【光电智造】算法|OpenCV快速傅里叶变换(FFT)用于图像和视频流的模糊检测

$ tree --dirsfirst.├── images│   ├── adrian_01.png│   ├── adrian_02.png│   ├── jemma.png│   └── resume.png├── pyimagesearch│   ├── __init__.py│   └── blur_detector.py├── blur_detector_image.py└── blur_detector_video.py2 directories, 8 files

# import the necessary packagesimport matplotlib.pyplot as pltimport numpy as npdef detect_blur_fft(image, size=60, thresh=10, vis=False):  # grab the dimensions of the image and use the dimensions to  # derive the center (x, y)-coordinates  (h, w) = image.shape  (cX, cY) = (int(w / 2.0), int(h / 2.0))

  # compute the FFT to find the frequency transform, then shift  # the zero frequency component (i.e., DC component located at  # the top-left corner) to the center where it will be more  # easy to analyze  fft = np.fft.fft2(image)  fftShift = np.fft.fftshift(fft)

  # check to see if we are visualizing our output  if vis:    # compute the magnitude spectrum of the transform    magnitude = 20 * np.log(np.abs(fftShift))    # display the original input image    (fig, ax) = plt.subplots(1, 2, )    ax[0].imshow(image, cmap="gray")    ax[0].set_title("Input")    ax[0].set_xticks([])    ax[0].set_yticks([])    # display the magnitude image    ax[1].imshow(magnitude, cmap="gray")    ax[1].set_title("Magnitude Spectrum")    ax[1].set_xticks([])    ax[1].set_yticks([])    # show our plots    plt.show()

  # zero-out the center of the FFT shift (i.e., remove low  # frequencies), apply the inverse shift such that the DC  # component once again becomes the top-left, and then apply  # the inverse FFT  fftShift[cY - size:cY + size, cX - size:cX + size] = 0  fftShift = np.fft.ifftshift(fftShift)  recon = np.fft.ifft2(fftShift)

  # compute the magnitude spectrum of the reconstructed image,  # then compute the mean of the magnitude values  magnitude = 20 * np.log(np.abs(recon))  mean = np.mean(magnitude)  # the image will be considered "blurry" if the mean value of the  # magnitudes is less than the threshold value  return (mean, mean <= thresh

# import the necessary packagesfrom pyimagesearch.blur_detector import detect_blur_fftimport numpy as npimport argparseimport imutilsimport cv2# construct the argument parser and parse the argumentsap = argparse.ArgumentParser()ap.add_argument("-i", "--image", type=str, required=True,  help="path input image that we'll detect blur in")ap.add_argument("-t", "--thresh", type=int, default=20,  help="threshold for our blur detector to fire")ap.add_argument("-v", "--vis", type=int, default=-1,  help="whether or not we are visualizing intermediary steps")ap.add_argument("-d", "--test", type=int, default=-1,  help="whether or not we should progressively blur the image")args = vars(ap.parse_args())

# load the input image from disk, resize it, and convert it to# grayscaleorig = cv2.imread(args["image"])orig = imutils.resize(orig, width=500)gray = cv2.cvtColor(orig, cv2.COLOR_BGR2GRAY)# apply our blur detector using the FFT(mean, blurry) = detect_blur_fft(gray, size=60,  thresh=args["thresh"], vis=args["vis"] > 0)

# draw on the image, indicating whether or not it is blurryimage = np.dstack([gray] * 3)color = (0, 0, 255) if blurry else (0, 255, 0)text = "Blurry ({:.4f})" if blurry else "Not Blurry ({:.4f})"text = text.format(mean)cv2.putText(image, text, (10, 25), cv2.FONT_HERSHEY_SIMPLEX, 0.7,  color, 2)print("[INFO] {}".format(text))# show the output imagecv2.imshow("Output", image)cv2.waitKey(0)

# check to see if are going to test our FFT blurriness detector using# various sizes of a Gaussian kernelif args["test"] > 0:  # loop over various blur radii  for radius in range(1, 30, 2):    # clone the original grayscale image    image = gray.copy()    # check to see if the kernel radius is greater than zero    if radius > 0:      # blur the input image by the supplied radius using a      # Gaussian kernel      image = cv2.GaussianBlur(image, (radius, radius), 0)      # apply our blur detector using the FFT      (mean, blurry) = detect_blur_fft(image, size=60,        thresh=args["thresh"], vis=args["vis"] > 0)      # draw on the image, indicating whether or not it is      # blurry      image = np.dstack([image] * 3)      color = (0, 0, 255) if blurry else (0, 255, 0)      text = "Blurry ({:.4f})" if blurry else "Not Blurry ({:.4f})"      text = text.format(mean)      cv2.putText(image, text, (10, 25), cv2.FONT_HERSHEY_SIMPLEX,        0.7, color, 2)      print("[INFO] Kernel: {}, Result: {}".format(radius, text))    # show the image    cv2.imshow("Test Image", image)    cv2.waitKey(0)

$ python blur_detector_image.py --image images/adrian_01.png[INFO] Not Blurry (42.4630)

$ python blur_detector_image.py --image images/jemma.png[INFO] Blurry (12.4738)

$ python blur_detector_image.py --image images/adrian_02.png --test 1[INFO] Not Blurry (32.0934)[INFO] Kernel: 1, Result: Not Blurry (32.0934)[INFO] Kernel: 3, Result: Not Blurry (25.1770)[INFO] Kernel: 5, Result: Not Blurry (20.5668)[INFO] Kernel: 7, Result: Blurry (13.4830)[INFO] Kernel: 9, Result: Blurry (7.8893)[INFO] Kernel: 11, Result: Blurry (0.6506)[INFO] Kernel: 13, Result: Blurry (-5.3609)[INFO] Kernel: 15, Result: Blurry (-11.4612)[INFO] Kernel: 17, Result: Blurry (-17.0109)[INFO] Kernel: 19, Result: Blurry (-19.6464)[INFO] Kernel: 21, Result: Blurry (-20.4758)[INFO] Kernel: 23, Result: Blurry (-20.7365)[INFO] Kernel: 25, Result: Blurry (-20.9362)[INFO] Kernel: 27, Result: Blurry (-21.1911)[INFO] Kernel: 29, Result: Blurry (-21.3853)

$ python blur_detector_image.py --image images/resume.png --thresh 27 --test 1 --vis 1[INFO] Not Blurry (34.6735)[INFO] Kernel: 1, Result: Not Blurry (34.6735)[INFO] Kernel: 3, Result: Not Blurry (29.2539)[INFO] Kernel: 5, Result: Blurry (26.2893)[INFO] Kernel: 7, Result: Blurry (21.7390)[INFO] Kernel: 9, Result: Blurry (18.3632)[INFO] Kernel: 11, Result: Blurry (12.7235)[INFO] Kernel: 13, Result: Blurry (9.1489)[INFO] Kernel: 15, Result: Blurry (2.3377)[INFO] Kernel: 17, Result: Blurry (-2.6372)[INFO] Kernel: 19, Result: Blurry (-9.1908)[INFO] Kernel: 21, Result: Blurry (-15.9808)[INFO] Kernel: 23, Result: Blurry (-20.6240)[INFO] Kernel: 25, Result: Blurry (-29.7478)[INFO] Kernel: 27, Result: Blurry (-29.0728)[INFO] Kernel: 29, Result: Blurry (-37.7561)

# import the necessary packagesfrom imutils.video import VideoStreamfrom pyimagesearch.blur_detector import detect_blur_fftimport argparseimport imutilsimport timeimport cv2# construct the argument parser and parse the argumentsap = argparse.ArgumentParser()ap.add_argument("-t", "--thresh", type=int, default=10,  help="threshold for our blur detector to fire")args = vars(ap.parse_args())

# initialize the video stream and allow the camera sensor to warm upprint("[INFO] starting video stream...")vs = VideoStream(src=0).start()time.sleep(2.0)# loop over the frames from the video streamwhile True:  # grab the frame from the threaded video stream and resize it  # to have a maximum width of 400 pixels  frame = vs.read()  frame = imutils.resize(frame, width=500)  # convert the frame to grayscale and detect blur in it  gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)  (mean, blurry) = detect_blur_fft(gray, size=60,    thresh=args["thresh"], vis=False)

  # draw on the frame, indicating whether or not it is blurry  color = (0, 0, 255) if blurry else (0, 255, 0)  text = "Blurry ({:.4f})" if blurry else "Not Blurry ({:.4f})"  text = text.format(mean)  cv2.putText(frame, text, (10, 25), cv2.FONT_HERSHEY_SIMPLEX,    0.7, color, 2)  # show the output frame  cv2.imshow("Frame", frame)  key = cv2.waitKey(1) & 0xFF  # if the `q` key was pressed, break from the loop  if key == ord("q"):    break# do a bit of cleanupcv2.destroyAllWindows()vs.stop()

$ python blur_detector_video.py[INFO] starting video stream...