面向透射文档图像复原的模糊扩散模型  

Fuzzy diffusion model for seen-through document image restoration

作　　者：王义杰 龚嘉鑫 梁宗宝 崇乾鹏 程翔[2] 徐金东 Wang Yijie;Gong Jiaxin;Liang Zongbao;Chong Qianpeng;Cheng Xiang;Xu Jindong(School of Computer and Control Engineering,Yantai University,Yantai 264005,China;School of Information Science and Technology,Peking University,Beijing 100871,China)

机构地区：[1]烟台大学计算机与控制工程学院,烟台264005 [2]北京大学信息科学与技术学院,北京100871

出　　处：《中国图象图形学报》2025年第4期1118-1129,共12页Journal of Image and Graphics

基　　金：烟台市科技创新发展计划基础研究重点项目(2024JCYT037);国家自然科学基金项目(62072391,62066013)。

摘　　要：目的在对文档进行数码成像时,墨水浓度和材质透明度等因素可能会导致文档背面内容透过纸张变得可见,从而导致数字图像中出现透射现象,影响文档图像的实际使用。针对这一现象,提出了一种模糊扩散模型,基于模糊逻辑的均值回归思想,不需要任何先验知识,增强扩散模型处理文档图像中随机因素的能力,不仅解决了文档图像的透射现象,而且增强了图像的视觉效果。方法所提方法通过均值回归随机微分方程连续添加随机噪声降低原始图像质量,将其转换为带有固定高斯噪声的透射均值状态,随后在噪声网络中引入模糊逻辑操作来推理每个像素点的隶属度关系,使模型更好地学习噪声和数据分布,在逆向过程中,通过模拟相应的逆时间随机微分方程来逐渐恢复低质量图像,获得干净的无透射图像。结果将所提方法分别在合成灰度数据集和合成彩色数据集上进行训练,并在3个合成数据集和2个真实数据集上进行测试,与代表性的5种方法进行了比较,所提方法取得了最好的视觉效果,且在一定程度上消除了原始图像中的噪声。在峰值信噪比(peak signal-to-noise ratio,PSNR)、结构相似性(structural similarity index,SSIM)、学习感知图像块相似度(learned perceptual image patch similarity,LPIPS)和费雷歇初始距离(Fréchet inception distance,FID)4个评价指标上均取得了最好的结果。结论本文方法能够有效地解决不同类型文档图像中的透射现象,提高了文档图像去透射任务的准确性和效率,有望集成到各种摄像头、扫描仪等实际硬件设备。Objective Document images have significant applications across various fields,such as optical character recognition(OCR),historical document restoration,and electronic reading.While scanning or shooting a document,factors such as ink density and paper transparency may cause the content from the reverse side to become visible through the paper,resulting in a digital image with a“seen-through”phenomenon that affects practical applications.Image acquisition is often affected by various sources of uncertainty,including differences in camera equipment performance,paper quality,lighting conditions,lens shake,and variations in the physical properties of the documents themselves.All these random factors contribute to the noise in document images and may complicate the seen-through phenomenon,thereby influencing subsequent tasks such as text recognition,word identification,and layout analysis.Although restoring the content of document images is important,the backgrounds of many color document images also provide valuable information.Recovering color images with complex backgrounds affected by the seen-through phenomenon presents its own challenges.Despite the improvement in image quality achieved by existing methods for removing seen-through effects from document images,algorithms specifically tailored to handle variations in seen-through effects,complex background colors,and influence of uncertainty factors have not yet been developed.This work aims to develop a comprehensive algorithm for addressing the diverse seen-through problems in regular document images,handwritten document images,and color document images.We propose the fuzzy diffusion model(FDM)that integrates fuzzy logic with conditional diffusion models,introducing a novel approach to document image enhancement and restoration.The objective of this algorithm is to restore document images affected by various types and degrees of seen-through phenomenon.Method The overall process of this algorithm can be divided into forward diffusion and corresponding rever

关 键 词：扩散模型 模糊逻辑 图像复原 透射去除 随机微分方程(SDE) 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]