Image processor for converting image by using image retrieved based on keyword

• US 8,311,323 B2
• Filed: 09/02/2008
• Issued: 11/13/2012
• Est. Priority Date: 08/31/2007
• Status: Active Grant

• Current Assignee: Brother Kogyo Kabushiki Kaisha
• Original Assignee: Brother Kogyo Kabushiki Kaisha
• Inventors: Kondo, Masaki, Hasegawa, Tomohiko
• Primary Examiner(s): Liu, Li
• Application Number:
  US12/202,885
• Publication Number:
  US 20090060364A1
• Time in Patent Office: 1,533 Days
• Field of Search: None
• US Class Current: 382/167
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: H04N 1/6075 Corrections to the hue
• CPC Class Codes: H04N 1/62 Retouching, i.e. modification of isolated colours only or in isolated picture areas only

Abstract

An image processor includes a keyword inputting unit, a first image acquiring unit, a first characteristic quantity determining unit, a second image inputting unit, a second characteristic quantity determining unit and an image correcting unit. The keyword inputting unit inputs a keyword. The first image acquiring unit acquires at least one first image related to the keyword inputted by the keyword inputting unit. The first characteristic quantity determining unit determines first characteristic quantity data expressing a characteristic of at least one of the at least one first image acquired by the first image acquiring unit. The second image inputting unit inputs a second image. The second characteristic quantity determining unit determines second characteristic quantity data expressing a characteristic of the second image inputted by the second image inputting unit. The image correcting unit performs an image correction process on the second image to adjust characteristic of the second image represented by the second characteristic quantity data close to the first characteristic quantity data.

Claims

1. An image processor comprising:

a keyword inputting unit that inputs a keyword;

a first image acquiring unit that acquires a plurality of first images related to the keyword inputted by the keyword inputting unit;

a calculating unit that calculates a mean value of pixel values of pixels in each of the plurality of first images acquired by the first image acquiring unit, thereby determining a plurality of mean values for the plurality of first images;

a selection unit that selects one first image from the plurality of first images based upon a color attribute of pixels in each of the plurality of first images, the selecting unit selects one of the first images whose mean value is closest to a mean value of the plurality of mean values;

a first characteristic quantity determining unit that determines first characteristic quantity data expressing a characteristic of the selected one first image;

a second image inputting unit that inputs a second image;

a second characteristic quantity determining unit that determines second characteristic quantity data expressing a characteristic of the second image inputted by the second image inputting unit; and

an image correcting unit that performs an image correction process on the second image to adjust characteristic of the second image represented by the second characteristic quantity data close to the first characteristic quantity data.

2. An image processor according to claim 1, wherein the calculating unit calculates a mean total value by calculating a mean value of the plurality of mean values of the plurality of first images acquired by the first image acquiring unit, and extracts a sub-set of the first images whose mean values satisfy a prescribed condition relative to the calculated mean total value, and recalculates the mean total value by calculating a mean value of the mean values of the extracted sub-set of the first images, and wherein the selecting unit selects, from among the plurality of first images acquired by the first image acquiring unit, one first image whose mean value is closest to the recalculated mean total.

3. An image processor according to claim 2, further comprising a mean total value storing unit that stores, in association with the inputted keyword, the mean total value recalculated by the calculating unit;

wherein when a keyword newly inputted by the keyword inputting unit is the same as the keyword stored in the mean total value storing unit, the first image acquiring unit newly acquires a plurality of first images related to the newly inputted keyword, and

wherein when the first image acquiring unit newly acquires the plurality of first images related to the newly inputted keyword, the calculating unit newly calculates a mean value of pixel values of pixels in each of the newly acquired first images, the calculating unit newly extracts a sub-set of the newly acquired first images whose mean values satisfy a prescribed condition relative to the mean total value stored in association with the keyword, and newly recalculates the mean total value by calculating a mean value of the mean values of the newly extracted sub-set of the newly acquired first images and the selecting unit newly selects, from among the newly acquired first images, one first image whose mean value is closest to the newly recalculated mean total value.

4. An image processor according to claim 1, further comprising a characteristic quantity storing unit that stores first characteristic quantity data determined by the first characteristic quantity data determining unit in association with the keyword;

wherein, when a keyword newly inputted with the keyword inputting unit is the same as the keyword stored in the characteristic quantity storing unit, the first characteristic quantity determining unit reads the first characteristic quantity data stored in association with the keyword.

5. An image processor according to claim 1, wherein the first image acquiring unit acquires the plurality of first images from a storage device through communications via the Internet.

6. An image processor according to claim 1, wherein the first characteristic quantity determining unit determines a plurality of values as the first characteristic quantity data according to a prescribed condition;

the second characteristic quantity determining unit determines a plurality of values as second characteristic quantity data according to the same condition as that used by the first characteristic quantity determining unit; and

the image correcting unit performs an image correction process on each pixel constituting the second image based on a correction value that is determined for the subject pixel based on the plurality of values determined as the first characteristic quantity data and the plurality of values determined as the second characteristic quantity data.

7. An image processing method, comprising:

inputting a keyword;

acquiring a plurality of first images related to the inputted keyword;

calculating a mean value of pixel values of pixels in each of the acquired plurality of first images, thereby determining a plurality of mean values for the plurality of first images,

selecting one first image from the plurality of first images based upon a color attribute of pixels in each of the plurality of first images, the selecting including selecting the one first image whose mean value is closet to a mean value of the plurality of mean values;

determining first characteristic quantity data expressing a characteristic of the selected one first image;

inputting a second image;

determining second characteristic quantity data expressing a characteristic of the inputted second image; and

performing an image correction process on the second image to adjust characteristic of the second image represented by the second characteristic quantity data close to the first characteristic quantity data.

8. A computer readable storage medium storing a set of image processing program instructions, the instructions comprising:

inputting a keyword;

acquiring a plurality of first images related to the inputted keyword;

calculating a mean value of pixel values of pixels in each of the acquired plurality of first images, thereby determining a plurality of mean values for the plurality of first images,

selecting one first image from the plurality of first images based upon a color attribute of pixels in each of the plurality of first images, the selecting including selecting the one first image whose mean value is closest to a mean value of the plurality of the mean value;

determining first characteristic quantity data expressing a characteristic of the selected one first;

inputting a second image;

determining second characteristic quantity data expressing a characteristic of the inputted second image; and

performing an image correction process on the second image to adjust characteristic of the second image represented by the second characteristic quantity data close to the first characteristic quantity data.