Image processing apparatus and image processing method
First Claim
Patent Images
1. An image processing apparatus comprising:
- a characteristic signal calculation section that calculates at least one characteristic amount of an input image signal to produce a first characteristic signal;
a conversion process section that executes a conversion process for decreasing a resolution and the number of bits of the first characteristic signal produced by the characteristic signal calculation section to convert the first characteristic signal into a second characteristic signal having a characteristic amount smaller than that of the first characteristic signal;
a storing section that stores the second characteristic signal that is obtained by conversion by the conversion process section;
a processor that reads out the second characteristic signal stored in the storing section, and executes an arithmetic operation for only a macro-scoped correction process with software or an arithmetic operation for both the macro-scoped correction process and a macro-discrimination process with the software;
a synthesizing process section that outputs a discrimination signal obtained by synthesizing an arithmetic result of the processor and the first characteristic signal produced by the characteristic signal calculation section; and
an image processing section that executes a color conversion process, a frequency filtering process and a tone process for the image signal in accordance with the discrimination signal output from the synthesizing process section,wherein in the macro-scoped process, a pixel value is corrected by one of a smearing process in which pixel values of pixels interposed between two pixels which both have a value “
1”
, and which are separated from each other by a distance of a predetermined value or less are changed to “
1”
, and a majority process in which the number of pixels having pixel value “
1”
, which are included in pixels close to a pixel of interest, is counted, and when the counted number is greater than a predetermined value, an output value is determined as “
1”
, and when the counted number is smaller than the predetermined value, the output value is determined as “
0”
, andwherein in the macro-discrimination process, a connected region is extracted with respect to a white background region, a halftone region, a character region and a halftone-dot region, and the extracted connected region is determined as one of a background graphic, a halftone-dot background graphic, a halftone-dot photo and a continuous photo region.
1 Assignment
0 Petitions
Accused Products
Abstract
An image region discrimination section in an image processing section, a characteristic signal calculation result obtained by hardware is subjected to macro-scoped correction and macro-discrimination by a processor. Further, in the image region discrimination section, a resolution and a signal bit number of a characteristic signals are decreased, the resultant characteristic signals is stored in a memory, and both a macro-discrimination result and the characteristic signals are synthesized to produce a final discrimination signal.
-
Citations
12 Claims
-
1. An image processing apparatus comprising:
-
a characteristic signal calculation section that calculates at least one characteristic amount of an input image signal to produce a first characteristic signal; a conversion process section that executes a conversion process for decreasing a resolution and the number of bits of the first characteristic signal produced by the characteristic signal calculation section to convert the first characteristic signal into a second characteristic signal having a characteristic amount smaller than that of the first characteristic signal; a storing section that stores the second characteristic signal that is obtained by conversion by the conversion process section; a processor that reads out the second characteristic signal stored in the storing section, and executes an arithmetic operation for only a macro-scoped correction process with software or an arithmetic operation for both the macro-scoped correction process and a macro-discrimination process with the software; a synthesizing process section that outputs a discrimination signal obtained by synthesizing an arithmetic result of the processor and the first characteristic signal produced by the characteristic signal calculation section; and an image processing section that executes a color conversion process, a frequency filtering process and a tone process for the image signal in accordance with the discrimination signal output from the synthesizing process section, wherein in the macro-scoped process, a pixel value is corrected by one of a smearing process in which pixel values of pixels interposed between two pixels which both have a value “
1”
, and which are separated from each other by a distance of a predetermined value or less are changed to “
1”
, and a majority process in which the number of pixels having pixel value “
1”
, which are included in pixels close to a pixel of interest, is counted, and when the counted number is greater than a predetermined value, an output value is determined as “
1”
, and when the counted number is smaller than the predetermined value, the output value is determined as “
0”
, andwherein in the macro-discrimination process, a connected region is extracted with respect to a white background region, a halftone region, a character region and a halftone-dot region, and the extracted connected region is determined as one of a background graphic, a halftone-dot background graphic, a halftone-dot photo and a continuous photo region. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10)
-
-
11. An image processing method for an image processing apparatus, comprising:
-
calculating at least one characteristic amount of an input image signal to produce a first characteristic signal; executing a conversion process for decreasing a resolution and the number of bits of the produced first characteristic signal to convert the first characteristic signal into a second characteristic signal having a characteristic amount smaller than that of the first characteristic signal; storing the second characteristic signal obtained by the conversion process; reading out the stored second characteristic signal, and executing an arithmetic operation for only a macro-scoped correction process with software or an arithmetic operation for both the macro-scoped correction process and a macro-discrimination process with the software; outputting a discrimination signal obtained by synthesizing an arithmetic result of the arithmetic operation and the produced first characteristic signal; and executing a color conversion process, a frequency filtering process and a tone process for the image signal in accordance with the output discrimination signal, wherein in the macro-scoped process, a pixel value is corrected by one of a smearing process in which pixel values of pixels interposed between two pixels which both have a value “
1”
, and which are separated from each other by a distance of a predetermined value or less are changed to “
1”
, and a majority process in which the number of pixels having pixel value “
1”
, which are included in pixels close to a pixel of interest, is counted, and when the counted number is greater than a predetermined value, an output value is determined as “
1”
, and when the counted number is smaller than the predetermined value, the output value is determined as “
0”
, andwherein in the macro-discrimination process, a connected region is extracted with respect to a white background region, a halftone region, a character region and a halftone-dot region, and the extracted connected region is determined as one of a background graphic, a halftone-dot background graphic, a halftone-dot photo and a continuous photo region. - View Dependent Claims (12)
-
Specification