on a result of the determining, one of a rectangular elimination method, in which a region within a smallest possible rectangle that surrounds the document is taken as the document region and a region other than the document region is taken as the document-external region and eliminated, and an angular elimination method, in which a shape of the document itself is taken as the document region and a region other than the document region is taken as the document-external region and eliminated.
Dependencies are inferred from the claim text.