Form Image Stroke Classification and Standardization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing processes for processing form images using portable computing devices are error-prone and time-consuming, particularly in converting strokes to text, as they often require unnecessary OCR or OMR processing and are complicated in identifying and extracting information from forms.
Innovation Solution
A system and method utilizing an Image Based Document Management (IBDM) server with components like a controller, stroke identification module, geometry engine, label detector, table generator, field image classifier, stroke standardizer, symbolic representation module, query engine, and user interface engine to identify, classify, and standardize strokes, generating field images and labels, and sorting them efficiently.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If OCR or OMR is applied to all strokes to convert them into text, then text conversion is performed, but the process becomes error-prone and time-consuming
Solution Approach 1:
The patent extracts only the necessary strokes for conversion to text, rather than applying OCR/OMR to all strokes. The system identifies and selects specific strokes that require conversion, eliminating unnecessary processing and reducing errors while saving time.
Solution Approach 2:
The patent applies partial action by converting only the subset of strokes that need text conversion, rather than processing all strokes uniformly. This selective approach reduces processing time and minimizes conversion errors by focusing resources only where needed.
2Loss of information
If all strokes are processed through OCR or OMR, then complete text conversion is achieved, but unnecessary processing increases complexity and errors
Solution Approach 1:
The system extracts and identifies only the relevant strokes that require text conversion, separating them from strokes that do not need processing. This reduces processing complexity while maintaining complete text conversion for all necessary elements.
Solution Approach 2:
The patent applies different processing approaches to different strokes based on their characteristics and requirements. Some strokes undergo OCR/OMR conversion while others are handled differently, optimizing the overall process by applying the right treatment to each stroke locally.
3Productivity
If forms are processed by identifying the form, extracting information about fields and performing actions, then form processing is completed, but the process is time-consuming and complicated
Solution Approach 1:
The patent performs preliminary actions by pre-identifying form structures, field locations, and stroke classifications before the main processing occurs. This preliminary organization enables faster subsequent processing and reduces overall form handling time.
Solution Approach 2:
The system segments the form processing into distinct components: form identification, field extraction, stroke identification, and text conversion. This segmentation allows each component to be optimized independently and processed in an efficient pipeline, improving overall productivity.
Data Source
AI summary
A system and method for processing form images including strokes. A stroke identification module identifies the position of each stroke in each of form image. A geometry engine identifies a group of overlapping strokes from an overlay of the plurality of form images. The geometry engine generates a field bounding box encompassing the group of strokes and generates a field image from each form image based on the field bounding box. A label detector analyzes an area around the field image in the form image and generates a label image. A field image classifier determines stroke features for field images associated with a field. The field image classifier classifies the field images into one or more groups based on the stroke features. A stroke standardizer determines a representative image for field images associated with a field.