Whiteboard Image Comparison for Vectorization Automation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Vectorization software struggles to accurately convert complex and indecipherable whiteboard drawings into electronic formats without human assistance, as it is confused by complicated markings and erasures over time.
Innovation Solution
A system and method that captures 'before' and 'after' images of a writing surface using a camera, compares them to identify changes, and uses image processing to extract and display the modified objects, allowing for conversion into digital formats such as text, flowcharts, or vector graphics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If vectorization software processes complex whiteboard drawings directly, then conversion to electronic formats is attempted, but the software becomes confused by complicated markings and erasures over time
Solution Approach 1:
The system performs preliminary actions by capturing a 'before' image of the whiteboard before any modifications occur. This baseline image is stored and later used for comparison with the 'after' image to automatically identify changes, eliminating the need for manual intervention while maintaining high conversion accuracy
Solution Approach 2:
The system implements feedback by comparing the 'after' image with the stored 'before' image to identify differences. This feedback mechanism allows the software to automatically detect added or removed markings, resolving the confusion caused by complicated whiteboard histories and enabling reliable automated conversion
2Manufacturing precision
If manual assistance is provided to identify separate elements on the whiteboard, then conversion accuracy improves, but human intervention increases time and effort requirements
Solution Approach 1:
The system practices self-service by automatically comparing images and identifying changes without human assistance. The software independently determines which markings were added or removed by analyzing pixel differences between the 'before' and 'after' images, achieving both high precision and time efficiency
Solution Approach 2:
The system replaces the mechanical process of manual element identification with an automated image processing mechanism. By substituting human visual inspection with computer-based image comparison algorithms, the system achieves equivalent or superior precision while eliminating time loss associated with manual intervention
3Productivity
If the whiteboard is used extensively over time with multiple markings and erasures, then more content can be developed, but the complexity and indecipherability of the whiteboard contents increases
Solution Approach 1:
The system applies segmentation by dividing the complex whiteboard content into discrete change elements through image comparison. By segmenting the overall whiteboard state into individual added or removed markings, the system manages complexity while preserving the ability to process extensive content developments over time
Solution Approach 2:
The system uses preliminary action by capturing and storing the initial 'before' image before content development begins. This baseline allows subsequent changes to be identified clearly against a known reference state, enabling the system to handle extensive content development without being overwhelmed by accumulating complexity
Data Source
AI summary
A method, a non-transitory computer readable medium (CRM), and an apparatus are disclosed for processing images on a writing board. The method includes: capturing a first image of one or more objects on the writing board; capturing a second image of the one or more objects on the writing board after at least one object has been removed and/or modified on the writing board; extracting the at least one object from the first image by comparing the first image to the second image and constructing a digital image via an image processing application; and displaying the digital image of the extracted at least one object on a display screen of a device.