Automated Group Photo Composition Using Relationship Data

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing camera systems lack the ability to automatically adjust the composition of group photographs based on relationship data, failing to include or exclude individuals appropriately within the frame during image capture, leading to incomplete or inappropriate groupings.

Innovation Solution

A computerized method and system that identifies individuals within a camera's viewfinder, determines the geographic location of related persons outside the frame using proximity data, and recommends their inclusion or exclusion based on relationship attributes, allowing for automated adjustments to the frame before image acquisition.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Speed

If automated facial detection is used to identify persons in the frame, then the speed of person identification is improved, but the system cannot automatically determine which persons should be included or excluded based on relationships

Engineering Contradiction:
Improveperson identification speedVSAvoidautomated composition decision-making
Core Design Contradiction:
SpeedVSExtent of automation

Solution Approach 1:

The system introduces relationship data from social networks as an intermediary between facial detection and composition decisions. This intermediary layer provides the missing contextual information about person relationships, enabling automated determination of who should be included or excluded from the photograph without requiring manual user input.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system performs preliminary actions by proactively identifying persons who should be added to or removed from the frame based on relationship attributes before the photograph is taken. This includes determining geographic proximity of related persons and pre-calculating composition adjustments needed, rather than waiting for manual user review.

Inventive Principle:
Principle #10Preliminary action

2Manufacturing precision

If manual adjustment of composition attributes is required to ensure each person is clearly visible, then the precision of person visibility is improved, but the time required for photograph composition increases

Engineering Contradiction:
Improveperson visibility precisionVSAvoidphotograph composition time
Core Design Contradiction:
Manufacturing precisionVSLoss of time

Solution Approach 1:

The system performs self-service by automatically adjusting composition attributes (framing, focus, zoom) based on relationship data and detected person positions. The camera system autonomously determines the optimal composition that ensures all relevant persons are clearly visible, eliminating the need for manual user adjustment while maintaining high precision in person visibility.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system uses feedback from relationship data and real-time facial detection to automatically refine composition attributes. By continuously monitoring which persons should be included based on their relationships and adjusting the frame accordingly, the system achieves precise person visibility without requiring manual intervention or time-consuming user adjustments.

Inventive Principle:
Principle #23Feedback

3Device complexity

If the camera only captures persons currently visible in the frame, then the simplicity of the capture process is maintained, but the completeness of group photographs is reduced

Engineering Contradiction:
Improvecapture process simplicityVSAvoidgroup photograph completeness
Core Design Contradiction:
Device complexityVSLoss of information

Solution Approach 1:

The system performs preliminary identification of persons who should be in the photograph by querying relationship data and determining geographic proximity before the capture moment. This allows the system to proactively notify missing persons or automatically adjust the frame to include them, ensuring complete group photographs without adding significant complexity to the capture process.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS10218898B2Automated group photograph composition
Publication Date: 2019.02.26 INTERNATIONAL BUSINESS MACHINE CORPORATION
  • US10218898B2 patent drawing
  • US10218898B2 patent drawing
  • US10218898B2 patent drawing

AI summary

Aspects identify one or more persons appearing within a photographic image framing of a camera viewfinder. A geographic location is determined for an additional person related to such identified persons, wherein the additional person is located within a specified proximity range to the identified persons but does not appear within the photographic image framing. In response to determining that a relationship of the additional person to a person identified within the image framing indicates that the additional person should be included within photographic images of the identified person, aspects recommend that the additional person be added to the photographic image framing prior to acquisition of image data by the camera from the photographic image framing.