# US 2015/0104113 A1 · Method and Apparatus for Producing a Cinemagraph

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2015/0104113 A1
- Document ID: US20150104113A1
- Status: Published application
- Kind: A1
- Application number: 14/403,212
- Filed: 2012-05-25
- Published: 2015-04-16
- Earliest claimed: 2012-05-25
- Assignees: Nokia Corporation
- Applicants: Nokia Corporation
- Inventors: Kemal Ugur; Ali Karaoglu; Miska Hannuksela; Jani Lainema
- Web page: https://patentgrep.com/patent/US20150104113A1

## CPC

- G06T 13/80: Two-dimensional [2D] animation, e.g. using sprites
- G06T 7/11: Region-based segmentation
- G06T 7/187: involving region growing; involving region merging; involving connected component labelling
- G11B 27/007: {reproducing continuously a part of the information, i.e. repeating}
- G11B 27/031: Electronic editing of digitised analogue information signals, e.g. audio or video signals
- H04N 5/2621: {Cameras specially adapted for the electronic generation of special effects during image pickup, e.g. digital cameras, camcorders, video cameras having integrated special effects capability}
- H04N 23/62: Control of parameters via user interfaces
- G06T 2207/20104: Interactive definition of region of interest [ROI]
- G06T 2207/20221: Image fusion; Image merging
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G11B: INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER (recording measured values in a way that does not require playback through a transducer G01D9/00; recording or playback apparatus using mechanically marked tape, e.g. punched paper tape, or using unit records, e.g. punched or magnetically marked cards G06K; transferring data from one type of record carrier to another G06K1/18; circuits for coupling output of reproducer to radio receiver H04B1/20; gramophone pick-ups or like acoustic electromechanical transducers or circuits therefor H04R)
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

Method and apparatus for producing a cinemagraph, wherein based on received user input an image from a sequence of images is selected as a baseframe image. The baseframe image is segmented and at least one segment is selected based on user input. A mask is created based on the selected segments and at least one image most similar to the baseframe is selected from the sequence of images using the mask. The selected images are aligned the baseframe image a first cinemagraph is created from the selected images and the baseframe image using the mask.

## Claims

### Claim 1

An apparatus, comprising:
a user interface;
a memory configured to store a sequence of images; and
a processor configured to cause:
receiving user input from a user through the user interface;
selecting based on the user input from the sequence of images an image as a baseframe image;
segmenting the baseframe image;
selecting based on the user input at least one segment of the baseframe image; creating a mask based on the at least one selected segment;
selecting from the sequence of images at least one image most similar to the baseframe image using the mask;
aligning the selected images with the baseframe image; and
creating a first cinemagraph from the selected images and the baseframe image using the mask.

### Claim 2 (depends on 1)

The apparatus according to claim 1 further comprising a camera unit, wherein the processor is further configured to cause capturing the sequence of images with the camera unit.

### Claim 3 (depends on 1)

The apparatus according to claim 1, wherein the processor is further configured to cause creating at least one second cinemagraph by changing the order of the images and the baseframe image in the first cinemagraph.

### Claim 4 (depends on 1)

The apparatus according to claim 1, wherein the processor is further configured to cause creating at least one second cinemagraph by adding duplicate images to the first cinemagraph.

### Claim 5 (depends on 1)

The apparatus according to claim 1, wherein the processor is further configured to cause creating at least one second cinemagraph by adding images interpolated from the existing images and the baseframe image of the first cinemagraph to the first cinemagraph.

### Claim 6 (depends on 3)

The apparatus according to claim 3, wherein the apparatus further comprises a display; and the processor is further configured to cause presenting the first and the at least one second cinemagraph to the user on the display; and to cause selecting a cinemagraph from the first and at least one second cinemagraph based on the user input.

### Claim 7 (depends on 1)

The apparatus according to any claim 1, wherein the baseframe image is segmented into super-pixels.

### Claim 8 (depends on 7)

The apparatus according to claim 7, wherein the super-pixels are formed based on image characteristics.

### Claim 9 (depends on 1)

The apparatus according to claim 1, wherein at least two masks are created based on the user input.

### Claim 10 (depends on 9)

The apparatus according to claim 9, wherein at least one of the masks is created using a mask enlargement algorithm to enlarge the mask by further selecting one or more adjacent super-pixels in addition to the selected super-pixels.

### Claim 11 (depends on 9)

The apparatus according to claim 9, wherein at least one of the masks is created using a gap filling algorithm to enlarge the mask by further selecting one or more super-pixels in-between the selected super-pixels in addition to the selected super-pixels.

### Claim 12 (depends on 9)

The apparatus according to claim 9, wherein the processor is further configured to cause repeating the selecting from the sequence of images at least one image most similar to the baseframe image so that for each mask at least the one image is selected.

### Claim 13 (depends on 9)

The apparatus according to claim 9, wherein the processor is further configured to cause repeating the aligning the selected images with the baseframe image so that the images selected using each mask are aligned.

### Claim 14 (depends on 1)

The apparatus according to claim 1, wherein the processor is further configured to cause aligning of the images using an alignment algorithm.

### Claim 15 (depends on 9)

The apparatus according to claim 9, wherein the processor is further configured to cause repeating the forming a first cinemagraph from the selected images and the baseframe image so that for each mask a first cinemagraph is created.

### Claim 16 (depends on 15)

The apparatus according to claim 15, wherein the processor is further configured to cause presenting the at least two first cinemagraphs to the user on the display; and to cause selecting a single first cinemagraph from the at least two first cinemagraphs based on the user input.

### Claim 17 (depends on 1)

The apparatus according to claim 1, wherein the mask comprises a masked area; and wherein the processor is further configured to cause the selecting from the sequence group of images at least one image most similar to the baseframe image using a mask by determining the smallest rectangle in which the masked area fits and comparing the area of said rectangle in at least some of the images of the sequence of images.

### Claim 18 (depends on 17)

The apparatus according to claim 17, wherein the processor is further configured to cause comparing the area of said rectangle in at least some of the images of the sequence of images using an algorithm.

### Claim 19 (depends on 1)

The apparatus according to claim 1, wherein the display is a touch sensitive display; and the processor is configured to receive the user input from the touch sensitive display.

### Claim 20 (depends on 1)

The apparatus according to claim 1, wherein the user interface is configured to receive the user input in at least two different entries from the user.

### Claim 21 (depends on 1)

The apparatus according to claim 1, wherein the processor is further configured to cause storing the cinemagraph into a file.

### Claim 22

A method comprising:
receiving user input from a user through a user interface;
selecting based on user input an image from a sequence of images as a baseframe image;
segmenting the baseframe image;
selecting based on the user input at least one segment of the baseframe image;
creating a mask based on the at least one selected segment;
selecting from the sequence of images at least one image most similar to the baseframe image using the mask;
aligning the selected images with the baseframe image; and
creating a first cinemagraph from the selected images and the baseframe image using the mask.

### Claim 23 (depends on 22)

The method according to claim 22 further comprising capturing the sequence of images with a camera unit.

### Claim 24 (depends on 22)

The method according to claim 22 further comprising storing a sequence of images into a memory.

### Claim 25 (depends on 22)

The method according to claim 22 further comprising creating at least one second cinemagraph by changing the order of the images and the baseframe image in the first cinemagraph.

### Claim 26 (depends on 22)

The method according to claim 22 further comprising creating at least one second cinemagraph by adding duplicate images to the first cinemagraph.

### Claim 27 (depends on 22)

The method according to claim 22 further comprising creating at least one second cinemagraph by adding images interpolated from the existing images and the baseframe image of the first cinemagraph to the first cinemagraph.

### Claim 28 (depends on 25)

The method according to claim 25, further comprising presenting the first and at least one second cinemagraph to the user; and selecting a cinemagraph from the first and at least one second cinemagraph based on the user input.

### Claim 29 (depends on 22)

The method according to claim 22, wherein the baseframe image is segmented into super-pixels.

### Claim 30 (depends on 29)

The method according to claim 29, wherein the super-pixels are formed based on image characteristics.

### Claim 31 (depends on 22)

The method according to claim 22, wherein at least two masks are created based on the user input.

### Claim 32 (depends on 31)

The method according to claim 31, wherein at least one of the masks is created using a mask enlargement algorithm to enlarge the mask by further selecting one or more adjacent super-pixels in addition to the selected super-pixels.

### Claim 33 (depends on 31)

The method according to claim 31, wherein at least one of the masks is created using a gap filling algorithm to enlarge the mask by further selecting one or more super-pixels in-between the selected super-pixels in addition to the selected super-pixels.

### Claim 34 (depends on 31)

The method according to claim 31 further comprising repeating the selecting from the sequence of images at least one image most similar to the baseframe image so that for each mask at least the one image is selected.

### Claim 35 (depends on 31)

The method according to claim 31 further comprising repeating the aligning the selected images with the baseframe image so that the images selected using each mask are aligned.

### Claim 36 (depends on 22)

The method according to claim 22, wherein the aligning of the images comprises using an aligning algorithm.

### Claim 37 (depends on 31)

The method according to claim 31, further comprising repeating the forming a first cinemagraph from the selected images and the baseframe image so that for each mask a first cinemagraph is created.

### Claim 38 (depends on 37)

The method according to claim 37 further comprising presenting the at least two first cinemagraphs to the user; and selecting a single first cinemagraph from the at least two first cinemagraphs based on the user input.

### Claim 39 (depends on 22)

The method according to claim 22, wherein the mask comprises a masked area; and wherein the selecting from the sequence of images at least one image most similar to the baseframe image using a mask comprises determining the smallest rectangle in which the masked area fits and comparing the area of said rectangle in at least some of the images of the sequence of images.

### Claim 40 (depends on 39)

The method according to claim 39, wherein comparing the area of said rectangle in at least some of the images of the sequence of images comprises using an algorithm.

### Claim 41 (depends on 22)

The method according to claim 22, wherein the user input is received through a touch sensitive display.

### Claim 42 (depends on 22)

The method according to claim 22 further comprising storing the cinemagraph into a file.

### Claim 43 (depends on 22)

A non-transitory program storage device comprising computer code for causing performance of the method of claim 22, when executed by an apparatus.

### Claim 44

(canceled)
