# US 11,907,284 B2 · Method and a system for processing an image and for generating a contextually coherent video based on images processed thereby > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,907,284 B2 - Document ID: US11907284B2 - Status: Granted - Kind: B2 - Application number: 17/283,979 - Filed: 2019-09-26 - Published: 2022-04-21 - Granted: 2024-02-20 - Earliest claimed: 2019-07-09 - Applicants: Visuo Technology Pty Limited - Inventors: Lap-Tin Tsun; Daniel Leau - Web page: https://patentgrep.com/patent/US11907284B2 ## CPC - G06F 16/58: Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually - G06F 16/5846: {using extracted text} - G06N 20/00: Machine learning - G06T 7/194: involving foreground-background segmentation - G06T 7/70: Determining position or orientation of objects or cameras (camera calibration G06T7/80) - G06V 10/764: using classification, e.g. of video objects - G06V 10/82: using neural networks - G06V 20/35: {Categorising the entire scene, e.g. birthday party or wedding scene} - G06V 2201/10: Recognition assisted with metadata - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract The invention provides a computer-implemented method of processing an image, the method comprising the steps of: identifying objects in the image using a content analysis engine; based on information from a relationship database, using a contextual analysis engine to automatically: identify contextual relationships between some or all of the identified objects in the image, derive a background or landscape of said image from one or more of said identified objects; and subsequently, and analyse the identified contextual relationships between the identified objects and the derived background or landscape to thereby associate one or more contexts with said image. ## Claims ### Claim 1 A computer-implemented method of processing an image, the method comprising the steps of: identifying objects in the image using a content analysis engine; based on information from a relationship database, using a contextual analysis engine to automatically: identify contextual relationships between some or all of the identified objects in the image, derive a background or landscape of said image from one or more of said identified objects; and subsequently, and analyse the identified contextual relationships between the identified objects and the derived background or landscape to thereby associate one or more contexts with said image; wherein the objects identified by the content analysis engine comprise primary objects provided at a first visual layer having a first distance from an image viewpoint; and the background or landscape derived by the context analysis engine comprises other, secondary objects provided at a second visual layer having a second distance from the view-point. ### Claim 2 (depends on 1) The computer-implemented method according to claim 1, further comprising the step of storing said image in an image database in association with metadata describing said contexts. ### Claim 3 (depends on 2) The computer-implemented method according to claim 2, further comprising the step of tagging said stored image with context tags, and storing said image with the context tags as part of the metadata. ### Claim 4 (depends on 2) The computer-implemented method according to claim 2, further comprising the step of comparing the associated metadata describing said contexts of an image stored in the image database with manually inputted metadata describing said image; and modifying the associated metadata based on a difference identified by the comparing step. ### Claim 5 (depends on 1) The computer-implemented method according to claim 1, wherein the step of identifying objects in the image using a content analysis engine comprises analysing one or more characteristics of the objects to thereby identify content of the objects in the image. ### Claim 6 (depends on 1) The computer-implemented method according to claim 1, wherein the second distance is further than the first distance relative to the view-point. ### Claim 7 (depends on 1) The computer-implemented method according to claim 1, wherein the information from the relationship database is provided via manual input and/or generated automatically by a machine learning algorithm. ### Claim 8 (depends on 1) The computer-implemented method according to claim 1, further comprising the step of recognising one or more texts in the image and, based on the information from the relationship database, using the contextual analysis engine to automatically identify contextual relationships between some or all of the identified objects and the recognized texts in the image. ### Claim 9 (depends on 1) The computer-implemented method according to claim 1, further comprising a step of storing the identified contextual relationships of the identified objects in the image in the relationship database to form part of the information. ### Claim 10 (depends on 1) A computer-implemented method for generating a contextually coherent image sequence based on a plurality of images processed by the method of claim 1, comprising the steps of: inputting one or more instructions; identifying one or more keywords associated with the inputted instructions; matching the keywords with metadata stored in association with images in an image database; retrieving a plurality of matched images based on the matching step; and joining the plurality of matched images to form a contextually coherent image sequence. ### Claim 11 (depends on 10) The computer-implemented method according to claim 10, further comprising the step of rating the plurality of matched images based on a degree of matching of the keywords with the metadata; and selecting the plurality of matched images based on the rating prior to the retrieving step. ### Claim 12 (depends on 10) The computer-implemented method according to claim 10, further comprising the step of modifying the joined image sequence by manually including and/or removing one or more images from the image sequence after the joining step. ### Claim 13 (depends on 12) The computer-implemented method according to claim 12, further comprising the step of storing the formed contextually coherent image sequence and/or the modified image sequence in an image sequence database in association with the inputted one or more instructions. ### Claim 14 (depends on 13) The computer-implemented method according to claim 13, further comprising the step of analysing the stored image sequence in the image sequence database via a machine learning algorithm. ### Claim 15 (depends on 10) The computer-implemented method according to claim 10, further comprising, after the identifying step, the steps of matching the keywords with a set of stored narratives and identifying the matched narratives. ### Claim 16 (depends on 15) The computer-implemented method according to claim 15, further comprising, after the joining step to form the contextual coherent image sequence, the step of presenting the identified narratives at or with the formed video. ### Claim 17 (depends on 16) The computer-implemented method according to claim 16, further comprising the step of modifying the presented narratives by manually including and/or removing one or more words from the narratives. ### Claim 18 (depends on 1, 10) A system comprising a memory for storing data and a processor for executing computer readable instructions, wherein the processor is configured by the computer readable instructions when being executed to implement the method of claim 1 or claim 10.