首页> 外文期刊>Image Processing, IET >Blending-weight diffusion for image colourisation
【24h】

Blending-weight diffusion for image colourisation

机译:混合权重扩散使图像着色

获取原文
获取原文并翻译 | 示例
           

摘要

An image colourisation method based on diffusion of colour-blending weights is presented. The authors propose to use reciprocal function for smoothness measurement to determine the priority order of colour propagation in image colourisation. The reciprocal measurement can improve the recent exponential-measurement-based propagation, which has a trend towards being greedy for smooth pixels, and is likely to cause wrong boundaries nearby the object juncture joining the grey levels without significant difference. In addition, the proposed method uses the blending-weight diffusion instead of the direct propagation of chrominance values. By doing so, it can respond quickly to the user demand for stroke editing. Experimental results show that compared with the exponential-measurement-based propagation, the proposed method filled colours more precisely in the positions representing real object surfaces, and saved 85.92% of computation time for adding a stroke and 98.60% for deleting a stroke, to an illustrative image. Compared with two conventional techniques which also implement-blending weights, this method can provide the blending weights for acceptable colourisation by using the economical strokes which positions are less constrained and which sizes are reduced.
机译:提出了一种基于混色权重扩散的图像着色方法。作者建议使用倒数函数进行平滑度测量,以确定图像着色中颜色传播的优先顺序。倒数测量可以改善最近的基于指数测量的传播,这种传播趋向于对平滑像素贪婪,并且有可能在对象接合点附近导致错误的边界接合灰度级而没有明显差异。另外,所提出的方法使用混合权重扩散而不是色度值的直接传播。这样,它可以快速响应用户对笔划编辑的需求。实验结果表明,与基于指数测量的传播相比,该方法在代表真实物体表面的位置上更精确地填充了颜色,并为添加笔划节省了85.92%的计算时间,而删除笔划则节省了98.60%的计算时间。说明性图像。与也实现混合权重的两种常规技术相比,该方法可以通过使用经济的笔划来提供用于可接受的着色的混合权重,该笔画的位置约束较小,尺寸减小。

著录项

  • 来源
    《Image Processing, IET》 |2012年第6期|p.786-794|共9页
  • 作者

    K.-C. Ho; Y.-T. Chung;

  • 作者单位

    Department of Electronic Engineering, National United University;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号