| 改进的规范化卷积图像修复算法 |
| |
| 引用本文： | 秦绪佳,桑贤生,程时伟,徐晓刚. 改进的规范化卷积图像修复算法[J]. 计算机辅助设计与图形学学报, 2011, 23(2) |
| |
| 作者姓名： | 秦绪佳 桑贤生 程时伟 徐晓刚 |
| |
| 作者单位： | 1. 浙江工业大学计算机科学与技术学院,杭州,310032
2. 大连舰艇学院装备系统与自动化系,大连,116018;浙江大学CAD&CG国家重点实验室,杭州,310058 |
| |
| 基金项目： | 国家自然科学基金(61075118,60975016,61005056); 浙江省自然科学基金(Y1080436,Y1100880); 浙江省科技计划(2009C31106); 浙江大学CAD&CG国家重点实验室开放课题(A0906) |
| |
| 摘 要： | 规范化卷积算法可用来处理离散、孤立丢失数据的修复,但针对大量数据连续缺失的图像修复效果不佳,为此设计了像素的邻域滤波器,提出一种改进的基于规范化卷积的图像修复算法.首先设定由待修复区域边界向区域内部逐步扩散的修复顺序;然后为每个待修复像素关联一个置信度,并根据修复的先后顺序从高到低进行赋值,即最后修复的像素置信度取值最小;最后根据像素值和置信度进行插值,修复缺失的图像信息.实验结果表明,该算法是一种实用的图像修复算法,可实现图像连续块状区域信息丢失的修复,并可得到良好的修复效果.
|
| 关 键 词： | 规范化卷积 图像修复 插值 |
An Improved Image Inpainting Algorithm Based on Normalized Convolution |
| |
| Qin Xujia,Sang Xiansheng,Cheng Shiwei,Xu Xiaogang. An Improved Image Inpainting Algorithm Based on Normalized Convolution[J]. Journal of Computer-Aided Design & Computer Graphics, 2011, 23(2) |
| |
| Authors: | Qin Xujia Sang Xiansheng Cheng Shiwei Xu Xiaogang |
| |
| Affiliation: | Qin Xujia1),Sang Xiansheng1),Cheng Shiwei1),and Xu Xiaogang2,3)1)(School of Computer Science and Technology,Zhejiang University of Technology,Hangzhou 310032) 2)(Department of Equipment System and Automatization,Dalian Naval Academy,Dalian 116018) 3)(State Key Laboratory of CAD & CG,Zhejiang University,Hangzhou 310058) |
| |
| Abstract: | Although normalized convolution(NC) algorithm can be used to repair discrete isolated data loss,the image inpainting performance for the continuous block data loss using NC isn't good.A filter of neighborhood of pixel is defined,and a new image inpainting algorithm based on NC is proposed.The repair order for the loss block data is from the block borders gradually spread to the center.Then,each pixel of the image block is assigned to a confidence,and each pixel is set a confidence value from high to low acc... |
| |
| Keywords: | normalized convolution image inpainting interpolation |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
