opencv—常用函数学习_“干货“_9

import cv2
import numpy as np# 读取图像并转换为灰度图
image = cv2.imread('path_to_image.jpg')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)# 使用Canny边缘检测
edges = cv2.Canny(gray, 50, 150, apertureSize=3)# 使用HoughLines检测直线
lines = cv2.HoughLines(edges, 1, np.pi / 180, 200)# 绘制检测到的直线
if lines is not None:for rho, theta in lines[:, 0]:a = np.cos(theta)b = np.sin(theta)x0 = a * rhoy0 = b * rhox1 = int(x0 + 1000 * (-b))y1 = int(y0 + 1000 * (a))x2 = int(x0 - 1000 * (-b))y2 = int(y0 - 1000 * (a))cv2.line(image, (x1, y1), (x2, y2), (0, 0, 255), 2)cv2.imshow('Hough Lines', image)
cv2.waitKey(0)
cv2.destroyAllWindows()

# 使用HoughLinesP检测直线段
lines_p = cv2.HoughLinesP(edges, 1, np.pi / 180, 100, minLineLength=100, maxLineGap=10)# 绘制检测到的直线段
if lines_p is not None:for x1, y1, x2, y2 in lines_p[:, 0]:cv2.line(image, (x1, y1), (x2, y2), (0, 255, 0), 2)cv2.imshow('Hough Lines P', image)
cv2.waitKey(0)
cv2.destroyAllWindows()

# 使用HoughCircles检测圆
circles = cv2.HoughCircles(gray, cv2.HOUGH_GRADIENT, dp=1, minDist=20, param1=50, param2=30, minRadius=0, maxRadius=0)# 绘制检测到的圆
if circles is not None:circles = np.uint16(np.around(circles))for i in circles[0, :]:# 绘制圆的外圆cv2.circle(image, (i[0], i[1]), i[2], (255, 0, 0), 2)# 绘制圆心cv2.circle(image, (i[0], i[1]), 2, (0, 255, 0), 3)cv2.imshow('Hough Circles', image)
cv2.waitKey(0)
cv2.destroyAllWindows()

import cv2
import numpy as np# 获取最优的DFT大小
rows, cols = 480, 640  # 假设图像大小
optimal_rows = cv2.getOptimalDFTSize(rows)
optimal_cols = cv2.getOptimalDFTSize(cols)print(f"Original size: ({rows}, {cols})")
print(f"Optimal DFT size: ({optimal_rows}, {optimal_cols})")

# 读取图像并转换为灰度图
image = cv2.imread('path_to_image.jpg', cv2.IMREAD_GRAYSCALE)
rows, cols = image.shape# 获取最优的DFT大小
optimal_rows = cv2.getOptimalDFTSize(rows)
optimal_cols = cv2.getOptimalDFTSize(cols)# 扩展图像到最佳大小
padded_image = cv2.copyMakeBorder(image, 0, optimal_rows - rows, 0, optimal_cols - cols, cv2.BORDER_CONSTANT, value=0)# 执行DFT
dft_image = cv2.dft(np.float32(padded_image), flags=cv2.DFT_COMPLEX_OUTPUT)# 移动频谱
dft_shift = np.fft.fftshift(dft_image)# 计算幅度谱
magnitude_spectrum = 20 * np.log(cv2.magnitude(dft_shift[:, :, 0], dft_shift[:, :, 1]))# 显示幅度谱
cv2.imshow('Magnitude Spectrum', magnitude_spectrum)
cv2.waitKey(0)
cv2.destroyAllWindows()# 执行逆DFT
idft_shift = np.fft.ifftshift(dft_shift)
idft_image = cv2.idft(idft_shift)
idft_image = cv2.magnitude(idft_image[:, :, 0], idft_image[:, :, 1])# 显示逆变换后的图像
cv2.imshow('Inverse DFT Image', idft_image)
cv2.waitKey(0)
cv2.destroyAllWindows()

# 创建低通滤波器
crow, ccol = optimal_rows // 2 , optimal_cols // 2
mask = np.zeros((optimal_rows, optimal_cols, 2), np.uint8)
mask[crow-30:crow+30, ccol-30:ccol+30] = 1# 应用低通滤波器
fshift = dft_shift * mask# 计算滤波后的幅度谱
fshift_magnitude_spectrum = 20 * np.log(cv2.magnitude(fshift[:, :, 0], fshift[:, :, 1]))# 显示滤波后的幅度谱
cv2.imshow('Filtered Magnitude Spectrum', fshift_magnitude_spectrum)
cv2.waitKey(0)
cv2.destroyAllWindows()# 执行逆DFT
f_ishift = np.fft.ifftshift(fshift)
img_back = cv2.idft(f_ishift)
img_back = cv2.magnitude(img_back[:, :, 0], img_back[:, :, 1])# 显示滤波后的图像
cv2.imshow('Filtered Image', img_back)
cv2.waitKey(0)
cv2.destroyAllWindows()