A handwriting erasing method based on sentence-level connected domain generation and region-aware description feature extraction

By using sentence-level connected component generation and region-aware descriptive feature extraction, the problem of high precision and high efficiency in handwritten and printed text segmentation on edge devices is solved, achieving accurate erasure of handwritten characters and structural stability of printed text, which is suitable for multilingual document processing.

CN122200698BActive Publication Date: 2026-07-21CHENGDU UNIV +1
2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
CHENGDU UNIV
Filing Date
2026-05-14
Publication Date
2026-07-21

AI Technical Summary

Technical Problem

Existing technologies struggle to achieve high-precision segmentation and efficient processing of handwritten and printed text on resource-constrained edge devices, especially in the case of interwoven strokes and complex backgrounds. Existing methods cannot effectively remove handwritten areas, making it difficult to balance segmentation accuracy and computational efficiency.

Method used

We employ a method of sentence-level connected component generation and region-aware descriptive feature extraction. By segmenting sentence-level connected components and extracting region-aware handwritten descriptor features, we construct a lightweight classification model. Using a random forest decision system, we explicitly model the spatial statistical distribution differences between handwritten and printed characters to achieve the erasure of handwritten characters.

Benefits of technology

While maintaining high accuracy, it significantly reduces computational complexity, improves processing speed, adapts to multilingual documents and reduces power consumption, is suitable for resource-constrained embedded devices, and achieves precise erasure of handwritten text and structural stability of printed text.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122200698B_ABST
    Figure CN122200698B_ABST
Patent Text Reader

Abstract

The application discloses a handwriting character erasing method based on sentence-level connected domain generation and region perception description feature extraction, which is applied to the field of text segmentation and aims at the problem that the existing technology is difficult to capture the fine visual difference between handwriting and printed matter and the segmentation precision is far from reaching the industrial standard. The application firstly introduces a minimum discrimination unit system taking a sentence-level connected domain as a core to realize accurate conversion of physically discrete components into semantically consistent units by using a union-find set and an adaptive threshold aggregation mechanism; then, feature modeling is carried out by using the physical difference between the inherent variability of handwriting and the structural uniformity of printed matter; finally, attribute mapping is carried out by using the extracted high-dimensional feature vector, and handwriting character erasing is realized based on the mapping result. The application can effectively avoid the misdeletion of printed text under the scene of stroke interlacing and complex background, reduce handwriting residues, improve erasing integrity and keep the stability of the layout structure of the original document.
Need to check novelty before this filing date? Find Prior Art