Automated Image Organization by Event Attributes

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Manually sorting through large digital image libraries is time-consuming and tedious, as users must manually organize images by events, locations, or individuals, which can be inefficient.

Innovation Solution

An automated system that uses image analysis components to identify attributes such as object recognition, geotags, and metadata to generate albums associated with specific events, excluding duplicates and low-quality images, thereby organizing images automatically.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If manual sorting is used to organize images by events, locations, or individuals, then users can have full control over image organization, but the process becomes time-consuming and tedious

Engineering Contradiction:

ImproveManual control over image organizationVSAvoidTime required to sort through images

Core Design Contradiction:

Ease of operationVSLoss of time

Solution Approach 1:

The system performs automatic image organization without requiring user intervention. The album generation component automatically identifies events from images, selects relevant images, and creates organized albums, allowing the system to serve itself rather than requiring manual user sorting

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical manual sorting process with an automated computational system. The image analysis component uses computer vision and machine learning to automatically identify events, objects, and relationships in images, substituting human manual effort with automated image recognition technology

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Quantity of substance

If all images associated with an event are included in an album, then the album is comprehensive, but it may include duplicate or low-quality images that reduce organization effectiveness

Engineering Contradiction:

ImproveNumber of images in albumVSAvoidQuality and relevance of images

Core Design Contradiction:

Quantity of substanceVSReliability

Solution Approach 1:

The system applies different quality standards and selection criteria to different images based on their individual characteristics. The image analysis component evaluates each image's quality, relevance, and uniqueness, selecting only those that meet specific criteria for inclusion in the album, rather than treating all images uniformly

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS9405774B2Automated image organization techniques

Publication Date: 2016.08.02 VERIZON PATENT & LICENSING INC

AI summary

A device may receive multiple images captured by a user device; and determine an event based on at least one of: attributes of the multiple images, information regarding a user associated with the multiple images, or information regarding the user device. The device may determine attributes of the event; identify, based on the attributes of the multiple the images and the attributes of the event, particular images, of the multiple images, associated with the event; generate a digital image album that includes one or more of the particular images; and output the digital image album.