huxw_magus的博客

1、介绍2、代码3、结果

1、介绍2、代码import cv2import numpy as npimport matplotlib.pyplot as plt# Grayscaledef BGR2GRAY(img): # Grayscale gray = 0.2126 * img[..., 2] + 0.7152 * img[..., 1] + 0.0722 * img[..., 0] return gray# Bi-Linear interpolationdef bl_interpolate(img,

1、介绍2、代码import cv2import numpy as npimport matplotlib.pyplot as plt# Grayscaledef BGR2GRAY(img): # Grayscale gray = 0.2126 * img[..., 2] + 0.7152 * img[..., 1] + 0.0722 * img[..., 0] return gray# Bi-Linear interpolationdef bl_interpolate(img,

1、介绍2、代码import cv2import numpy as npimport matplotlib.pyplot as plt# Grayscaledef BGR2GRAY(img): # Grayscale gray = 0.2126 * img[..., 2] + 0.7152 * img[..., 1] + 0.0722 * img[..., 0] return gray# Bi-Linear interpolationdef bl_interpolate(img,

1、介绍2、代码import cv2import numpy as npimport matplotlib.pyplot as plt# BGR -> HSVdef BGR2HSV(_img): img = _img.copy() / 255. hsv = np.zeros_like(img, dtype=np.float32) # get max and min max_v = np.max(img, axis=2).copy() min_v = np.min(img,

1、介绍2、代码import cv2import numpy as npimport matplotlib.pyplot as plt# make maskdef get_mask(hsv): mask = np.zeros_like(hsv[..., 0]) mask[np.logical_and((hsv[..., 0] > 180), (hsv[..., 0] < 260))] = 1 return mask# maskingdef m

1、介绍2、代码import cv2import numpy as npimport matplotlib.pyplot as pltdef get_mask(hsv): mask = np.zeros_like(hsv[..., 0]) mask[np.logical_and((hsv[..., 0] > 180), (hsv[..., 0] < 260))] = 255 return maskimg = cv2.imread('imori.j

1、介绍2、代码import cv2import numpy as npimport matplotlib.pyplot as plt# get HOGdef HOG(img): # Grayscale def BGR2GRAY(img): gray = 0.2126 * img[..., 2] + 0.7152 * img[..., 1] + 0.0722 * img[..., 0] return gray # Magnitude

1、介绍2、代码import cv2import numpy as npimport matplotlib.pyplot as pltdef HOG_step(img): # Grayscale def BGR2GRAY(img): gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) return gray # Magnitude and gradient def get_gradXY(g

1、介绍2、代码import cv2import numpy as npimport matplotlib.pyplot as plt# get HOG step2def HOG_step2(img): # Grayscale def BGR2GRAY(img): gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) return gray # Magnitude and gradient

1、介绍2、代码import cv2import numpy as npimport matplotlib.pyplot as plt# get HOG step1def HOG_step1(img): # Grayscale def BGR2GRAY(img): gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) return gray # Magnitude and gradient

1、介绍2、代码import cv2import numpy as npimport matplotlib.pyplot as plt# Zhang Suen thining algorythmdef Zhang_Suen_thining(img): # get shape H, W, C = img.shape # prepare out image out = np.zeros((H, W), dtype=np.int) out[img[...

1、介绍2、代码import cv2import numpy as npimport matplotlib.pyplot as plt# hilditch thiningdef hilditch(img): # get shape H, W, C = img.shape # prepare out image out = np.zeros((H, W), dtype=np.int) out[img[..., 0] > 0] = 1

1、介绍2、代码import cv2import numpy as npimport matplotlib.pyplot as plt# thining algorythmdef thining(img): # get shape H, W, C = img.shape # prepare out image out = np.zeros((H, W), dtype=np.int) out[img[..., 0] > 0] = 1

1、介绍2、代码import cv2import numpy as npimport matplotlib.pyplot as plt# connect 8def connect_8(img): # get shape H, W, C = img.shape # prepare temporary _tmp = np.zeros((H, W), dtype=np.int) # get binarize _tmp[img[..., 0] &g

1、介绍2、代码import cv2import numpy as npimport matplotlib.pyplot as pltdef connect_4(img): # get shape H, W, C = img.shape # prepare temporary image tmp = np.zeros((H, W), dtype=np.int) # binarize tmp[img[..., 0] > 0] = 1

1、介绍2、代码import cv2import numpy as npimport matplotlib.pyplot as pltimg = cv2.imread('imori.jpg').astype(np.float32)img_gray = cv2.imread('thorino.jpg').astype(np.float32)a = 0.6out = img * a + img_gray * (1 - a)out = out.astype(np.uint8)cv2.

