Object-Aware Image Cropping for Variable Display Dimensions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Images transferred between devices with different display sizes often result in distorted content or loss of information due to mismatched display dimensions.
Innovation Solution
An image processing method that detects objects within an input image, crops it to fit the target display, identifies missing objects, and outputs representations of these objects alongside the cropped image, allowing user selection to generate an updated image that matches the display dimensions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If the input image is cropped to fit the target display dimensions, then the image matches the display size, but some detected objects may be lost or not visible in the cropped image
Solution Approach 1:
The patent segments the image content by detecting multiple objects and separating them into two groups: those visible in the cropped image and those missing. The system then generates separate representations for missing objects and displays them alongside the cropped image, allowing users to view both the main cropped content and the missing objects separately.
Solution Approach 2:
The patent introduces an intermediary representation layer that bridges the cropped image and missing objects. This intermediary system generates visual representations of missing objects based on their detected positions and characteristics, then displays them as supplementary content alongside the cropped image, mediating between the space constraints and information completeness.
2Loss of information
If the original image is displayed without cropping, then all objects are visible, but the image may not fit the display dimensions and content may be distorted
Solution Approach 1:
The patent extracts the distortion problem by separating the display into two distinct components: the cropped main image that fits the display dimensions without distortion, and the extracted missing objects that are displayed separately as representations. This extraction allows the system to maintain proper aspect ratio in the main view while preserving information about objects that would otherwise be lost.
3Adaptability or versatility
If multiple representations of missing objects are displayed alongside the cropped image, then user customization is enabled, but the device complexity increases
Solution Approach 1:
The patent performs preliminary object detection and categorization before display, identifying which objects will be visible in the cropped image and which will be missing. This preliminary action allows the system to prepare representations of missing objects in advance, reducing the complexity of real-time processing during user interaction and enabling smoother customization experiences.
Data Source
AI summary
A method and system for processing an image is described. For example, the method comprises detecting a plurality of objects within an in input image; identifying dimensions of a display on which the input image is to be displayed; cropping the input image to obtain a cropped image which matches the identified dimensions, wherein the cropped image includes at least one of the plurality of detected objects; obtaining a list of missing objects which are not visible in the cropped image and which were detected in the input image; outputting a representation of each missing object in the list of missing objects to be displayed together with the cropped image; generating an updated image comprising the representation of at least one missing object and which matches the identified dimensions; and outputting the updated image to be displayed on the display.