计算机应用 ›› 2013, Vol. 33 ›› Issue (08): 2325-2329.

• 多媒体处理技术 • 上一篇    下一篇

基于并行运算的双层图像锐化方法

张巍1,贺星1,霍颖翔1,滕少华1,滕毅2,李日贵1   

  1. 1. 广东工业大学 计算机学院,广州 510006;
    2. 香港理工大学 纺织及成衣系,香港 999077
  • 收稿日期:2013-03-01 修回日期:2013-05-02 出版日期:2013-08-01 发布日期:2013-09-11
  • 通讯作者: 张巍
  • 作者简介:张巍(1964-),女,江西萍乡人,副教授,硕士,CCF会员,主要研究方向:数据挖掘、网络安全、协同计算、数学建模;
    贺星(1987-),男,湖南株洲人,硕士研究生,主要研究方向:算法设计、图像处理;
    霍颖翔(1989-),男,广东广州人,主要研究方向:算法设计与实现;
    滕少华(1962-),男,江西南昌人,教授,博士,CCF会员,主要研究方向:协同计算、数据挖掘、网络安全;
    滕毅(1986-),女,江西南昌人,博士研究生,主要研究方向:数据建模、计算机仿真;
    李日贵(1989-),男,广东茂名人,主要研究方向:算法设计。
  • 基金资助:
    国家自然科学基金资助项目;教育部重点实验室基金资助项目;广东省自然科学基金资助项目;广东省科技计划项目;广东省科技计划项目

Bi-level image sharpening method based on parallel computing

ZHANG Wei1,HE Xing1,HUO Yingxiang1,TENG Shaohua1,TENG Yi2,LI Rigui1   

  1. 1. School of Computer Science and Technology, Guangdong University of Technology, Guangzhou Guangdong 510006, China
    2. Institute of Textile and Clothing, The Hong Kong Polytechnic University, Hong Kong 999077, China
  • Received:2013-03-01 Revised:2013-05-02 Online:2013-09-11 Published:2013-08-01
  • Contact: ZHANG Wei

摘要: 针对低清晰度照片或图像放大后边界模糊、画质差及人们对高清图像的实际需求,基于统一计算架构(CUDA)环境,提出了一个两层结构的图像并行锐化方法,设计并实现了一个基于GPU的并行锐化算法:第一层采用并行线性插值法,反复对图像非边界部分进行计算以及边缘区域锐化处理;第二层采用改进的梯度法对图像进一步优化。放大后的图像经该方法处理后,基本上可消除图像边缘区域的锯齿,使图像画质平滑、自然、清晰。经实验验证,设计的基于GPU的并行锐化算法在效率和画质上都优于目前流行的算法,提出的方法可应用于现有图像及照片放大后处理。

关键词: 图像放大, 图像锐化, 并行设计, 双层锐化算法, 梯度优化

Abstract: A parallel bi-level image sharpening methodology in Compute Unified Device Architecture (CUDA) circumstance was proposed especially for the improvements on fuzzy boundaries and poor quality when enlarging low resolution photos or images. A GPU-based parallel sharpening algorithm with two stages was designed and implemented. Firstly, the parallel linear interpolation algorism was repeatedly adopted by the calculation of non-edge region and the sharpening treatments of edge area. Secondly, an improved gradient method was utilized for the further optimized images. The jagged edges of the enlarged images were basically eliminated by the proposed method, making the images much more smooth, natural, and legible. The experimental results prove that the GPU-based parallel image sharpening algorithm is superior to the currently popular algorithms in calculation efficiency and image quality, and it can be applied in sharpening images and amplifying photos.

Key words: image zooming, image sharpening, parallel design, bi-level sharpening algorithm, gradient optimization

中图分类号: