1 图像增强

1.1 含义

突出图像细节，让图像更加清晰。

1.2 方法

直方图均衡

1.2.1 直方图均衡

直方图均衡

import cv2
import numpy as np
import matplotlib.pyplot as pltdef histequal(img_gray):# 1 计算各个像素的频数、累积频数、归一化h,w = img_gray.shapecum_freq = np.array([(img_gray==i).sum() for i in range(255)]).cumsum()cum_freq = (cum_freq/cum_freq[-1]*255).astype(np.uint8)tmp = img_gray.copy()for i in range(255):tmp[img_gray == i] = cum_freq[i]return tmpimg = cv2.imread('opencv/features/cat0.jpg', 0)
out = histequal(img)
plt.subplot(121)
plt.title('org')
plt.imshow( img,cmap='gray')
plt.subplot(122)
plt.title('histequal')
plt.imshow( out,cmap='gray')
plt.show()

1.2.2 gamma变换

import cv2
import numpy as np
import matplotlib.pyplot as pltdef gamma(img,c=2,r=2):return np.array(c*img**r,dtype=np.uint8).clip(0,255)img = cv2.imread('/Users/liushuang/Desktop/LearnGit/项目实战/鱼苗检测/yolov5-master/opencv/features/cat.jpg')
out = gamma(img)
plt.subplot(121)
plt.title('org')
plt.imshow( img,cmap='gray')
plt.subplot(122)
plt.title('gamma')
plt.imshow( out,cmap='gray')
plt.show()

2 除噪

2.1 含义

除去图片上的噪声

2.2 方法

空间滤波法（均值滤波、高斯滤波、中值滤波、双边滤波），变换滤波（傅立叶，小波变换）、形态学等

2.2.1 高斯滤波

高斯滤波
高斯滤波适合处理呈正态分布的噪声。滤波器的特点是权值成正态分布。方差越大，滤波效果越明显；反之，效果越差。

import cv2
import numpy as np
import matplotlib.pyplot as pltdef guassian_filter(img, k_size=3, sigma=2):# 获取通道if len(img.shape) == 3:h, w, c = img.shapeelse:img = np.expand_dims(img, axis=-1)h, w, c = img.shape# img padiingpad = (k_size - 1) // 2out_put = np.zeros((h + pad * 2, w + pad * 2,3), dtype=np.float32)out_put[pad:pad + h, pad:pad + w] = img.copy().astype(np.float32)# generate kernelk = np.zeros((k_size, k_size), dtype = np.float32)for i in range(-pad, k_size - pad):for j in range(-pad, k_size - pad):k[j + pad, i + pad] = np.exp(-(i ** 2 + j ** 2) / (2 * sigma ** 2))k /= (2 * np.pi * sigma ** 2)k /= k.sum()tmp = out_put.copy()# Gaussian filterfor i in range(h):for j in range(w):for cc in range(c):out_put[pad + i, pad + j, cc] = np.sum(k * tmp[i:i + k_size, j:j + k_size, cc])out_put = np.clip(out_put, 0, 255)return out_put[pad:pad + h, pad:pad + w].astype(np.uint8)#
img = cv2.imread('opencv/features/dogGauss.jpeg')
out = guassian_filter(img, k_size=3, sigma=2)
plt.subplot(121)
plt.title('org')
plt.imshow( img[...,::-1])
plt.subplot(122)
plt.title('out')
plt.imshow( out[...,::-1])
plt.show()# sigma = 1 ,高斯核
'''
array([[0.07511362, 0.12384141, 0.07511362],[0.12384141, 0.20417996, 0.12384141],[0.07511362, 0.12384141, 0.07511362]], dtype=float32)# sigma = 3
array([[0.10699731, 0.11310981, 0.10699731],[0.11310981, 0.11957153, 0.11310981],[0.10699731, 0.11310981, 0.10699731]], dtype=float32)
'''

2.2.2 均值滤波

### 2.2.2 mean+filter
import cv2
import numpy as np
import matplotlib.pyplot as pltdef mean_filter(img, k_size=3):# shapeif len(img.shape) != 3:img = img[..., None]h, w, c = img.shape# 1 kernelk = np.ones((k_size, k_size), np.float32) / (k_size * k_size)# 2 out_Putpad = (k_size - 1) // 2out_put = np.zeros((h + 2*pad, w + 2*pad, c), np.float32)out_put[pad:pad + h, pad:pad + w] = img.copy().astype(np.float32)# 3 filtetmp = out_put.copy()for i in range(h):for j in range(w):for cc in range(c):out_put[pad + i:, pad + j, cc] = (tmp[i:i + k_size, j:j + k_size, cc] * k).sum()out_put = np.clip(out_put, 0, 255)return out_put[pad:pad + h, pad:pad + w].astype(np.uint8)# filteimg = cv2.imread('opencv/features/dogGauss.jpeg')
out = mean_filter(img, k_size=3)
plt.subplot(121)
plt.title('org')
plt.imshow(img[..., ::-1])
plt.subplot(122)
plt.title('out_mean_filter')
plt.imshow(out[..., ::-1])
plt.show()

