基于自适应插值法的单幅图像边缘保持仿真  

Simulation of Single Image Edge Preserving Based on Adaptive Interpolation

作　　者：刘磊[1] 牟飞燕[1] LIU Lei;MOU Fei-yan(Chengdu College,University of Electronic Science and Technology of Sichuan,Chengdu Sichuan 611731,China)

机构地区：[1]电子科技大学成都学院,四川成都611731

出　　处：《计算机仿真》2023年第1期267-271,共5页Computer Simulation

摘　　要：针对单幅图像边缘信息不易保持的问题,从自适应阈值及插值处理两个角度出发,提出基于自适应插值法的单幅图像边缘保持方法。采用小波图像去噪方法预处理图像,降低图像噪声,并改进硬软阈值函数,精准估算小波变换时的小波系数,提高图像去噪效果;通过直方图平衡算法增强去噪后图像的低频子带,提高图像间的对比度;利用Canny自适应阈值边缘检测方法,将增强后图像直方图的子图像分割为边缘区间和平坦区间,采用众数法和邻近法判定插值点所在区间后,分别利用非线性或双线性插值处理区间,完成单幅图像边缘保持。仿真结果证明,所提方法的单幅图像边缘保持效果最佳,图像质感好。In this paper, a single image edge preserving method based on adaptive interpolation is reported to solve the preservation of single image edge information. Firstly, wavelet image denoising method was applied to preprocess the image, reducing the image noise and improving the hard and soft threshold function. Then, in order to improve the effect of image denoising, the wavelet coefficients in wavelet transform were estimated accurately. Secondly, histogram balance algorithm was introduced to enhance the low-frequency sub-band of denoised images for improving the contrast between images. Then, Canny adaptive threshold edge detection method was used to segment the sub-image of the enhanced image histogram into edge interval and flat interval respectively. Mode method and proximity method were used to determine the interval of interpolation points. Nonlinear or bilinear interpolation was used to process the interval. Eventually, the edge preservation of a single image was achieved. The simulation results show that this method has excellent edge preserving effect and good image texture.

关 键 词：自适应插值法 单幅图像 边缘保持 阈值 低频子带 

分 类 号：TP912[自动化与计算机技术]