1、介绍2、代码import cv2import numpy as npimg = cv2.imread('imori.jpg').astype(np.float32)H, W, C = img.shapemi = np.mean(img)temp = cv2.imread('imori_part.jpg').astype(np.float32)Ht, Wt, Ct = temp.shapemt = np.mean(temp)i, j = -1, -1v = -1for y

1、介绍2、代码import cv2import numpy as npimg = cv2.imread('imori.jpg').astype(np.float32)H, W, C = img.shapetemp = cv2.imread('imori_part.jpg').astype(np.float32)Ht, Wt, Ct = temp.shapei, j = -1, -1v = -1for y in range(H - Ht): for x in range(

1、介绍2、代码import cv2import numpy as npimg = cv2.imread('imori.jpg').astype(np.float32)H, W, C = img.shapetemp = cv2.imread('imori_part.jpg').astype(np.float32)Ht, Wt, Ct = temp.shapei, j = -1, -1v = 255 * H * W * Cfor y in range(H - Ht): fo

1、介绍2、代码import cv2import numpy as npimg = cv2.imread('imori.jpg').astype(np.float32)H, W, C = img.shapetemp = cv2.imread('imori_part.jpg').astype(np.float32)Ht, Wt, Ct = temp.shapei, j = -1, -1v = 255 * H * W * Cfor y in range(H - Ht): fo

1、介绍礼帽 = 原始输入-开运算结果黑帽 = 闭运算-原始输入tophat = cv2.morphologyEx(img, cv2.MORPH_TOPHAT, kernel)balckhat = cv2.morphologyEx(img, cv2.MORPH_BLACKHAT, kernel)2、代码import cv2import numpy as npimg = cv2.imread('lena.jpg', 0)kernel = np.ones((3, 3), np.uint8)

1、介绍梯度=膨胀-腐蚀gradient = cv2.morphologyEx(img, cv2.MORPH_GRADIENT, kernel)2、代码import cv2import numpy as np# 形态学梯度运算=膨胀-腐蚀img = cv2.imread('lena.jpg', 0)kernel = np.ones((5, 5), np.uint8)dilate = cv2.dilate(img, kernel, iterations=5)erosion = cv

1、介绍2、代码import cv2import numpy as np# 开运算img = cv2.imread('lena.jpg', 0)kernel = np.ones((3, 3), np.uint8)opening=cv2.morphologyEx(img,cv2.MORPH_OPEN,kernel)res = np.hstack((img, opening))cv2.imshow('res', res)cv2.waitKey(0)cv2.destroyAllW

1、介绍与腐蚀相反，与卷积核对应的原图像的像素值中只要有一个是1，中心元素的像素值就是1。所以这个操作会增加图像中的白色区域（前景）。一般在去噪声时先用腐蚀再用膨胀。因为腐蚀在去掉白噪声的同时，也会使前景对象变小。所以我们再对他进行膨胀。这时噪声已经被去除了，不会再回来了，但是前景还在并会增加。膨胀也可以用来连接两个分开的物体。2、代码import cv2import numpy as npimg = cv2.imread('lena.jpg')kernel = np.ones((3,

1、介绍-图像的腐蚀：就像土壤侵蚀一样，这个操作会把前景物体的边界腐蚀掉（但是前景仍然是白色）。这是怎么做到的呢？卷积核沿着图像滑动，如果与卷积核对应的原图像的所有像素值都是1，那么中心元素就保持原来的像素值，否则就变为零。这回产生什么影响呢？根据卷积核的大小靠近前景的所有像素都会被腐蚀掉（变为0），所以前景物体会变小，整幅图像的白色区域会减少。这对于去除白噪声很有用，也可以用来断开两个连在一块的物体等。这里我们有一个例子，使用一个5x5的卷积核，其中所有的值都是以。让我们看看他是如何工作的：

import numpy as npimport cv2"""cv2.HoughLines() dst: 输出图像. 它应该是个灰度图 (但事实上是个二值化图) lines: 储存着检测到的直线的参数对 (r,\theta) 的容器 rho : 参数极径 r 以像素值为单位的分辨率. 我们使用 1 像素. theta: 参数极角 \theta 以弧度为单位的分辨率. 我们使用 1度 (即CV_PI/180) threshold: 设置阈值： 一条直线所需最少的的曲线交点 sr

import numpy as npimport cv2img=cv2.imread('lena.jpg',0)v1=cv2.Canny(img,80,150)v2=cv2.Canny(img,50,100)res=np.hstack((v1,v2))cv2.imshow('res',res)cv2.waitKey(0)cv2.destroyAllWindows()