2.2.3 中值滤波

取窗口的中位数作为中心点的值，如果效果不好，可以增大核的尺寸，或者多循环几次。

import cv2
import numpy as np
import matplotlib.pyplot as pltdef median_filter(img, k_size=10):# shapeif len(img.shape) != 3:img = img[..., None]h, w, c = img.shape# 2 out_Putpad = (k_size - 1) // 2out_put = np.ones((h + 2 * pad, w + 2 * pad, c), np.float32) * (-1)out_put[pad:pad + h, pad:pad + w] = img.copy().astype(np.float32)# 3 filtetmp = out_put.copy()for i in range(h):for j in range(w):for cc in range(c):t = tmp[i:i + k_size, j:j + k_size, cc]out_put[pad + i:, pad + j, cc] = np.median(t[t > 0])return out_put[pad:pad + h, pad:pad + w].astype(np.uint8)# filteimg = cv2.imread('opencv/features/letteropen.png')
out = median_filter(img, k_size=20)
plt.subplot(121)
plt.title('org')
plt.imshow(img[..., ::-1])
plt.subplot(122)
plt.title('median_filter')
plt.imshow(out[..., ::-1])
plt.show()

3 边缘检测

3.1 canny

canny 边缘检测流程

1. 平滑处理
2. 梯度检测
3. 非极大值抑制
4. 滞后阈值处理

import cv2 as cv
import numpy as np
import matplotlib.pyplot as pltdef canny(img):# 1. 平滑img_blur = cv.GaussianBlur(img, (5, 5), 2)# 2. 梯度gradx = cv.Sobel(img_blur, cv.CV_64F, 1, 0)  # xgrady = cv.Sobel(img_blur, cv.CV_64F, 0, 1)  # yR = np.abs(gradx) + np.abs(grady)T = np.arctan(grady / (gradx + 1e-3))# 3. 非极大值抑制，细化边缘h, w = R.shapeimg_thin = np.zeros_like(R)for i in range(1, h - 1):for j in range(1, w - 1):theta = T[i, j]if -np.pi / 8 <= theta < np.pi / 8:        #  (-22,22)if R[i, j] == max([R[i, j], R[i, j - 1], R[i, j + 1]]):            #  上下img_thin[i, j] = R[i, j]elif -3 * np.pi / 8 <= theta < -np.pi / 8:  #  (-66,-22)if R[i, j] == max([R[i, j], R[i - 1, j + 1], R[i + 1, j - 1]]):  #  斜线img_thin[i, j] = R[i, j]elif np.pi / 8 <= theta < 3 * np.pi / 8:    #  (22,66)if R[i, j] == max([R[i, j], R[i - 1, j - 1], R[i + 1, j + 1]]):  # 反斜线img_thin[i, j] = R[i, j]else:                                       #  (66,110)if R[i, j] == max([R[i, j], R[i - 1, j], R[i + 1, j]]):            # 左右img_thin[i, j] = R[i, j]# 4 双阈值抑制th1 = 5th2 = 30maxv = 255img_edge = np.zeros_like(img_thin)h, w = img_thin.shapefor i in range(1, h - 1):for j in range(1, w - 1):if img_thin[i, j] >= th2:img_edge[i, j] = maxvelif img_thin[i, j] > th1:around = img_thin[i - 1:i + 2, j - 1:j + 2]if around.max() >= th2:img_edge[i, j] = maxvreturn img_edgeimg = cv2.imread('opencv/features/letteropen.png', 0)
out = canny(img)
plt.subplot(121)
plt.title('org')
plt.imshow( img,cmap='gray')
plt.subplot(122)
plt.title('canny')
plt.imshow( out,cmap='gray')
plt.show()

4 HOG特征提取

4.1 含义

通过提取图像局部区域梯度直方图构成特征，进而获取整个图像的特征。HOG对几何和光学形变都能保持不变形。通过局部归一化，忽略细节的变化，提取共哦那个特性。

4.2 流程

img --> cells,blocks --> 计算每个cell的梯度直方图

4.3 案例

6 两个比赛

6.1 三个功能整合

6.2 目标检测

6.3 yolov5代码详解