METHODS AND SYSTEMS FOR ENABLING OBJECT ATTRIBUTE DRIVEN SUPER RESOLUTION ENCODING

• US 20190311498A1
• Filed: 04/04/2018
• Published: 10/10/2019
• Est. Priority Date: 04/04/2018
• Status: Active Grant

• Current Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Robinson, David C., Das, Arindam
• Granted Patent: US 10,839,562 B2
• Time in Patent Office: Days
• CPC Class Codes: G06T 3/4053 based on super-resolution, i.e. the output image resolution being higher than the sensor resolution
• CPC Class Codes: G06T 7/60 Analysis of geometric attributes
• CPC Class Codes: G06T 9/00 Image coding bandwidth or redundancy reduction for static pictures H04N1/41; coding or decoding of static colour picture signals H04N1/64; methods or arrangements for coding, decoding, compressing or decompressing digital video signals H04N19/00
• CPC Class Codes: H04N 1/4092 Edge or detail enhancement
• CPC Class Codes: H04N 1/4105 for halftone screened pictures
• CPC Class Codes: H04N 1/4115 involving the recognition of specific patterns, e.g. by symbol matching

Abstract

Systems and methods for encoding high resolution data associated with a relatively large number of bits to an encoded form having a relatively reduced number of bits. The method includes, by a processor: receiving an input image comprising one or more high resolution objects. The method further includes, for each of the one or more high resolution objects: identifying an object family for that object and determining whether a reference table exists for the object family. If a reference table exists for the object family, the method includes determining a size of that object, and identifying a tag based on the size. The method also includes encoding that object to form an encoded object having a relatively reduced number of bits, associating the identified tag with the encoded object, and saving the encoded object.

Claims

1. A method for encoding high resolution data associated with a relatively large number of bits to an encoded form having a relatively reduced number of bits, the method comprising, by a processor:

receiving an input image comprising one or more high resolution objects; and

for each of the one or more high resolution objects;

identifying an object family for that object,

determining whether a reference table exists for the object family,

upon determining that the reference table exists for the object family;

determining a size of that object, and

identifying a tag, based on the size, using the reference table,

encoding that object to form an encoded object having a relatively reduced number of bits,

associating the identified tag with the encoded object, and

saving the encoded object.

2. The method of claim 1, further comprising upon determining that the reference table does not exist for the object family:

determining a ratio of a size of a foreground region of that object to a size of a background region of that object, and

identifying a tag based on the ratio.

3. The method of claim 2, further comprising, using the ratio to create a reference table for that object.

4. The method of claim 1, wherein the reference table comprises a plurality of object size ranges and corresponding tags for the object size ranges.

5. The method of claim 1, wherein:

encoding that object comprises encoding that object using super resolution encoding (SRE); and

the identified tag is used to determine a set of bit patterns to be used for decoding and rendering the encoded object using SRE.

6. The method of claim 1, wherein the one or more high resolution objects are included on a single page corresponding to the input image.

7. The method of claim 1, wherein identifying the object family comprises identifying the object family based on one or more characteristics of that object selected from one or more of the following:

object location in the image, language associated with an object, type of an object, font of an object, style of an object, or orientation of an object.

8. The method of claim 1, determining the size of that object comprises determining the size based on metadata associated with that object.

9. The method of claim 1, further comprising, transmitting an encoded image to a rendering device, wherein the encoded image comprises one or more high resolution objects encoded to form one or more encoded objects having a relatively reduced number of bits.

10. The method of claim 9, further comprising, by a rendering device:

receiving the encoded image;

extracting tags associated with each of the one or more encoded objects;

using the tags to identify bit patterns for decoding the one or more encoded objects; and

decoding the one or more encoded objects using the bit patterns.

11. The method of claim 1, wherein determining the size of that object comprises determining one or more of the following:

point size, pixel height, or pixel width.

12. A system for encoding high resolution data associated with a relatively large number of bits to an encoded form having a relatively reduced number of bits, the system comprising:

a processing device; and

a non-transitory, computer-readable memory containing programming instructions that are configured to cause the processing device to;

receive an input image comprising one or more high resolution objects; and

for each of the one or more high resolution objects;

identify an object family for that object,

determine whether a reference table exists for the object family,

upon determining that the reference table exists for the object family;

determine a size of that object, and

identify a tag, based on the size, using the reference table,

encode that object to form an encoded object having a relatively reduced number of bits,

associate the identified tag with the encoded object, and

save the encoded object.

13. The system of claim 12, further comprising programming instructions that are configured to cause the processing device to, upon determining that the reference table does not exist for the object family:

determine a ratio of a size of a foreground region of that object to a size of a background region of that object, and

identify a tag based on the ratio.

14. The system of claim 13, further comprising programming instructions that are configured to cause the processing device to use the ratio to create a reference table for that object.

15. The system of claim 12, wherein the reference table comprises a plurality of object size ranges and corresponding tags for the object size ranges.

16. The system of claim 12, wherein:

the programming instructions that cause the processor to encode that object comprise instructions to encode that object using super resolution encoding (SRE); and

the identified tag is used to determine a set of bit patterns to be used for decoding and rendering the encoded object using SRE.

17. The system of claim 12, wherein the one or more high resolution objects are included on a single page corresponding to the input image.

18. The system of claim 12, wherein the programming instructions that cause the processor to identify the object family comprise programming instructions to identify the object family based on one or more characteristics of that object selected from one or more of the following:

object location in the image, language associated with an object, type of an object, font of an object, style of an object, or orientation of an object.

19. The system of claim 12, the programming instructions that cause the processor to determine the size of that object comprise programming instructions to determine the size based on metadata associated with that object.

20. The system of claim 12, further comprising programming instructions that are configured to cause the processing device to transmit an encoded image to a rendering device, wherein the encoded image comprises one or more high resolution objects encoded to form one or more encoded objects having a relatively reduced number of bits.

21. The system of claim 20, further comprising programming instructions that are configured to cause the processing device to cause the rendering device to:

receive the encoded image;

extract tags associated with each of the one or more encoded objects;

use the tags to identify bit patterns for decoding the one or more encoded objects; and

decode the one or more encoded objects using the bit patterns.

22. The system of claim 12, wherein the programming instructions that cause the processing device to determine the size of that object comprise programming instructions to determine one or more of the following:

point size, pixel height, or pixel width.