python - OpenCV:检测FFT上最亮的行

Question

我对图像有一个快速的傅立叶变换，如下所示:



我想使用边缘检测和霍夫变换来获得这条明亮的水平线(我正在测量图像的旋转 Angular )。但是Canny运算符的效果不好，因为颜色变化很小。我怎么能检测到那条线？

我产生这样的FFT:

dft = cv2.dft(frame, flags=cv2.DFT_COMPLEX_OUTPUT)
dft = np.fft.fftshift(dft)
spectrum = 20 * np.log(cv2.magnitude(dft[:, :, 0], dft[:, :, 1]))
# Converting to uint8 for Canny and HoughLinesP
spectrum = spectrum / np.max(spectrum) * 255
spectrum = spectrum.astype(np.uint8)

Answer 1

这是Python / OpenCV中的一种方法。

读取输入的

转换为灰色并反转

应用自适应阈值并反转

应用形态学清理阈值并填写

行

应用Canny边缘检测

应用霍夫线检测

画出最大的线

保存结果

输入:

import cv2
import numpy as np

# read image
img = cv2.imread('fft.png')

# convert to grayscale
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
gray = 255 - gray

# threshold
thresh = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_MEAN_C, cv2.THRESH_BINARY, 13, 3)
thresh = 255 - thresh

# apply close to connect the white areas
kernel = np.ones((3,3), np.uint8)
morph = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel)
kernel = np.ones((1,9), np.uint8)
morph = cv2.morphologyEx(morph, cv2.MORPH_CLOSE, kernel)

# apply canny edge detection
edges = cv2.Canny(morph, 150, 200)

# get hough lines
result = img.copy()
lines = cv2.HoughLines(edges, 1, np.pi/180, 50)
# Draw line on the image
for rho,theta in lines[0]:
    a = np.cos(theta)
    b = np.sin(theta)
    x0 = a*rho
    y0 = b*rho
    x1 = int(x0 + 1000*(-b))
    y1 = int(y0 + 1000*(a))
    x2 = int(x0 - 1000*(-b))
    y2 = int(y0 - 1000*(a))
    cv2.line(result, (x1, y1), (x2, y2), (0, 0, 255), 1)

# save resulting images
cv2.imwrite('fft_thresh.jpg',thresh)
cv2.imwrite('fft_morph.jpg',morph)
cv2.imwrite('fft_edges.jpg',edges)
cv2.imwrite('fft_line.jpg',result)

# show thresh and result    
cv2.imshow("thresh", thresh)
cv2.imshow("morph", morph)
cv2.imshow("edges", edges)
cv2.imshow("result", result)
cv2.waitKey(0)
cv2.destroyAllWindows()

阈值图片:



形态清除图像:



边缘图片:



在输入图像上绘制的结果霍夫线: