Text Image Resizing via Layout-Aware Operation Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Images captured by electronic devices often lose recognizable text when resized for display on smaller screens, as existing resizing methods may remove text portions, especially when reducing the image resolution.
Innovation Solution
An electronic device determines layout information of text regions in an image, such as number, size, location, and shape, to select between seam carving, cropping, or scaling operations, ensuring that text regions are preserved during resizing to a target image size.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If the image is reduced in resolution by removing an outer portion, then the image size is reduced to fit the display screen, but the text in the image may be removed so that the reduced image does not include the text
Solution Approach 1:
The patent applies preliminary action by detecting text regions in the image before performing the resizing operation. The system identifies the location and extent of text areas, then uses this information to guide the cropping process, ensuring that text regions are preserved while still achieving the desired size reduction. This pre-detection step allows the system to make informed decisions about which portions of the image to retain and which to remove.
2Area of stationary object
If the image is scaled to fit a smaller resolution, then the image fits the display screen, but the text in the displayed image may not be readily recognizable due to the reduced resolution
Solution Approach 1:
The patent applies local quality by treating different regions of the image differently based on their content. Specifically, text regions are identified and given special consideration during the resizing process. The system adjusts the scaling or cropping parameters locally to ensure that text areas maintain sufficient resolution and readability, while other non-critical regions can be compressed more aggressively to achieve overall size reduction.
Data Source
AI summary
A method, which is performed by an electronic device, for resizing an image having text is disclosed. The method may include determining layout information of at least one text region in the image. The layout information may include at least one of a number, a size, a location, a shape, or a text density of the at least one text region in the image. The method may also select a seam carving operation, a cropping operation, or a scaling operation for the image based on the layout information, a size of the image, and a target image size. The selected operation may be performed to resize the image to the target image size based at least on one of the layout information, the size of the image, or the target image size. The resized image may include the at least one text region.