1、介绍2、代码–>好理解版本import cv2import numpy as npimport matplotlib.pyplot as plt# grayimg = cv2.imread("lena.jpg", 0).astype(np.float32)# 进行傅里叶变化dft = cv2.dft(img, flags=cv2.DFT_COMPLEX_OUTPUT)# dft=np.fft.fft2(gray)# 将图像中的低频部分移动到图像的中心dft_shif

1、介绍2、代码–>非常好理解的代码import cv2import numpy as npimport matplotlib.pyplot as plt# grayimg = cv2.imread("lena.jpg",0).astype(np.float32)# 进行傅里叶变化dft = cv2.dft(img, flags=cv2.DFT_COMPLEX_OUTPUT)# dft=np.fft.fft2(gray)# 将图像中的低频部分移动到图像的中心dft_sh

import cv2import numpy as npimport matplotlib.pyplot as plt# DFT hyper-parametersK, L = 128, 128channel = 3# DFTdef dft(img): H, W, _ = img.shape # Prepare DFT coefficient G = np.zeros((L, K, channel), dtype=np.complex) # prepare processe.

1、介绍2、代码import cv2import numpy as npimport matplotlib.pyplot as plt![# Affine](https://img-blog.csdnimg.cn/20200525155930993.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2h1eHdfbWFndXM=,size_

1、介绍2、代码import cv2import numpy as npimport matplotlib.pyplot as plt# Affinedef affine(img2, a, b, c, d, tx, ty): H, W, C = img2.shape # temporary image img = np.zeros((H + 2, W + 2, C), dtype=np.float32) img[1:H + 1, 1:W + 1] = im

1、介绍2、代码import cv2import numpy as npimport matplotlib.pyplot as plt# Affinedef affine(img2, a, b, c, d, tx, ty): H, W, C = img2.shape # temporary image img = np.zeros((H + 2, W + 2, C), dtype=np.float32) img[1:H + 1, 1:W + 1] = im

1、介绍2、代码import cv2import numpy as npimport matplotlib.pyplot as plt# Affinedef affine(img2, a, b, c, d, tx, ty): H, W, C = img2.shape # temporary image img = np.zeros((H + 2, W + 2, C), dtype=np.float32) img[1:H + 1, 1:W + 1] = i

1、问题2、代码import cv2import numpy as npimport matplotlib.pyplot as plt# Bi-cubic interpolationdef bc_interpolate(img, ax=1., ay=1.): H, W, C = img.shape aH = int(ay * H) aW = int(ax * W) # get position of resized image y = np.ara

1、介绍2、代码import cv2import numpy as npimport matplotlib.pyplot as plt# Bi-Linear interpolationdef bl_interpolate(img, ax=1., ay=1.): H, W, C = img.shape aH = int(ay * H) aW = int(ax * W) # get position of resized image y = np.ar

1、介绍2、代码import cv2import numpy as npimport matplotlib.pyplot as pltdef nn_interpolate(img, ax=1, ay=1): H, W, C = img.shape aH = int(ay * H) aW = int(ax * W) y = np.arange(aH).repeat(aW).reshape(aW, -1) # 使得y为aW*aH的一个矩阵（初始化） x

1、题目介绍2、代码import cv2import numpy as npimport matplotlib.pyplot as pltdef gamma_correction(img, c=1, g=2.2): out=img.copy() out/=255. # 很重要，先进行归一化，限定在【0，1]范围内。 out=(1/c)*out**(1/g) # 【0，1】内进行伽马变换 out*=255 # 之后变回来 out=out.asty

1、问题介绍2、代码import cv2import numpy as npimport matplotlib.pyplot as pltdef hist_equal(img, z_max=255): H, W, C = img.shape S = H * W * C out = img.copy() sum_h = 0. for i in range(1, 255): ind = np.where(img == i)