Signature recognition method and device, storage medium, electronic equipment and product

By working together with detection, enhancement, and recognition sub-models, the problem of low accuracy in signature detection and recognition in existing technologies is solved. It achieves efficient signature region localization and feature analysis in complex backgrounds and low-quality images, thereby improving the accuracy and anti-counterfeiting capabilities of signature detection and recognition.

CN121708607APending Publication Date: 2026-03-20CHINA CONSTRUCTION BANK +1
0 Cites 2 Cited by

Patent Information

Application Number
CN202511766620.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-11-27
Publication Date
2026-03-20

AI Technical Summary

Technical Problem

Existing technologies cannot effectively improve the accuracy of signature detection and recognition when dealing with complex backgrounds and low-quality images.

Method used

The signature region is extracted by the detection sub-model, the image is enhanced by the preprocessing sub-model, and the signature features are obtained by the recognition sub-model. The target recognition result of the signature region is determined by combining deep learning algorithms, including multi-level feature extraction and feature fusion. CLAHE, DnCNN and ESRGAN are used for image processing. ResNet-50 is used for feature matching and GAN is used to generate forged signature samples for anti-counterfeiting detection.

Benefits of technology

It enables efficient and accurate location of signature regions under complex backgrounds and low-quality image conditions, optimizes image quality, and compares and analyzes signature features, thereby improving the accuracy and anti-counterfeiting capabilities of signature detection and recognition.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a signature recognition method and device, a storage medium, electronic equipment and a product, and the method comprises the steps: carrying out the extraction of a signature region in a file through a detection sub-model, and obtaining a first image; performing enhancement processing on the first image by using the preprocessing sub-model to obtain a second image; and obtaining a target signature feature in the second image through the identification sub-model, and determining the similarity between the target signature feature and a preset signature feature in a database, so as to determine a target identification result of the signature region based on the similarity. By adopting the technical scheme, the problem that the signature detection and recognition precision cannot be effectively improved when a complex background and a low-quality image are processed is solved. And furthermore, through cooperative work of the detection sub-model, the enhancement sub-model and the identification sub-model, a signature region is accurately positioned from the document, the image quality is optimized, and signature features are compared and analyzed, so that the authenticity of the signature is efficiently judged.
Need to check novelty before this filing date? Find Prior Art