打不开wordpress,优化网址,科技网站建设 长沙,扬州做公司网站的公司文章目录1. 原理概述2. 实验环节2.1 验证与opencv 库函数的结果一致2.2 与 双边滤波比较2.3 引导滤波应用#xff0c;fathering2.3 引导滤波应用#xff0c;图像增强2.4 灰度图引导#xff0c;和各自通道引导的效果差异2.5 不同参数设置影响3. 参考引导滤波1. 原理概述
引导…
文章目录1. 原理概述2. 实验环节2.1 验证与opencv 库函数的结果一致2.2 与 双边滤波比较2.3 引导滤波应用fathering2.3 引导滤波应用图像增强2.4 灰度图引导和各自通道引导的效果差异2.5 不同参数设置影响3. 参考引导滤波1. 原理概述
引导滤波是三大保边平滑算法之一。 原理介绍参考 图像处理基础一引导滤波
2. 实验环节
2.1 验证与opencv 库函数的结果一致
引导图是单通道时的函数guided_filter(I,p,win_size,eps)引导图时三通道时的函数multi_dim_guide_filter(I, p, r, eps)I, p的输入如果归一化 0-1之间则eps设置为小于1的数比如0.2 如果没有归一化则 eps 需要乘以 (255 * 255)I, p应该是浮点数cv2.ximgproc.guidedFilter 的输入参数r是 window_size // 2
实验图像
guided_filter 和multi_dim_guide_filter 代码 import cv2
import numpy as np
from matplotlib import pyplot as pltdef guided_filter(I,p,win_size,eps):% - guidance image: I (should be a gray-scale/single channel image)% - filtering input image: p (should be a gray-scale/single channel image)% - local window radius: r% - regularization parameter: epsmean_I cv2.blur(I,(win_size,win_size))mean_p cv2.blur(p,(win_size,win_size))mean_II cv2.blur(I*I,(win_size,win_size))mean_Ip cv2.blur(I*p,(win_size,win_size))var_I mean_II - mean_I*mean_Icov_Ip mean_Ip - mean_I*mean_p#print(np.allclose(var_I, cov_Ip))a cov_Ip/(var_Ieps)b mean_p-a*mean_Imean_a cv2.blur(a,(win_size,win_size))mean_b cv2.blur(b,(win_size,win_size))q mean_a*I mean_b#print(mean_II.dtype, cov_Ip.dtype, b.dtype, mean_a.dtype, I.dtype, q.dtype)return qdef multi_dim_guide_filter(I, p, r, eps):I 是三通道p 是单通道或者多通道图像out np.zeros_like(p)if len(p.shape) 2:out multi_dim_guide_filter_single(I, p, r, eps)else:for c in range(p.shape[2]):out[..., c] multi_dim_guide_filter_single(I, p[..., c], r, eps)return outdef multi_dim_guide_filter_single(I, p, r, eps):I : 导向图多个通道 H, W, Cp : 单个通道 H, W, 1radius : 均值滤波核长度eps:# if len(p.shape) 2:# p p[..., None]r (r, r)mean_I_r cv2.blur(I[..., 0], r);mean_I_g cv2.blur(I[..., 1], r);mean_I_b cv2.blur(I[..., 2], r);# variance of I in each local patch: the matrix Sigma in Eqn(14).# Note the variance in each local patch is a 3x3 symmetric matrix:# rr, rg, rb# Sigma rg, gg, gb# rb, gb, bbvar_I_rr cv2.blur(I[..., 0] * (I[..., 0]), r) - mean_I_r * (mean_I_r) epsvar_I_rg cv2.blur(I[..., 0] * (I[..., 1]), r) - mean_I_r * (mean_I_g)var_I_rb cv2.blur(I[..., 0] * (I[..., 2]), r) - mean_I_r * (mean_I_b)var_I_gg cv2.blur(I[..., 1] * (I[..., 1]), r) - mean_I_g * (mean_I_g) epsvar_I_gb cv2.blur(I[..., 1] * (I[..., 2]), r) - mean_I_g * (mean_I_b)var_I_bb cv2.blur(I[..., 2] * (I[..., 2]), r) - mean_I_b * (mean_I_b) eps# Inverse of Sigma eps * Iinvrr var_I_gg * (var_I_bb) - var_I_gb * (var_I_gb)invrg var_I_gb * (var_I_rb) - var_I_rg * (var_I_bb)invrb var_I_rg * (var_I_gb) - var_I_gg * (var_I_rb)invgg var_I_rr * (var_I_bb) - var_I_rb * (var_I_rb)invgb var_I_rb * (var_I_rg) - var_I_rr * (var_I_gb)invbb var_I_rr * (var_I_gg) - var_I_rg * (var_I_rg)covDet invrr * (var_I_rr) invrg * (var_I_rg) invrb * (var_I_rb)invrr / covDetinvrg / covDetinvrb / covDetinvgg / covDetinvgb / covDetinvbb / covDet# process pmean_p cv2.blur(p, r)mean_Ip_r cv2.blur(I[..., 0] * (p), r)mean_Ip_g cv2.blur(I[..., 1] * (p), r)mean_Ip_b cv2.blur(I[..., 2] * (p), r)# covariance of(I, p) in each local patch.cov_Ip_r mean_Ip_r - mean_I_r * (mean_p)cov_Ip_g mean_Ip_g - mean_I_g * (mean_p)cov_Ip_b mean_Ip_b - mean_I_b * (mean_p)a_r invrr * (cov_Ip_r) invrg * (cov_Ip_g) invrb * (cov_Ip_b)a_g invrg * (cov_Ip_r) invgg * (cov_Ip_g) invgb * (cov_Ip_b)a_b invrb * (cov_Ip_r) invgb * (cov_Ip_g) invbb * (cov_Ip_b)b mean_p - a_r * (mean_I_r) - a_g * (mean_I_g) - a_b * (mean_I_b)return (cv2.blur(a_r, r) * (I[..., 0]) cv2.blur(a_g, r) * (I[..., 1]) cv2.blur(a_b, r) * (I[..., 2]) cv2.blur(b, r))实验代码
def compare_1_3channel(im, r, eps):分通道进行和一起进行结果完全一致out1 guided_filter(im, im, r, eps)out2 np.zeros_like(out1)out2[..., 0] guided_filter(im[..., 0], im[..., 0], r, eps)out2[..., 1] guided_filter(im[..., 1], im[..., 1], r, eps)out2[..., 2] guided_filter(im[..., 2], im[..., 2], r, eps)return out1, out2if __name__ __main__:file rD:\code\denoise\denoise_video\guide_filter_image\dd.pngkernel_size 7r kernel_size // 2eps 0.002input cv2.imread(file, 1)out1, out2 compare_1_3channel(input, kernel_size, (eps * 255 * 255))cv2.imwrite(file[:-4] out1.png, out1) # 这个结果错误因为uint8 * uint8仍然赋给了uint8# out2.png, out3.png, out4.png 结果基本一致input input.astype(np.float32) # 要转换为float类型out1, out2 compare_1_3channel(input, kernel_size, (eps * 255 * 255))cv2.imwrite(file[:-4] out2.png, out2)out1[..., 0] cv2.ximgproc.guidedFilter(input[..., 0], input[..., 0], r, (eps * 255 * 255))out1[..., 1] cv2.ximgproc.guidedFilter(input[..., 1][..., None], input[..., 1][..., None], 3, (eps * 255 * 255))out1[..., 2] cv2.ximgproc.guidedFilter(input[..., 2][..., None], input[..., 2][..., None], 3, (eps * 255 * 255))print(tt : , out1.min(), out1.max())out4 np.clip(out1 * 1, 0, 255).astype(np.uint8)cv2.imwrite(file[:-4] out4.png, out4)input input / 255input input.astype(np.float32)out1, out2 compare_1_3channel(input, kernel_size, (eps)) # 注意0-1 和 0-255 在eps的差异。out3 np.clip(out1 * 255, 0, 255).astype(np.uint8)cv2.imwrite(file[:-4] out3.png, out3)# out5.png 和 out6.png结果一致利用灰度图作为导向图 注意半径和kernel_size的区别。guide cv2.cvtColor(input,cv2.COLOR_BGR2GRAY)out1 cv2.ximgproc.guidedFilter(guide, input, r, (eps))out5 np.clip(out1 * 255, 0, 255).astype(np.uint8)cv2.imwrite(file[:-4] out5.png, out5)out2[..., 0] guided_filter(guide, input[..., 0], kernel_size, eps)out2[..., 1] guided_filter(guide, input[..., 1], kernel_size, eps)out2[..., 2] guided_filter(guide, input[..., 2], kernel_size, eps)out6 np.clip(out2 * 255, 0, 255).astype(np.uint8)cv2.imwrite(file[:-4] out6.png, out6)plt.figure(figsize(9, 14))plt.subplot(231), plt.axis(off), plt.title(guidedFilter