Image compression by object segregation

• US 8,064,706 B1
• Filed: 11/21/2009
• Issued: 11/22/2011
• Est. Priority Date: 06/29/2001
• Status: Expired due to Fees

• Current Assignee: Nagravision SA (Kudelski SA)
• Original Assignee: RPX Corporation
• Inventors: Harris, Scott C.
• Primary Examiner(s): Couso; Yon
• Application Number:
  US12/623,390
• Time in Patent Office: 731 Days
• Field of Search: 382/305, 382/209, 382/217, 382/224, 382/181, 382/203, 707/6, 707/100, 707/200, 715/515, 345/625, 348/91, 358/538
• US Class Current: 382/203
• CPC Class Codes: G06T 9/001 Model-based coding, e.g. wire frame
• CPC Class Codes: H04N 19/27 involving both synthetic and natural picture components, e.g. synthetic natural hybrid coding [SNHC]

Abstract

A system of analyzing and processing images. The image is processed using machine vision techniques to find shapes and objects in the image. In one embodiment, the system finds geometric shapes and textures in the images. In another embodiment, the image processor finds actual objects in the image. Each of these items may be replaced with an indication of the item, along with difference information indicating the difference between the actual object in the image, and the object stored in the database. The difference information may include scale information, rotation information, color information and others. The information in the database may also include sub indicia, such as information about different parts of the item, and/or information about other things that may exist in the image.

Claims

1. A computer system comprising:

a memory, storing an electronic file that represents an image;

a processor reading said electronic file, and reading an indication in the file representing at least one first unit real-life object within the electronic file indicative of a first part of the image, and said processor also reading first individual part information indicative of how said at least one first real-life object within the image differs from the first unit real-life object represented by said indication;

said processor reconstructing and outputting an output representing image information from said electronic file, said output being formed from said reading of said first unit real-life object and said reading of said first individual part information, where said processor changes said first unit real-life object based on said first individual part information, and where only a part of the image information is based on said first unit real-life object; and

said processor reading said indication in the file representing a second part of the image different than said first part of the image, wherein said first and second parts of the image are both based on the same first unit real-life object, and said processor also reading second individual part information for said second part of the image, where said second individual part information is different than said first individual part information, and said processor reconstructs said image information representing the first part based on said first unit real-life object information and said first individual part information, and said processor reconstructs said image information representing the second part based on said first unit real-life object information and said second individual part information, wherein both said first part and said second part are within the same image.

2. A computer system as in claim 1, wherein said first individual part information includes information about both size and orientation information for the first unit real-life object.

3. A computer system as in claim 1, wherein said first individual part information includes a multiplier that is multiplied by said first unit real-life object to change said first unit real-life object according to multiplying by the multiplier.

4. A system as in claim 3, wherein said multiplier changes an overall size of the first unit real-life object.

5. A system as in claim 3, wherein said multiplier changes a rotation of the first unit real-life object.

6. A system as in claim 3, wherein said multiplier changes the color of the first unit real-life object.

7. A system as in claim 1, wherein said processor also reads a remaining part of the electronic file, and creates another image portion from the remaining part of the electronic file, where said the another image portion does not include said first real-life objects therein.

8. A system as in claim 7, wherein said processor also reads a perimeter definition to determine a location of said first part of said image.

9. A system as in claim 8, wherein said perimeter definition includes a definition of the location of said first unit real-life object, as modified by modification information, within said image.

10. A system as in claim 1, wherein said first unit real-life image is an image of a plant which has a number of plant parts, and said processor reconstructs a plant image from said first unit real-life object and said first individual part information.

11. A system as in claim 10, wherein said plant part includes at least leaves of the plant, and said first individual part information represents a look of said leaves.

12. A system as in claim 1, wherein said first unit real-life image is an image of a plant which has a number of plant parts, and said processor reconstructs a first plant image from said first unit real-life object and said first individual part, and said processor reconstructs a second plant image from said first unit real-life object and said second individual part information, wherein said first plant image looks different than said second plant image.

13. A system as in claim 12, wherein the leaves of said first plant image look different than the leaves of said second plant image.

14. A system as in claim 3, wherein said processor further reads text information in a text form, and includes said text information as part of said image.

15. An image storing device, comprising:

a memory, storing an electronic file indicative of an image;

a database memory, storing a plurality of image parts representing likely real-life objects which may exist in the electronic file indicative of the image; and

an image processing device, processing said electronic file to recognize real-life objects within said electronic file that correspond to said image parts in said database memory, and to provide a modified electronic file, indicative of the image, where said modified electronic file has recognized real-life objects replaced with indications representing the real-life objects based on information in said database memory, wherein said image processing device also produces additional information that represents how a recognized real-life object within the image differs from said real-life objects within the database memory, said image processing device including image processing kernel that calculates differences between portions of the file in the memory, and said image parts in the database memory, and forms information indicative of a designation representing the real-life object from the database memory, a scale factor representing a difference in size between the real-life object from the database and the real-life object, rotation information representing a difference in size between the real-life object from the database memory and the real-life object, and color information, representing a difference in color between the real-life object from the database memory and the real-life object.

16. A device as in claim 15, wherein an identified shape is removed, leaving a rest of image without the shape therein.

17. A device as in claim 15, wherein said database also stores information indicative of other objects in said image which may appear near said real-life objects, and wherein said image processing device processes said electronic file to find said other objects.

18. A device as in claim 15, wherein said scale factor, said rotation information and said color information are multipliers that are multiplied by said information about the real-life object from the database.

19. A device as in claim 15, wherein said image processing device reads said indication in the file representing a second part of the image different than a first part of the image, wherein said first and second parts of the image are both based on the same real-life object from the database, and said image processing device reads individual part information for said second part of the image, where said individual part information is different than said scale factor, rotation information, and color information for said first part of the image.

20. A device as in claim 15, wherein said image is an image of a plant which has a number of plant parts, and said image processing device reconstructs a plant image from said real-life object and said additional information.

21. A computer system comprising:

a memory, storing an electronic file that represents an image;

a processor reading said electronic file, and reading an indication in the file representing prestored image information indicative of a first prestored plant part within the electronic file indicative of a first plant part forming a first part of the image, and said processor also reading first individual part information indicative of how said first plant part within the image differs from the first prestored plant part represented by said indication;

said processor reconstructing and outputting an output representing image information from said electronic file and said first individual part information,

said output being formed from said reading of said first prestored plant part and said reading of said first individual part information, where said processor changes said first prestored plant part based on said first individual part information to produce said output; and

said processor reading said indication in the file representing a second part of the image different than said first part of the image, wherein said first and second parts of the image are both based on the same first prestored plant part, and said processor reading second individual part information for said second part of the image, where said second individual part information is different than said first individual part information, and said processor reconstructing said image information representing the first part based on said first prestored plant part information and said first individual part information, and said processor reconstructs said image information representing the second part based on said first prestored plant part information and said second individual part information.

22. A system as in claim 21, wherein said first individual part information includes information about leaves of the plant.

23. A computer system as in claim 22, wherein said first individual part information includes information about both size and orientation information for the plant part.

24. A computer system as in claim 21, wherein said first individual part information includes a multiplier that is multiplied by said first prestored plant part to change said plant part according to multiplying by the multiplier.

25. A system as in claim 24, wherein said multiplier changes an overall size of the first prestored plant part.

26. A system as in claim 24, wherein said multiplier changes a rotation of the first prestored plant part.

27. A system as in claim 24, wherein said multiplier changes the color of the first prestored plant part.

28. A system as in claim 21, wherein said processor also reads a remaining part of the electronic file, and creates another image portion from the remaining part of the electronic file, where said another image portion does not include said first prestored plant parts therein.

29. A system as in claim 28, wherein said processor also read a perimeter definition to determine a location of said first part of said image.

30. A computer system comprising:

a memory, storing an electronic file that represents an image;

a database, storing a plurality of image parts representing objects which may exist in the image, where said objects are indicative of real-life objects; and

an image processing device, processing said electronic file to recognize objects within said electronic file that correspond to said image parts in said database, to provide a modified electronic file, indicative of the image, which replaces said recognized real-life objects with indications representing the real-life objects based on information in said database, wherein said database stores a generic identifier for each of said actual objects, and individual characteristics for the actual objects which individualize the actual objects, and where said individual characteristics represent multiplier values that are multiplied by at least one aspect of the objects in the database; and

said processor reads said indication in the file representing a second part of the image different than said first part of the image, wherein said first and second parts of the image are both based on the same image part from the database, and said processor reads second individual part information for said second part of the image, where said second individual part information is different than said first individual part information, and said processor reconstructs said image information representing the first part based on said image part from the database and said first individual part information, and said processor reconstructs said image information representing the second part based on said image part from the database and said second individual part information, wherein both said first part and said second part are within the same image.

31. A system as in claim 30, wherein said multiplier changes an overall size of the image part from the database.

32. A system as in claim 30, wherein said multiplier changes a rotation of the image part from the database.

33. A system as in claim 30, wherein said multiplier changes the color of the image part from the database.