Image processing apparatus and method

• US 8,045,801 B2
• Filed: 08/31/2006
• Issued: 10/25/2011
• Est. Priority Date: 09/02/2005
• Status: Expired due to Fees

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: Kanatsu, Tomotoshi
• Primary Examiner(s): Ahmed; Samir
• Assistant Examiner(s): Liu; Li
• Application Number:
  US11/468,918
• Publication Number:
  US 20070053602A1
• Time in Patent Office: 1,881 Days
• Field of Search: 382/171, 382/173, 382/176, 382/180, 382/232
• US Class Current: 382/176
• CPC Class Codes: H04N 1/642 Adapting to different types of images, e.g. characters, graphs, black and white image portions
• CPC Class Codes: H04N 19/12 Selection from among a plurality of transforms or standards, e.g. selection between discrete cosine transform [DCT] and sub-band transform or selection between H.263 and H.264
• CPC Class Codes: H04N 19/14 Coding unit complexity, e.g. amount of activity or edge presence estimation H04N19/146 takes precedence
• CPC Class Codes: H04N 19/162 User input
• CPC Class Codes: H04N 19/17 the unit being an image region, e.g. an object

Abstract

An image processing apparatus segments an image into a plurality of regions in accordance with attributes of a plurality of types, and acquires feature amount data from image information of a region of a first attribute (an image region) from among the plurality of regions. The apparatus then applies compression processing to the image and acquires compressed data. The apparatus outputs the acquired feature amount data and compressed data as output data of the image.

Claims

1. An image processing apparatus comprising:

a region segmentation unit adapted to segment an image into a plurality of regions, the plurality of segmented regions including a region of a first attribute and a region of a second attribute;

a feature amount acquisition unit adapted to acquire image feature amount data of the region of the first attribute from an image included in the region of the first attribute, wherein the feature amount acquisition unit does not acquire image feature amount data of the region of the second attribute;

a compression unit adapted to acquire compressed data of the region of the first attribute by applying lossy compression to the image corresponding to the region of the first attribute, and adapted to acquire compressed data of the region of the second attribute by applying lossless compression to the image corresponding to the region of the second attribute; and

an output unit adapted to output the image feature amount data of the region of the first attribute acquired by said feature amount acquisition unit and the compressed data acquired by said compression unit as output data of the image,

wherein the output image feature amount data is used for retrieving the compressed data of the region of the first attribute from a database which stores the output data of the image, and

wherein said feature amount acquisition unit acquires the image feature amount data of the region of the first attribute before said compression unit applies the lossy compression to the image corresponding to the region of the first attribute.

2. The apparatus according to claim 1, further comprising a coordinate acquisition unit adapted to acquire coordinate information indicating the position of the region in which the image feature amount data has been extracted by said feature amount acquisition unit;

wherein said output unit outputs the image feature amount data, the coordinate information and the compressed data as output data of the image.

3. The apparatus according to claim 1, wherein the region of the first attribute is an image region that includes a natural image and/or drawing, and the region of the second attribute is a text region.

4. The apparatus according to claim 3, wherein said compression unit acquires the compressed data of the region of the first attribute by applying the lossy compression to a background image obtained by filling the text region included in the image with a surrounding color.

5. The apparatus according to claim 1, wherein said compression unit acquires the compressed data of the region of the first attribute by applying the lossy compression after lowering resolution of image corresponding to the region of the first attribute.

10. The apparatus according to claim 1, further comprising setting unit for setting whether to perform acquisition of the image feature amount by said feature amount acquisition unit with respect to the region of the first attribute.

6. An image processing method comprising:

a region segmentation step of segmenting an image into a plurality of regions, the plurality of segmented regions including a region of a first attribute and a region of a second attribute;

a feature amount acquisition step of acquiring image feature amount data of the region of the first attribute from an image included in the region of the first attribute, wherein image feature amount data of the region of the second attribute is not acquired in the feature amount acquisition step;

a compression step of acquiring compressed data of the region of the first attribute by applying lossy compression to the image corresponding to the region of the first attribute, and acquiring compressed data of the region of the second attribute by applying lossless compression to the image corresponding to the region of the second attribute; and

an output step of outputting the image feature amount data acquired in said feature amount acquisition step and the compressed data acquired in said compression step as output data of the image,

wherein the output image feature amount data is used for retrieving the compressed data of the region of the first attribute from a database which stores the output data of the image, and

wherein, in said feature amount acquisition step, the image feature amount data of the region of the first attribute is acquired before the lossy compression is applied to the image corresponding to the region of the first attribute in said compression step.

7. A control program stored in a non-transitory computer readable medium, for causing a computer to execute the image processing method set forth in claim 6.

8. A non-transitory computer readable storage medium storing a control program for causing a computer to execute the image processing method set forth in claim 6.

9. An image processing apparatus comprising:

a region segmentation unit adapted to segment an image into a plurality of regions;

a setting unit adapted to set one of compression schemes with regard to each of the plurality of regions obtained by said region segmentation unit;

a feature amount acquisition unit adapted to acquire, from the image, included in the region to which a compression scheme of significant information degradation is set by said setting unit, image feature amount data of the region to which the compression scheme of significant information degradation is set by said setting unit, wherein the feature amount acquisition unit does not acquire image feature amount data of the region to which the compression scheme of significant information degradation is not set by said setting unit;

a compression unit adapted to acquire compressed data of each of the plurality of regions by applying the set compression schemes to the image corresponding to each of the plurality of regions; and

an output unit adapted to output the image feature amount data acquired by said feature amount acquisition unit and the compressed data acquired by said compression unit as output data of the image,

wherein the output image feature amount data is used for retrieving the compressed data of the region, to which the compression scheme of significant information degradation is set by said setting unit, from a database which stores the output data of the image, and

wherein said feature amount acquisition unit acquires the image feature amount data of the region to which the compression scheme of significant information degradation is set by said setting unit before said compression unit applies the set compression schemes to the image corresponding to each of the plurality of regions.

11. An image processing method comprising:

a region segmentation step of segmenting an image into a plurality of regions;

a setting step of setting one of compression schemes with regard to each of the plurality of regions obtained in said region segmentation step;

a feature amount acquisition step of acquiring, from the image included in the region to which a compression scheme of significant information degradation is set in said setting step, image feature amount data of the region to which the compression scheme of significant information degradation is set in said setting step, wherein image feature amount data of the region to which the compression scheme of significant information degradation is not set in said setting step is not acquired in said feature amount acquisition step;

a compression step of acquiring compressed data of each of the plurality of regions by applying the set compression schemes to the image corresponding to each of the plurality of regions; and

an output step of outputting the image feature amount data acquired in said feature amount acquisition step and the compressed data acquired in said compression step as output data of the image,

wherein the output image feature amount data is used for retrieving the compressed data of the region, to which the compression scheme of significant information degradation is set in said setting step, from a database which stores the output data of the image, and

wherein said feature amount acquisition step acquires the image feature amount data of the region to which the compression scheme of significant information degradation is set in said setting step before said compression step applies the set compression schemes to the image corresponding to each of the plurality of regions.