Python cv2.magnitude方法代码示例

# 需要导入模块: import cv2 [as 别名]
# 或者: from cv2 import magnitude [as 别名]
def get_mag_avg(img):

    img = np.sqrt(img)

    kernels = get_kernels()

    mag = np.zeros(img.shape, dtype='float32')

    for kernel_filter in kernels:

        gx = cv2.filter2D(np.float32(img), cv2.CV_32F, kernel_filter[1], borderType=cv2.BORDER_REFLECT)
        gy = cv2.filter2D(np.float32(img), cv2.CV_32F, kernel_filter[0], borderType=cv2.BORDER_REFLECT)

        mag += cv2.magnitude(gx, gy)

    mag /= len(kernels)

    return np.uint8(mag) 

# 需要导入模块: import cv2 [as 别名]
# 或者: from cv2 import magnitude [as 别名]
def get_mag_ang(img):

    """
    Gets image gradient (magnitude) and orientation (angle)

    Args:
        img

    Returns:
        Gradient, orientation
    """

    img = np.sqrt(img)

    gx = cv2.Sobel(np.float32(img), cv2.CV_32F, 1, 0)
    gy = cv2.Sobel(np.float32(img), cv2.CV_32F, 0, 1)

    mag, ang = cv2.cartToPolar(gx, gy)

    return mag, ang, gx, gy 

# 需要导入模块: import cv2 [as 别名]
# 或者: from cv2 import magnitude [as 别名]
def grad_mag(ch_bd):

    # normalize
    mu_ = ch_bd.mean()
    std_ = ch_bd.std()
    ch_bd = np.divide(np.subtract(ch_bd, mu_), std_)

    ch_bd[np.isnan(ch_bd)] = 0
    ch_bd += abs(ch_bd.min())

    # compute gradient orientation and magnitude
    return get_mag_ang(ch_bd) 

# 需要导入模块: import cv2 [as 别名]
# 或者: from cv2 import magnitude [as 别名]
def fourier_transform(ch_bd):

    dft = cv2.dft(np.float32(ch_bd), flags=cv2.DFT_COMPLEX_OUTPUT)
    dft_shift = np.fft.fftshift(dft)

    # get the Power Spectrum
    magnitude_spectrum = 20. * np.log(cv2.magnitude(dft_shift[:, :, 0], dft_shift[:, :, 1]))

    psd1D = azimuthal_avg(magnitude_spectrum)

    return list(cv2.meanStdDev(psd1D)) 

# 需要导入模块: import cv2 [as 别名]
# 或者: from cv2 import magnitude [as 别名]
def main():
    # read an image 
    img = cv2.imread('../figures/flower.png')
    
    # create cropped grayscale image from the original image
    crop_gray = cv2.cvtColor(img[100:400, 100:400], cv2.COLOR_BGR2GRAY)
    
    # take discrete fourier transform 
    dft = cv2.dft(np.float32(crop_gray),flags = cv2.DFT_COMPLEX_OUTPUT)
    dft_shift = np.fft.fftshift(dft)
    magnitude_spectrum = 20*np.log(cv2.magnitude(dft_shift[:,:,0],dft_shift[:,:,1]))
    
    # plot results
    plot_dft(crop_gray, magnitude_spectrum) 

# 需要导入模块: import cv2 [as 别名]
# 或者: from cv2 import magnitude [as 别名]
def filter(self, image):
        """
        Filter the given image with the Gabor kernels in this bank.

        Parameters
        ----------
        image: numpy.array
            Image to be filtered.

        Returns
        -------
        responses: numpy.array
            List of the responses of the filtering with the Gabor kernels. The
            responses are the magnitude of both the real and imaginary parts of
            the convolution with each kernel, hence this list dimensions are the
            same of the image, plus another dimension for the 32 responses (one
            for each kernel in the bank, since there are 4 wavelengths and 8
            orientations).
        """

        image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

        responses = []
        for wavelength in self._wavelengths:
            for orientation in self._orientations:

                # Get the kernel
                frequency = 1 / wavelength
                par = KernelParams(wavelength, orientation)
                kernel = self._kernels[par]

                # Filter with both real and imaginary parts
                real = cv2.filter2D(image, cv2.CV_32F, kernel.real)
                imag = cv2.filter2D(image, cv2.CV_32F, kernel.imag)

                # The response is the magnitude of the real and imaginary
                # responses to the filters, normalized to [-1, 1]
                mag = cv2.magnitude(real, imag)
                cv2.normalize(mag, mag, -1, 1, cv2.NORM_MINMAX)

                responses.append(mag)

        return np.array(responses) 

# 需要导入模块: import cv2 [as 别名]
# 或者: from cv2 import magnitude [as 别名]
def feature_fourier(chBd, blk, scs, end_scale):

    rows, cols = chBd.shape
    scales_half = int(end_scale / 2.0)
    scales_blk = end_scale - blk
    out_len = 0
    pix_ctr = 0

    for i in range(0, rows-scales_blk, blk):
        for j in range(0, cols-scales_blk, blk):
            for k in scs:
                out_len += 2

    # set the output list
    out_list = np.zeros(out_len, dtype='float32')

    for i in range(0, rows-scales_blk, blk):

        for j in range(0, cols-scales_blk, blk):

            for k in scs:

                k_half = int(k / 2.0)

                ch_bd = chBd[i+scales_half-k_half:i+scales_half-k_half+k,
                             j+scales_half-k_half:j+scales_half-k_half+k]

                # get the Fourier Transform
                dft = cv2.dft(np.float32(ch_bd), flags=cv2.DFT_COMPLEX_OUTPUT)
                dft_shift = np.fft.fftshift(dft)

                # get the Power Spectrum
                magnitude_spectrum = 20.0 * np.log(cv2.magnitude(dft_shift[:, :, 0], dft_shift[:, :, 1]))

                psd1D = azimuthal_avg(magnitude_spectrum)

                sts = list(cv2.meanStdDev(psd1D))

                # plt.subplot(121)
                # plt.imshow(ch_bd, cmap='gray')
                # plt.subplot(122)
                # plt.imshow(magnitude_spectrum, interpolation='nearest')
                # plt.show()
                # print psd1D
                # sys.exit()

                for st in sts:

                    if np.isnan(st[0][0]):
                        out_list[pix_ctr] = 0.0
                    else:
                        out_list[pix_ctr] = st[0][0]

                    pix_ctr += 1

    out_list[np.isnan(out_list) | np.isinf(out_list)] = 0.0

    return out_list