error)plt.imshow(cv2.cvtColor(out1, cv2.COLOR_BGR2RGB))plt.subplot(232), plt.axis(off), plt.title(cv2.guidedFilter)plt.imshow(cv2.cvtColor(out2, cv2.COLOR_BGR2RGB))plt.subplot(233), plt.axis(off), plt.title(cv2.guidedFilter)plt.imshow(cv2.cvtColor(out3, cv2.COLOR_BGR2RGB))plt.subplot(234), plt.axis(off), plt.title(cv2.guidedFilter)plt.imshow(cv2.cvtColor(out4, cv2.COLOR_BGR2RGB))plt.subplot(235), plt.axis(off), plt.title(cv2.guidedFilter)plt.imshow(cv2.cvtColor(out5, cv2.COLOR_BGR2RGB))plt.subplot(236), plt.axis(off), plt.title(cv2.guidedFilter)plt.imshow(cv2.cvtColor(out6, cv2.COLOR_BGR2RGB))plt.tight_layout()plt.show()输出结果
2.2 与 双边滤波比较
个人感觉引导滤波更好 完整代码如下
if __name____main__:file rD:\code\denoise\denoise_video\guide_filter_image\dd.pngkernel_size 7r kernel_size // 2eps1 0.004/2eps2 0.002/4input cv2.imread(file, 1)input input.astype(np.float32) # 要转换为float类型out1 guided_filter(input, input, kernel_size, eps1*255*255)out2 cv2.bilateralFilter(input, kernel_size, eps2*255*255, eps2*255*255)out1 np.clip(out1, 0, 255).astype(np.uint8)out2 np.clip(out2, 0, 255).astype(np.uint8)cv2.imwrite(file[:-4] guide.png, out1)cv2.imwrite(file[:-4] bi.png, out2)cv2.imshow(guide, out1)cv2.imshow(bi, out2)cv2.waitKey(0)2.3 引导滤波应用fathering
实验图像
实验code: 导向滤波的应用: fatheringdef run_fathering():file_I rD:\code\denoise\denoise_video\guide_filter_image\apply\c.pngfile_mask rD:\code\denoise\denoise_video\guide_filter_image\apply\d.pngI cv2.imread(file_I, 1)I_gray cv2.cvtColor(I, cv2.COLOR_BGR2GRAY)input cv2.imread(file_mask, 0)kernel_size 20r kernel_size // 2eps1 0.000008 / 2I I.astype(np.float32)I_gray I_gray.astype(np.float32)input input.astype(np.float32) # 要转换为float类型out1 cv2.ximgproc.guidedFilter(I, input, r, (eps1 * 255 * 255))out1 np.clip(out1, 0, 255).astype(np.uint8)cv2.imwrite(file_mask[:-4] guide.png, out1)out2 cv2.ximgproc.guidedFilter(I_gray, input, r, (eps1 * 255 * 255))out2 np.clip(out2, 0, 255).astype(np.uint8)cv2.imwrite(file_mask[:-4] guide2.png, out2)out3 guided_filter(I_gray, input, kernel_size, eps1 * 255 * 255)out3 np.clip(out3, 0, 255).astype(np.uint8)cv2.imwrite(file_mask[:-4] guide3.png, out3)print(I.shape, input.shape)out4 multi_dim_guide_filter(I, input, kernel_size, eps1 * 255 * 255)out4 np.clip(out4, 0, 255).astype(np.uint8)cv2.imwrite(file_mask[:-4] guide4.png, out4)out1 是彩色引导图opencv库 out2 是灰度引导图opencv库 out3 是灰度引导图 out4 是彩色引导图
结果 out1和out4 接近一致效果好。 out2和out3一致效果存在问题 2.3 引导滤波应用图像增强
图片
引导滤波结果稍好一些 实验code:
