摘要
为了解决传统方法无法很好保持图像边缘细节,通过极值检测算法检测甲骨拓片图像噪声点,利用双边滤波方法将空间域与值域的像素点邻域信息集合,滤除甲骨拓片图像噪声,针对甲骨拓片图像不同噪声,调整双边滤波空间标准参数与亮度标准参数,保持滤波噪声的下甲骨拓片图像边缘信息.从主观视觉效果与客观质量评价验证滤波性能,结果表明:所提方法在降低甲骨拓片图像噪声的同时,可保持图像边缘细节信息;相同噪声水平下,该方法滤波后峰值信噪比与结构相似性高于其它两种方法,去噪结果三维图更优.可见所提方法能够保持原图像细节与边缘,有很好的去噪效果.
In order to solve the problem that the traditional method cannot keep the image edge details well,the extremum detection algorithm is used to detect the noise points of oracle bone rubbings image,and the bilateral filtering method is used to collect the neighborhood information of the pixels in the spatial domain and the value domain,so as to filter out the noise of the image.According to the different noise,the standard parameters of bilateral filtering space and brightness are adjusted to keep the edge information under the filtering noise.The filtering performance is validated by subjective visual effect and objective quality evaluation.The results show that the proposed method can reduce the noise of oracle rubbings image while preserving the details of image edges.At the same noise level,the peak signal-to-noise ratio and the structural similarity of the method after filtering are higher than those of the other two methods,and the denoising result of the three-dimensional image is much better.It is clear that the proposed method can preserve the details and edges of the original image,and has a good denoising effect.
作者
王旖旎
WNG Yi-qi(Chongqing Business Vocational College?Chongqing 401331, China)
出处
《菏泽学院学报》
2019年第5期37-41,共5页
Journal of Heze University
基金
2018年度重庆市社会科学规划项目(2018PY22)
重庆商务职业学院2018年度校级重点项目(2018XJKTZD06)
关键词
极值检测
甲骨拓片
图像
双边滤波
extremum detection
oracle rubbings
image
bilateral filtering
作者简介
王旖旎(1981-),女,重庆人,副教授,硕士,研究方向:智能计算,数据挖掘,软件技术.
