Method of processing and storing images

• US 10,244,129 B2
• Filed: 09/27/2016
• Issued: 03/26/2019
• Est. Priority Date: 10/12/2015
• Status: Active Grant

• Current Assignee: Direct Cursus Technology LLC
• Original Assignee: Yandex Europe AG (Yandex N.V.)
• Inventors: Osipov, Alexander Alexandrovich
• Primary Examiner(s): Ky, Kevin
• Application Number:
  US15/276,929
• Publication Number:
  US 20170103286A1
• Time in Patent Office: 910 Days
• Field of Search: None
• CPC Class Codes: G06F 18/28 Determining representative reference patterns, e.g. by averaging or distorting; Generating dictionaries
• CPC Class Codes: G06T 7/174 involving the use of two or more images
• CPC Class Codes: G06T 7/97 Determining parameters from multiple pictures depth or shape recovery from multiple images G06T7/55; stereo camera calibration G06T7/85
• CPC Class Codes: G06V 10/7515 Shifting the patterns to accommodate for positional errors
• CPC Class Codes: G06V 10/772 Determining representative reference patterns, e.g. averaging or distorting patterns; Generating dictionaries
• CPC Class Codes: G06V 20/30 in albums, collections or shared content, e.g. social network photos or video
• CPC Class Codes: H04N 1/00244 with a server, e.g. an internet server fax-servers or the like for store and forward H04N1/324
• CPC Class Codes: H04N 5/765 Interface circuits between an apparatus for recording and another apparatus

Abstract

The methods and systems described herein relate to a method of processing and storing images. The method is executed by a server and comprises: acquiring, by the server, a first image and a second image; determining, by the server, a first mapping information between the first image and the second image; generating, by the server, a reference image based on the first image and the second image, the reference image comprising a set of synthetic pixels; computing, by the server, a first parameter and a second parameter, the first parameter being at least partially indicative of a visual dissimilarity between the first pixels of the first image and the respective synthetic pixels and the second parameter being at least partially indicative of the visual dissimilarity between the second pixels of the second image and the respective synthetic pixels.

Claims

1. A method of processing and storing a group of images, the method being executed by a server, the method comprising:

acquiring, by the server, a first image and a second image, the first image comprising a totality of pixels of the first image and the second image comprising a totality of pixels of the second image;

determining, by the server, that the first image and the second image are visually related, thus generating the group of images, the group of images including the first image and the second image, the determining that the first image and the second image are visually related comprises identifying, by the server, a set of first pixels within the first image amongst the totality of pixels of the first image and a set of second pixels within the second image amongst the totality of pixels of the second image, each first pixel within the set of first pixels being visually related to a respective second pixel within the set of second pixels;

determining, by the server, a first mapping information between the first image and the second image;

generating, by the server, a reference image based on the first image and the second image, the reference image comprising a set of synthetic pixels, the generating the reference image comprises;

determining, by the server, a second mapping information between the first image and the reference image; and

computing, by the server, each synthetic pixel within the set of synthetic pixels based on a respective first pixel within the set of first pixels correlated to a respective synthetic pixel within the set of synthetic pixels and a respective second pixel within the set of second pixels correlated to the respective synthetic pixel within the set of synthetic pixels, the computing each synthetic pixel comprises correlating, by the server, the respective first pixel to the respective synthetic pixel via the second mapping information and the respective second pixel to the respective synthetic pixel via the first and the second mapping information;

computing, by the server, a first parameter and a second parameter, the first parameter being at least partially indicative of a visual dissimilarity between the first pixels and the respective synthetic pixels, the second parameter being at least partially indicative of the visual dissimilarity between the second pixels and the respective synthetic pixels; and

storing, by the server, in a storage accessible by the server, the group of images as;

the reference image, the first parameter, the second parameter, the first mapping information and the second mapping information.

2. The method of claim 1, wherein the determining the first mapping information comprises:

selecting, by the server, at least two first pixels within the first image;

identifying, by the server, positions of the at least two first pixels within the first image and positions of respective visually related second pixels within the second image; and

computing, by the server, a first set of transposition factors based on the positions of the at least two first pixels within the first image and the positions of the respective visually related second pixels within the second image, the first set of transposition factors being indicative of the first mapping information between the first image and the second image.

3. The method of claim 1, wherein the generating the reference image further comprises:

assessing, by the server, a resolution of the first image;

selecting, by the server, a resolution of the reference image; and

computing, by the server, a second set of transposition factors being indicative of the second mapping information between the first image and the reference image based on the resolution of the reference image and the resolution of the first image.

4. The method of claim 1, the method further comprises:

identifying, by the server, a set of third pixels amongst the totality of pixels of the first image, each third pixel within the set of third pixels being visually unrelated to any pixel within the totality of pixels of the second image;

and wherein the reference image further comprises a set of first native pixels, the generating the reference image further comprises computing, by the server, each first native pixel within the set of first native pixels based on a respective third pixel within the set of third pixels correlated to a respective first native pixel; and

wherein the first parameter is further at least partially indicative of;

the visual dissimilarity between the third pixels and the respective first native pixels.

5. The method of claim 4, wherein the computing each first native pixel comprises correlating, by the server, the respective third pixel to the respective first native pixel via the second mapping information.

6. The method of claim 1, the method further comprises:

identifying, by the server, a set of fourth pixels amongst the totality of pixels of the second image, each fourth pixel within the set of fourth pixels being visually unrelated to any pixel within the totality of pixels of the first image;

and wherein the reference image further comprises a set of second native pixels, the generating the reference image further comprises computing, by the server, each second native pixel within the set of second native pixels based on a respective fourth pixel within the set of fourth pixels correlated to a respective second native pixel; and

wherein the second parameter is further at least partially indicative of;

the visual dissimilarity between the fourth pixels and the respective second native pixels.

7. The method of claim 6, wherein the computing each second native pixel comprises correlating, by the server, the respective fourth pixel to the respective second native pixel via the first and the second mapping information.

8. The method of claim 1, wherein the computing each synthetic pixel within the set of synthetic pixels further comprises computing, by the server, a distinctive synthetic pixel based on a distinctive pixel within the totality of pixels of the first image correlated to the distinctive synthetic pixel and an interpolated pixel correlated to the distinctive synthetic pixel, the computing the distinctive synthetic pixel comprises computing, by the server, the interpolated pixel based on an amalgamation of pixels within the totality of pixels of the second image;

and wherein the first parameter is further at least partially indicative of;

the visual dissimilarity between the distinctive pixel within totality of pixels of the first image and the respective distinctive synthetic pixel within the reference image.

9. The method of claim 8, wherein the computing the distinctive synthetic pixel is based on the distinctive pixel within the totality of pixels of the second image correlated to the distinctive synthetic pixel and the interpolated pixel correlated to the distinctive synthetic pixel, the computing the distinctive synthetic pixel comprises computing, by the server, the interpolated pixel based on the amalgamation of pixels within the totality of pixels of the first image;

and wherein the second parameter is further at least partially indicative of;

the visual dissimilarity between the distinctive pixel within totality of pixels of the second image and the respective distinctive synthetic pixel within the reference image.

10. The method of claim 9, wherein the computing the distinctive synthetic pixel further comprises correlating, by the server, the distinctive pixel within the totality of pixels of the second image to the distinctive synthetic pixel via the first and the second mapping information and correlating the interpolated pixel to the distinctive synthetic pixel via the second mapping information.

11. The method of claim 9, wherein the computing the interpolated pixel comprises determining, by the server, the amalgamation of pixels within the totality of pixels of the first image based on the second mapping information.

12. The method of claim 9, wherein the computing the distinctive synthetic pixel further comprises averaging, by the server, the distinctive pixel within the totality of pixels of the second image correlated to the distinctive synthetic pixel and the interpolated pixel correlated to the distinctive synthetic pixel.

13. The method of claim 8, wherein the computing the distinctive synthetic pixel further comprises correlating, by the server, the distinctive pixel within the totality of pixels of the first image to the distinctive synthetic pixel via the second mapping information and correlating the interpolated pixel to the distinctive synthetic pixel via the first and the second mapping information.

14. The method of claim 8, wherein the computing the interpolated pixel comprises determining, by the server, the amalgamation of pixels within the totality of pixels of the second image based on the first and the second mapping information.

15. The method of claim 8, wherein the computing the distinctive synthetic pixel further comprises averaging, by the server, the distinctive pixel within the totality of pixels of the first image correlated to the distinctive synthetic pixel and the interpolated pixel correlated to the distinctive synthetic pixel.

16. The method of claim 1, wherein the computing each synthetic pixel within the set of synthetic pixels further comprises averaging, by the server, the first pixel correlated to the respective synthetic pixel and the second pixel correlated to the respective synthetic pixel.

17. The method of claim 1, wherein the first and the second parameter comprise a set of first delta-pixels and a set of second delta-pixels respectively and a resolution of the first and the second image respectively, the first delta-pixels within the set of first delta-pixels being indicative of the visual dissimilarity between the first pixels and the respective synthetic pixels, the second delta-pixels within the set of second delta-pixels being indicative of the visual dissimilarity between the second pixels and the respective synthetic pixels.

18. The method of claim 17, wherein the first parameter further comprises the second mapping information and the second parameter further comprises the first and the second mapping information.

19. A method of generating a group of visually related images including a first image and a second image, the group of images having been stored in a storage accessible by the server as a first mapping information, a second mapping information, a first parameter, a second parameter, and a reference image, the first image comprising a set of first pixels, the second image comprising a set of second pixels, the method being executed by a server, the method comprises:

retrieving, by the server, from the storage accessible by the server;

i. the first mapping information between the first image and the second image;

ii. the second mapping information;

iii. the reference image, the reference image comprising a set of synthetic pixels, each synthetic pixel within the set of synthetic pixels being correlated via a second mapping information to a respective first pixel within the set of first pixels within the first image and correlated via the second mapping information and the first mapping information to a respective second pixel within the set of second pixels within the second image; and

iv. the first parameter, the first parameter being at least partially indicative of a visual dissimilarity between first pixels within the set of first pixels and the respective synthetic pixels;

v. the second parameter, the second parameter being at least partially indicative of a visual dissimilarity between the second pixels within the set of second pixels and respective synthetic pixels of the set of synthetic pixels; and

generating, by the server, the group of visually related images based on the first parameter, the second parameter, the first mapping information, the second mapping information and the reference image.