Dynamic OMR Model and Template Identification for Flexible Mark Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing optical mark recognition (OMR) systems are rigid and require specialized scanning hardware or pre-determined templates, limiting their flexibility and ability to detect marks in varying formats, particularly in voting stations where different ballot forms may be used.
Innovation Solution
A multifunction peripheral (MFP) system that uses a dynamic model and template identification, where metadata is generated and applied based on page description language documents to identify positional templates and OMR models, allowing for flexible mark recognition without the need for pre-defined templates, and incorporates a visible label to encode metadata for accurate mark detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If pre-determined templates are used for OMR, then the system can reliably detect marks in standardized formats, but the system becomes rigid and cannot handle varying document formats
Solution Approach 1:
The patent implements dynamic template generation that adapts to different document formats in real-time. Instead of using fixed pre-determined templates, the system generates templates dynamically based on the specific characteristics of each scanned document, allowing it to maintain reliability across varying formats while eliminating rigidity
Solution Approach 2:
The system changes parameters such as mark position coordinates, bubble sizes, and template dimensions based on the analyzed document characteristics. By adjusting these parameters dynamically rather than using fixed values, the system achieves both reliable mark detection and adaptability to different document formats
2Measurement precision
If specialized scanning hardware is used for OMR, then mark detection precision is improved, but device complexity and cost increase
Solution Approach 1:
The multifunction peripheral uses its existing scanning capabilities to perform OMR operations without requiring specialized hardware. The system leverages resources already present in the device, eliminating the need for additional specialized scanning hardware while maintaining mark detection precision through software-based template generation and analysis
Solution Approach 2:
The patent enables the multifunction peripheral to perform multiple functions including scanning, OMR, and document processing using the same hardware resources. By making the scanning system universal and capable of handling both general scanning and specialized OMR tasks, the system achieves high precision without increasing device complexity or requiring specialized hardware
3Productivity
If fixed templates are required for OMR operations, then processing speed is maintained, but the system cannot accommodate different ballot forms or document variations
Solution Approach 1:
The system performs preliminary analysis of the scanned document to identify characteristics such as mark positions, document layout, and format type before generating the appropriate template. This preliminary action enables rapid template generation tailored to each document, maintaining processing speed while achieving adaptability to different ballot forms and document variations
Data Source
AI summary
A system for multifunction peripheral assisted optical mark recognition uses a scanner to scan at least one printed page to generate a scanned image of the at least one printed page and to optically detect a presence of a visible label on the scanned image. Then, the multifunction peripheral may extract a model identification and a template identification from the visible label, select a template, identifying locations from which image data is to be extracted from the scanned image, select a model, specifically identifying at least two types of acceptable marks within the image data to be extracted from the scanned image, and perform optical mark recognition on the location from which image data is to be extracted identified by the template using the at least two types of acceptable marks identified by the model to extract useful data from the image data.