Mobile Terminal Touchscreen Text Region Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current mobile terminals cannot extract and isolate specific text from images using optical character recognition (OCR) based on user-defined regions, limiting the ability to recommend relevant applications.
Innovation Solution
A mobile terminal with a touchscreen and controller that allows users to select specific regions of an image through continuous touch input, displaying a line on the selected area, extracting text within that region, and displaying it in a pop-up window along with related application icons.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If OCR extracts all text from an image, then complete text extraction is achieved, but inability to extract only specific designated text occurs
Solution Approach 1:
The image is divided into multiple selectable regions or lines, allowing users to choose specific portions for text extraction. Each region can be independently selected and processed, enabling precise extraction of only the desired text while ignoring other parts of the image.
Solution Approach 2:
Different regions of the image are treated differently based on user selection. Selected regions undergo OCR processing while unselected regions are excluded, allowing the system to adapt its processing behavior to local user requirements rather than applying uniform extraction across the entire image.
2Productivity
If multiple lines are displayed for multiple touch inputs, then simultaneous extraction from multiple regions is enabled, but device complexity increases
Solution Approach 1:
Multiple line display functions and text extraction operations are merged into a single integrated system. The controller simultaneously manages multiple lines, performs OCR on each, and displays results in corresponding pop-up windows, allowing efficient batch processing without requiring separate systems for each function.
Data Source
AI summary
A mobile terminal and a method for controlling the mobile terminal are disclosed. The mobile terminal, according to one embodiment, can display images including characters on a touch screen, receive consecutive touch inputs through the touch screen, display lines on regions of images corresponding to the consecutive touch inputs, extract the characters of which parts intersect with the lines when a particular input is received through the touch screen, and display the characters on a pop-up window.