Image Cropping by Points of Interest Viewport Optimization

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Social-networking systems face challenges in effectively cropping images to maximize the number of points of interest visible within a viewport, which affects user interaction and engagement, as existing methods do not optimally balance image scaling and cropping based on points of interest.

Innovation Solution

The system determines the viewport position that includes the maximum number of points of interest in an image and crops the image accordingly, using a method that involves testing various positions to identify the optimal viewport placement that includes the most points of interest, ensuring that the image is scaled and cropped to fit within the viewport while maintaining relevant content.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If image scaling and cropping is performed using existing methods, then the image can be displayed within the viewport, but the number of visible points of interest is not maximized

Engineering Contradiction:

Improvenumber of visible points of interestVSAvoidcomplexity of image processing method

Core Design Contradiction:

Quantity of substanceVSDevice complexity

Solution Approach 1:

The system performs preliminary detection of points of interest in the image before cropping. By identifying all points of interest and their locations in advance, the system can calculate the optimal viewport position that maximizes visible points of interest, rather than attempting optimization during the cropping process itself

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent replaces traditional mechanical image processing approaches with computational methods. Instead of using fixed or manual cropping rules, the system uses automated detection algorithms to identify points of interest and computational geometry to determine the optimal viewport position based on their locations

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If the image is cropped to include maximum points of interest, then user engagement is improved, but the processing time increases

Engineering Contradiction:

Improveuser engagement efficiencyVSAvoidimage processing time

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The system segments the image processing task into distinct phases: detection of points of interest, calculation of optimal viewport position, and execution of cropping. This segmentation allows each phase to be optimized independently and enables parallel processing where possible

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system changes the parameter being optimized from generic image quality metrics to a specific count of visible points of interest. By defining the optimization criterion in terms of detectable semantic entities rather than continuous quality metrics, the system can use discrete optimization methods that are computationally more efficient

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS9978167B2Image cropping according to points of interest

Publication Date: 2018.05.22 META PLATFORMS INC

AI summary

In one embodiment, a computing device determines one or more points of interest in an image. The computing device selects a viewport position including a pre-determined number of the points of interest. The computing device crops the image based at least in part on the viewport position.