Handwritten Document Recognition Using Hash-Based Area Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional electronic devices face inefficiencies in character recognition and storage of handwritten documents, particularly when editing is involved, as they often require re-recognition of unchanged portions, leading to increased processing time and power consumption.
Innovation Solution
An electronic apparatus that compares handwritten documents before and after editing, using hash values to identify unchanged areas and only re-recognizing differing strokes, thereby reducing unnecessary character recognition and preserving recognized text data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If character recognition is performed on the entire handwritten document every time it is saved or edited, then recognition accuracy is maintained, but processing time and power consumption increase
Solution Approach 1:
The handwritten document is divided into multiple areas, and character recognition is performed independently for each area. This segmentation allows the system to process only the necessary portions of the document, reducing overall processing time while maintaining recognition accuracy for each segment.
Solution Approach 2:
The system determines whether to perform character recognition on a per-area basis rather than uniformly across the entire document. By applying recognition only to areas that require it (newly created or edited areas), the system optimizes processing efficiency while maintaining accuracy where needed.
2Reliability
If character recognition is performed on the entire handwritten document every time it is saved or edited, then up-to-date recognition results are ensured, but power consumption increases
Solution Approach 1:
The document is segmented into multiple areas for independent processing. This allows the system to consume power only when processing specific areas that require recognition, rather than continuously processing the entire document, thus reducing overall power consumption while maintaining result currency.
Solution Approach 2:
The system performs character recognition partially - only on the necessary areas (newly created or edited) rather than excessively processing the entire document every time. This partial action approach reduces power consumption while still ensuring recognition results are up-to-date for the relevant portions.
3Reliability
If the same handwritten document is re-recognized after editing, then updated recognition results are obtained, but redundant processing occurs
Solution Approach 1:
The document is divided into multiple areas, allowing the system to identify and process only the areas that have been edited or newly created. This segmentation eliminates redundant processing of unchanged areas, improving processing efficiency while maintaining accuracy for the relevant segments.
Solution Approach 2:
The system performs preliminary identification of areas requiring recognition by comparing the current document state with previous versions. This preliminary action allows the system to skip unchanged areas and directly process only the areas that need updated recognition, improving efficiency without compromising accuracy.
Data Source
AI summary
According to one embodiment, an electronic apparatus performs a character recognition process, uses, if a stroke in a first area of the first handwritten document and a stroke in a second area are the same, a character recognition result of the first handwritten document, and performs, if a stroke in the first area and a stroke in the second area are different, the character recognition process for the second area including the different stroke.