现代信息科技2026，Vol.10Issue(4)：116-121,6.DOI:10.19850/j.cnki.2096-4706.2026.04.020
面向结构化文本图像的四元数卷积神经网络模型设计
Design of Quaternion Convolutional Neural Network Model for Structured Text Images
摘要
Abstract
This paper designs a Quaternion Convolutional Neural Network(QCNN)for structured text images to address the problem of insufficient feature coupling and robustness drop in real-valued Convolutional Neural Networks caused by character adhesion and color fraud in complex color CAPTCHA recognition.This network encodes RGB pixels as a vector field using pure quaternions,and achieves full process hypercomplex processing through Hamilton product convolution,Phasor ReLU,and the generalized HR differential optimizer.It is compared with baseline models such as ResNet-18 on a 3 000 self-built strong interference dataset.The experimental results show that the character level accuracy of QCNN reaches 97.8%,and the sequence level accuracy is 96.4%,significantly better than existing real and complex models,providing a new approach for high interference structured text image recognition.关键词
四元数卷积神经网络/结构化文本图像/验证码识别/色彩矢量建模/Hamilton积Key words
Quaternion Convolutional Neural Network/structured text image/CAPTCHA recognition/color vector modeling/Hamilton product分类
信息技术与安全科学引用本文复制引用
马阳..面向结构化文本图像的四元数卷积神经网络模型设计[J].现代信息科技,2026,10(4):116-121,6.基金项目
江西省教育厅科学技术研究项目(GJJ2210602) （GJJ2210602）
