Genealogy Image Retrieval and Arrangement for Trait Inheritance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing genealogical research services fail to intuitively and accurately juxtapose traits across generations of a family, lack user-friendly connections to ancestors, and require high activation energy for users to build and engage with family trees.
Innovation Solution
A system and method for automatically identifying, retrieving, transforming, and arranging images of ancestors in predefined templates, leveraging rule-based approaches and machine learning models for face detection, and utilizing a stitched family tree database to enhance engagement by showcasing trait inheritance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If genealogical research services manually organize family information, then data accuracy is maintained, but user engagement and emotional connection are insufficient
Solution Approach 1:
The system automatically performs image identification, retrieval, transformation, and arrangement without requiring manual user intervention. The computing system navigates the family tree, identifies pertinent images, selects and retrieves them, transforms them to a standardized format, and arranges them in templates automatically, allowing the system to serve itself rather than requiring continuous user input.
Solution Approach 2:
The system pre-processes and organizes images before the user needs them by automatically identifying, retrieving, and transforming images in advance. This preliminary automation reduces the activation energy required for users to engage with their family trees by having the emotionally engaging content ready when users log in.
2Loss of information
If users manually search for and upload ancestor images, then complete family tree data is achieved, but activation energy and time requirements increase
Solution Approach 1:
The system automatically identifies which images are needed to complete the family tree by navigating the pedigree data structure, retrieves them from storage, and transforms them for display. This eliminates the need for users to manually search for and upload images, significantly reducing the time and effort required to build a complete family tree.
Solution Approach 2:
The system proactively identifies missing images and retrieves them before the user completes their family tree entry. By performing this data completion action in advance, the system reduces the overall time users spend building their family trees while ensuring data completeness.
3Ease of operation
If existing services display family information in traditional formats, then data organization is maintained, but emotional engagement and trait inheritance visualization are insufficient
Solution Approach 1:
The computing system automatically selects appropriate templates based on the family relationship type, retrieves relevant images, transforms them to a consistent format, and arranges them in emotionally engaging displays without user intervention. This complex multi-step process occurs automatically, providing high emotional engagement without requiring the user to understand or manage the underlying complexity.
Solution Approach 2:
The system pre-processes images by transforming them to a standardized format and pre-arranges them in appropriate templates before presentation to the user. This preliminary processing of the complex image arrangement task eliminates the need for users to manually organize images, making the emotional engagement feature accessible without requiring user expertise in image management.
Data Source
AI summary
Image identification, retrieval, transformation and arrangement systems, methods, and computer-program products are configured to access a family tree of a user in a family tree database, identify one or more additional persons of interest in the family tree, determine whether the one or more persons of interest is associated with an image, retrieve the image, and transform the image of the one or more additional persons of interest with an image of the user or other person such as in an image arrangement template. Whether an image pertains to a person is determined using a machine learning classifier. A plurality of candidate lineages from a root or self node may be evaluated based on the number and/or quality of images associated therewith and/or based on filtering the one or more characteristics of the nodes in the candidate lineages.