Vector Image Conversion for Handwritten Note Recognition

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional electronic devices struggle with accurately recognizing handwritten characters and automatically categorizing captured notes, leading to low usability due to low character recognition accuracy and lack of automated organization methods.

Innovation Solution

A content processing method that converts captured handwritten notes into vector images, allowing for easy editing and categorization, where the notes are stored as digital files and automatically arranged for better readability and organization.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional image recognition techniques are used to recognize handwritten characters, then the system can process captured images, but the character recognition accuracy is low

Engineering Contradiction:
Improvecharacter recognition accuracyVSAvoidrecognition reliability
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The patent transforms the parameter representation of handwritten characters from raster image format to vector format using spline curves. This parameter change enables precise mathematical representation of character shapes, allowing for accurate recognition even with rough handwriting. The vector representation captures the essential geometric features of characters while being invariant to minor variations in handwriting style.

Inventive Principle:
Principle #35Parameter changes

2Ease of operation

If users manually categorize captured images, then content organization is achieved, but user convenience is reduced due to manual effort required

Engineering Contradiction:
Improveuser convenienceVSAvoidtime for manual categorization
Core Design Contradiction:
Ease of operationVSLoss of time

Solution Approach 1:

The patent implements automatic categorization functionality that enables the system to self-organize captured content without user intervention. By analyzing vectorized character content and automatically assigning categories, the system performs the categorization task itself, eliminating the need for manual user effort and time investment while maintaining effective content organization.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent performs preliminary vectorization and content analysis of captured images immediately upon capture. By converting images to vector format and extracting content features in advance, the system prepares the data for automatic categorization, enabling seamless automated organization without requiring subsequent manual processing or user time investment.

Inventive Principle:
Principle #10Preliminary action

3Ease of manufacture

If handwritten notes are captured as images, then content can be stored, but the notes cannot be easily edited or managed

Engineering Contradiction:
Improveease of content editingVSAvoidcontent management complexity
Core Design Contradiction:
Ease of manufactureVSDevice complexity

Solution Approach 1:

The patent replaces the mechanical image processing approach with a mathematical vector-based system. By representing handwritten notes as vector graphics defined by spline curves and control points, the system enables programmatic manipulation and editing of note content. This substitution allows for easy modification, search, and management of notes through mathematical operations rather than pixel-level image processing.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS10430648B2Method of processing content and electronic device using the same
Publication Date: 2019.10.01 SAMSUNG ELECTRONICS CO LTD
  • US10430648B2 patent drawing
  • US10430648B2 patent drawing
  • US10430648B2 patent drawing

AI summary

A method for processing content in an electronic device and an electronic device for doing the same are provided. The method includes acquiring content including at least one character, and performing at least one of classifying the acquired content into at least one of a plurality of categories by analyzing the acquired content or generating vector images including a vector image corresponding to the at least one character based on the acquired content and displaying at least a part of the vector images on a display functionally connected to the electronic device.