if __name__ __main__:file rD:\code\denoise\denoise_video\guide_filter_image\apply\e.pngI cv2.imread(file, 1)I I.astype(np.float32)p Ikernel_size 20r kernel_size // 2eps1 0.008 / 2eps2 0.002 / 6out0 cv2.bilateralFilter(p, kernel_size, eps2 * 255 * 255, eps2 * 255 * 255) # 双边滤波out1 multi_dim_guide_filter(I, p, kernel_size, (eps1 * 255 * 255)) # 多通道guideout2 guided_filter(I, p, kernel_size, (eps1 * 255 * 255)) # 单通道各自guideout3 cv2.ximgproc.guidedFilter(I, p, r, (eps1 * 255 * 255)) # 多通道guideout4 (I - out0) * 2 out0out5 (I - out1) * 2 out1out6 (I - out2) * 2 out2out7 (I - out3) * 2 out3out0 np.clip(out0, 0, 255).astype(np.uint8)out1 np.clip(out1, 0, 255).astype(np.uint8)out2 np.clip(out2, 0, 255).astype(np.uint8)out3 np.clip(out3, 0, 255).astype(np.uint8) # out3 应该和 out1结果一致out4 np.clip(out4, 0, 255).astype(np.uint8)out5 np.clip(out5, 0, 255).astype(np.uint8)out6 np.clip(out6, 0, 255).astype(np.uint8) #out7 np.clip(out7, 0, 255).astype(np.uint8)cv2.imwrite(file[:-4] 0.png, out0)cv2.imwrite(file[:-4] 1.png, out1)cv2.imwrite(file[:-4] 2.png, out2)cv2.imwrite(file[:-4] 3.png, out3)cv2.imwrite(file[:-4] 4.png, out4)cv2.imwrite(file[:-4] 5.png, out5)cv2.imwrite(file[:-4] 6.png, out6)cv2.imwrite(file[:-4] 7.png, out7)2.4 灰度图引导和各自通道引导的效果差异
一致有个疑问
分别用r,g,b引导各自通道的效果利用灰度图引导各通道比1滤波强度更大利用彩色图引导
哪种效果更好呢 实际使用的时候利用彩色图引导要相对复杂计算量也更大。
def compare_1gray_3channel(im, r, eps):分通道进行和一起进行结果完全一致out1 guided_filter(im, im, r, eps)im_gray cv2.cvtColor(im, cv2.COLOR_RGB2GRAY)out2 np.zeros_like(out1)out2[..., 0] guided_filter(im_gray, im[..., 0], r, eps)out2[..., 1] guided_filter(im_gray, im[..., 1], r, eps)out2[..., 2] guided_filter(im_gray, im[..., 2], r, eps)return out1, out2def run_compare_gray_guide():file rD:\code\denoise\denoise_video\guide_filter_image\compare\dd.pngkernel_size 17r kernel_size // 2eps1 0.02 / 2input cv2.imread(file, 1)input input.astype(np.float32) # 要转换为float类型out1, out2 compare_1gray_3channel(input, r, (eps1 * 255 * 255))out1 np.clip(out1, 0, 255).astype(np.uint8)out2 np.clip(out2, 0, 255).astype(np.uint8)cv2.imwrite(file[:-4] 1.png, out1)cv2.imwrite(file[:-4] 2.png, out2)out3 cv2.ximgproc.guidedFilter(I, p, r, (eps1 * 255 * 255)) # 多通道out3 np.clip(out3, 0, 255).astype(np.uint8)cv2.imwrite(file[:-4] 3.png, out3)2.5 不同参数设置影响
def parameter_tuning():file rD:\code\denoise\denoise_video\guide_filter_image\paramter_tuning\dd.pngkernel_size 17r kernel_size // 2eps1 0.02 / 2input cv2.imread(file, 1)input input.astype(np.float32) # 要转换为float类型index 0for r in np.arange(3, 21, 4):for eps in np.arange(0.000001, 0.00001, 0.000001):eps1 eps * 255 * 255_, out2 compare_1gray_3channel(input, r, eps1)out2 np.clip(out2, 0, 255).astype(np.uint8)cv2.imwrite(file[:-4] {}.png.format(index), out2)index 1for eps in np.arange(0.2, 1, 0.1):eps1 eps * 255 * 255_, out2 compare_1gray_3channel(input, r, eps1)out2 np.clip(out2, 0, 255).astype(np.uint8)cv2.imwrite(file[:-4] {}.png.format(index), out2)index 13. 参考
[1]https://zhuanlan.zhihu.com/p/438206777 有详细解释 和 C相关代码仓库 [2]https://blog.csdn.net/huixingshao/article/details/42834939 高级图像去雾算法的快速实现, guide filter用于去雾解释的很清楚 [3]http://giantpandacv.com/academic/传统图像/一些有趣的图像算法/OpenCV图像处理专栏六 来自何凯明博士的暗通道去雾算法(CVPR 2009最佳论文)/去雾代码 [4]https://github.com/atilimcetin/guided-filter引导滤波Ccode
