Handwritten Document Search Indexing via Stroke Segmentation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing electronic devices with touch screen displays are not well-suited for business applications, and there is a lack of efficient technologies for searching handwritten documents.

Innovation Solution

An electronic device with a storage module, generator, and processor that stores handwritten documents as time-series information, generating index information for efficient search by character string likelihood, allowing for both handwriting and character string searches.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If handwritten documents are stored and searched using existing technologies, then the documents can be recognized and retrieved, but the search efficiency and precision are insufficient for business applications

Engineering Contradiction:
Improvesearch efficiencyVSAvoidsearch precision
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The patent segments handwritten documents into individual stroke data units, allowing for granular indexing and search operations. Each stroke is treated as a discrete element that can be independently analyzed and searched, improving both search efficiency and precision by breaking down complex handwritten content into manageable components.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent transforms handwritten stroke data into multiple parameter representations including time-series information, geometric features, and character string likelihood scores. By converting handwriting into various parametric forms, the system enables efficient searching through different dimensions while maintaining high precision in identifying handwritten content.

Inventive Principle:
Principle #35Parameter changes

2Ease of operation

If electronic devices are designed for consumer media consumption, then operability for images and music is improved, but suitability for business applications deteriorates

Engineering Contradiction:
Improveoperability for mediaVSAvoidsuitability for business applications
Core Design Contradiction:
Ease of operationVSAdaptability or versatility

Solution Approach 1:

The patent enables electronic devices to perform multiple functions by integrating handwriting recognition and search capabilities into existing touch screen systems. The device can simultaneously handle consumer media operations and business-related handwritten document management, making it versatile for both entertainment and professional applications without requiring separate dedicated devices.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system allows the electronic device to automatically recognize and process handwritten input without requiring external specialized equipment. The touch screen device itself provides the handwriting recognition and search functions, eliminating the need for separate handwriting recognition systems and enabling self-sufficient operation in business contexts.

Inventive Principle:
Principle #25Self-service

Data Source

PatentUS9183276B2Electronic device and method for searching handwritten document
Publication Date: 2015.11.10 DYNABOOK INC
  • US9183276B2 patent drawing
  • US9183276B2 patent drawing
  • US9183276B2 patent drawing

AI summary

According to one embodiment, an electronics device generates first and second index information, the first index information including codes of character strings corresponding to strokes, the second index information including characteristic quantity of strokes. The device executes at least either one of a first search and a second search, according to character string likelihood of first strokes which is a search key. The first search is performed by using the second index information and characteristic quantity of the first strokes. The second search is performed by using the first index information and a code of a character string corresponding to the first strokes.