OCR Mosaic Layout for Medical Controller Screen Variants
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing medical device controllers display critical information at varying screen locations due to software version or device type differences, complicating effective masking for optical character recognition (OCR) and necessitating multiple OCR processes, which are costly and time-consuming.
Innovation Solution
A server generates a mosaic image by copying source regions from medical device controllers' screens to predefined destination regions, allowing a single OCR process to accurately extract text results by comparing selector text results to predefined text, thus selecting the correct coordinates based on screen content.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple OCR processes are performed with different masks to handle varying screen layouts, then text extraction accuracy is improved, but processing time and computational cost increase
Solution Approach 1:
The system performs preliminary actions by detecting screen layout characteristics and identifying the appropriate mask type before executing the OCR process. The server analyzes the received screen image to determine which mask (first mask or second mask) is suitable based on the displayed information type and screen coordinates, then applies the selected mask prior to OCR. This preliminary mask selection and application eliminates the need to perform multiple OCR processes with different masks, reducing processing time while maintaining accurate text extraction.
2Measurement precision
If multiple OCR processes are performed with different masks to handle varying screen layouts, then text extraction accuracy is improved, but computational resources and costs increase
Solution Approach 1:
The server performs preliminary analysis of the screen image to determine the appropriate mask type before initiating OCR processing. By detecting the type of information displayed and the screen coordinates, the system pre-selects the suitable mask (first mask for certain layouts, second mask for others) and applies it before OCR. This preliminary action eliminates the need to execute multiple OCR processes with different masks, thereby reducing computational resource consumption and processing costs while maintaining accurate text extraction.
Solution Approach 2:
The system uses mask templates (first mask and second mask) that are pre-designed copies of appropriate masking patterns for different screen layouts. These mask copies are stored and selectively applied based on the detected screen characteristics, avoiding the need to create or process multiple complete OCR configurations. The mask copying approach simplifies the computational complexity by reusing pre-prepared mask patterns rather than generating new processing pipelines for each screen variation.
3Reliability
If the server uses several masks and performs OCR with each mask to handle different screen layouts, then text extraction completeness is improved, but the system complexity increases
Solution Approach 1:
The server performs preliminary detection of screen layout characteristics and determines the appropriate mask type before executing OCR. By analyzing the received screen image to identify the type of information displayed and the screen coordinates, the system pre-selects the suitable mask (first mask or second mask) and applies it before OCR processing. This preliminary mask selection ensures that the correct mask is used for the given screen layout, maintaining text extraction completeness while avoiding the need to implement complex systems that perform multiple OCR processes with different masks.
Data Source
AI summary
A medical device monitoring system and method extract information from screen images from medical device controllers, with a single OCR process invocation per screen image, despite critical information appearing in different screen locations, depending on which medical device controller's screen image is processed. For example, different software versions of the medical device controllers might display the same type of information in different screen locations. Copies of the critical screen information, one copy from each different screen location, are made in a mosaic image, and then the mosaic image is OCR processed to produce text results. Text is selectively extracted from the OCR text results, depending on contents of a selector field on the screen image, such as a software version number or a heart pump model identifier.