Inferring Stroke Timing for Hand-Drawn Text Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Intelligent character recognition (ICR) performance suffers when applied to archived images of hand-drawn text characters, as timing information is not available, leading to reduced accuracy and efficiency in recognizing the characters.
Innovation Solution
A method and system that extract character segments from an image, determine character bounding boxes, and analyze directions and timing properties such as ordering and drawing duration, which are then sent to an ICR engine to improve recognition accuracy by providing context to the engine.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If ICR is performed on archived images without timing information, then the images can be recognized, but the recognition accuracy and efficiency deteriorate
Solution Approach 1:
The patent applies preliminary action by pre-determining the ordering and drawing duration of character segments before performing ICR. The system divides characters into segments, determines their temporal ordering and duration, and uses this pre-analyzed timing information to guide the ICR process, thereby compensating for the lack of original timing data in archived images and improving recognition accuracy
Solution Approach 2:
The patent changes parameters by introducing synthetic timing parameters (ordering sequences and drawing duration values) to the archived image data. These parameters are derived from spatial relationships and visual features of character segments, transforming static image data into dynamic temporal representations that the ICR engine can process more effectively
2Productivity
If timing information is not available for archived images, then ICR can still be performed, but the efficiency and speed of recognition deteriorate
Solution Approach 1:
The patent applies segmentation by dividing characters into multiple character segments and processing them in determined orderings. This segmentation allows the system to analyze and recognize character parts sequentially based on spatial and visual features, improving processing efficiency by breaking down complex recognition tasks into manageable segments with inferred temporal relationships
3Measurement precision
If character segments are processed without determined ordering and duration, then processing is simpler, but recognition accuracy deteriorates
Solution Approach 1:
The patent applies preliminary action by pre-determining the ordering and drawing duration of character segments before ICR processing. This preliminary analysis of spatial relationships and visual features creates a temporal framework that guides subsequent recognition, improving precision without requiring complex real-time temporal analysis during the ICR process itself
Data Source
AI summary
A method for character recognition. The method includes: obtaining a plurality of character segments extracted from an image; determining a first character bounding box having a first set of the plurality of character segments and a second character bounding box having a second set of the plurality of character segments; determining a plurality of directions for the first set and a plurality of timing properties for the first set, where the plurality of timing properties includes an ordering for first set and a drawing duration for the first set; and executing character recognition for the first character bounding box by sending the first set, the plurality of directions for the first set, and the plurality of timing properties for the first set to an intelligent character recognition (ICR) engine.