Hand and Machine Print Discrimination via Binarization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for processing digital images to distinguish between machine-printed, hand-printed, and signature markings are limited in accuracy and feasibility, especially when using mobile devices, which struggle to capture and process documents effectively due to limitations in image resolution and processing capabilities.
Innovation Solution
A computer program product that receives an image, determines its color depth, reduces it to bi-tonal representation, identifies graphical line candidates, discriminates true graphical lines from false positives, and generates a component map to identify connected components, which are then labeled as machine-printed, hand-printed, or signature characters, using techniques such as connected component analysis and neural networks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If mobile devices are used to capture and process documents, then convenience and accessibility are improved, but image resolution and processing accuracy deteriorate
Solution Approach 1:
The patent segments the image processing task into multiple stages: initial capture, color depth reduction to bi-tonal, graphical line candidate identification, discrimination of true lines from false positives, and connected component analysis. This segmentation allows mobile devices to process images efficiently at each stage without requiring high resolution throughout the entire process.
Solution Approach 2:
The patent applies partial action by reducing color depth to bi-tonal representation before full processing, and by identifying only graphical line candidates rather than processing all image features. This partial processing approach maintains sufficient accuracy for signature detection while reducing computational requirements for mobile devices.
2Measurement precision
If complex image processing techniques are applied to distinguish handwriting types, then classification accuracy is improved, but processing time and computational complexity increase
Solution Approach 1:
The patent performs preliminary actions by first reducing color depth to bi-tonal and removing graphical lines before conducting connected component analysis. These preliminary processing steps simplify the image data structure, making subsequent classification faster and more accurate without requiring complex algorithms at later stages.
Solution Approach 2:
The patent replaces complex mechanical image processing with computational methods: using connected component analysis and neural networks to automatically classify handwriting types. This substitution reduces processing time by leveraging efficient algorithms rather than manual or brute-force methods.
3Productivity
If color depth is reduced to bi-tonal representation, then processing efficiency is improved, but information loss increases
Solution Approach 1:
The patent extracts only the essential information needed for signature detection by converting to bi-tonal representation and removing graphical lines. This extraction process eliminates unnecessary color and graphical data that would consume processing resources, while preserving the structural information required for connected component analysis and handwriting classification.
Data Source
AI summary
Computer program products for discriminating hand and machine print from each other, and from signatures, are disclosed and include program code readable and/or executable by a processor to: receive an image, determine a color depth of the image; reducing the color depth of non-bi-tonal images to generate a bi-tonal representation of the image; identify a set of one or more graphical line candidates in either the bi-tonal image or the bi-tonal representation, the graphical line candidates including true graphical lines and/or false positives; discriminate any of the true graphical lines from any of the false positives; remove the true graphical lines from the bi-tonal image or the bi-tonal representation without removing the false positives to generate a component map comprising connected components and excluding graphical lines; identify one or more of the connected components in the component map; and output and/or display and indicator of each of the connected components.