计算机应用 ›› 2013, Vol. 33 ›› Issue (07): 2002-2004.DOI: 10.11772/j.issn.1001-9081.2013.07.2002

• 多媒体技术 • 上一篇    下一篇

GPU并行实现的基于多方向线状梯度调节预测器边缘检测算法

党向盈,鲍蓉,姜代红   

  1. 徐州工程学院 江苏省大型工程装备检测与控制重点建设实验室,江苏 徐州 221000
  • 收稿日期:2013-01-16 修回日期:2013-03-12 出版日期:2013-07-01 发布日期:2013-07-06
  • 通讯作者: 党向盈
  • 作者简介:党向盈(1978-),女,江苏徐州人,讲师,硕士,CCF会员,主要研究方向:图像处理、模式识别;鲍蓉(1968-),女,江苏徐州人,教授,博士,CCF会员,主要研究方向:模式识别、嵌入式技术;姜代红(1969-),女,湖南郴州人,教授,博士研究生,主要研究方向:模式识别、嵌入式技术。
  • 基金资助:

    江苏省高校科研成果产业化推进工程项目(JHB2012-36);江苏省科技支撑计划(工业)项目(BE2011048)

GPU parallel implementation of edge-detection algorithm based on multidirectional linear gradient adjusted predictor

DANG Xiangying,BAO Rong,JIANG Daihong   

  1. Jiangsu Key Laboratory of Large Engineering Equipment Detection and Control, Xuzhou Institute of Technology, Xuzhou Jiangsu 221000, China
  • Received:2013-01-16 Revised:2013-03-12 Online:2013-07-06 Published:2013-07-01
  • Contact: DANG Xiangying

摘要: 针对无损压缩编码中梯度调节预测器(GAP)模板的方向固定、单一的问题,根据实际边缘具有线状变化增量相同的特征,提出多方向线状梯度调节预测器(MLGAP)模板。首先从图像中心向四周划分四个子图像,应用图形处理器(GPU)并行技术,在每个子图像中采用MLGAP模板计算预测值;然后利用错误反馈信息构建预测误差图像;再通过大津(OTSU)算法计算阈值;分类误差图像边缘;最后用Hilditch算法细化边缘。实验结果表明,图像边缘检测定位精确,噪声少,细节丰富,而且GPU并行技术加速了图像处理。

关键词: 多方向线状梯度调节预测器, 图形处理器, 大津算法, 阈值, 细化

Abstract: Concerning the fixed direction and monotony of lossless image compression template of Gradient Adjusted Predictor (GAP), according to the characteristic of the actual edge with the same linear increments, this paper proposed Multidirectional Linear Gradient Adjusted Predictor (MLGAP) template. Firstly the image was cut into four sub-images from the center to the periphery. With the application of Graphics Processor Unit (GPU) parallel technology operation, the predictive value was calculated by MLGAP template in each sub-image, and then error feedback was used to construct prediction error image. The threshold was calculated by OSTU algorithm, and error image edge was classified. At last the edge was thinned by Hilditch algorithm. The simulation results show that using the proposed method can get clear, complete and precise edges. In addition, the GPU parallel technology accelerates the image processing.

Key words: Multidirectional Linear Gradient Adjusted Predictor (MLGAP), Graphic Processing Unit (GPU), OTSU algorithm, threshold, thinning

中图分类号: