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.
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
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.
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.
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.
Smart Images

Figure CN122200698B_ABST