我们从Python开源项目中，提取了以下7个代码示例，用于说明如何使用scipy.ndimage.gaussian_gradient_magnitude()。
def image_gradient(in_file, snr, out_file=None): """Computes the magnitude gradient of an image using numpy""" import os.path as op import numpy as np import nibabel as nb from scipy.ndimage import gaussian_gradient_magnitude as gradient if out_file is None: fname, ext = op.splitext(op.basename(in_file)) if ext == '.gz': fname, ext2 = op.splitext(fname) ext = ext2 + ext out_file = op.abspath('{}_grad{}'.format(fname, ext)) imnii = nb.load(in_file) data = imnii.get_data().astype(np.float32) # pylint: disable=no-member datamax = np.percentile(data.reshape(-1), 99.5) data *= 100 / datamax grad = gradient(data, 3.0) gradmax = np.percentile(grad.reshape(-1), 99.5) grad *= 100. grad /= gradmax nb.Nifti1Image(grad, imnii.get_affine(), imnii.get_header()).to_filename(out_file) return out_file
def getGradientVideo(I, IDims, sigma = 1): GV = np.zeros(I.shape) for i in range(I.shape[0]): X = np.reshape(I[i, :], IDims) G = rgb2gray(X, False) GM = gaussian_gradient_magnitude(G, sigma) F = np.zeros(IDims) for k in range(F.shape[2]): F[:, :, k] = GM GV[i, :] = F.flatten() return GV
def debug_analyse_image_texture(file, sigma=1.0): image = cv2.imread(file, 0) blur = gaussian_filter(input=image, sigma=sigma) cv2.imshow('Image', image - blur) #analysis = ndimage.gaussian_gradient_magnitude(image, sigma=sigma) #cv2.imshow('Analysis', analysis * 10) cv2.waitKey(0) cv2.destroyAllWindows() ##########################################
def set_rocks_in_grad(self, elevation, landcover): """ Modify the land cover to create rocks in the large gradient pixels (large steepness) Position arguments: elevation -- Elevation image landcover -- Landcover to become edited Returned value: Edited landcover """ # Compute the steepness of each pixel grad = gaussian_gradient_magnitude(elevation, 1.0) grad /= self.mercator.Resolution(self.__zoom) # Get the mask of rock (with a smooth transition) mask = (grad >= ROCK_STEEPNESS).astype(np.float) mask = gaussian_filter(mask, 3.0) # Blend the images dtype = landcover.dtype rock_image = np.zeros(landcover.shape, dtype=dtype) rock_image[:,:] = ROCK_COLOR for i in range(3): rock_image[:,:,i] = (mask * rock_image[:,:,i]).astype(dtype) landcover[:,:,i] = ((1.0 - mask) * landcover[:,:,i]).astype(dtype) landcover += rock_image return landcover
def headmsk_wf(name='HeadMaskWorkflow', use_bet=True): """ Computes a head mask as in [Mortamet2009]_. .. workflow:: from mriqc.workflows.anatomical import headmsk_wf wf = headmsk_wf() """ has_dipy = False try: from dipy.denoise import nlmeans has_dipy = True except ImportError: pass workflow = pe.Workflow(name=name) inputnode = pe.Node(niu.IdentityInterface(fields=['in_file', 'in_segm']), name='inputnode') outputnode = pe.Node(niu.IdentityInterface(fields=['out_file']), name='outputnode') if use_bet or not has_dipy: # Alternative for when dipy is not installed bet = pe.Node(fsl.BET(surfaces=True), name='fsl_bet') workflow.connect([ (inputnode, bet, [('in_file', 'in_file')]), (bet, outputnode, [('outskin_mask_file', 'out_file')]) ]) else: from niworkflows.nipype.interfaces.dipy import Denoise enhance = pe.Node(niu.Function( input_names=['in_file'], output_names=['out_file'], function=_enhance), name='Enhance') estsnr = pe.Node(niu.Function( input_names=['in_file', 'seg_file'], output_names=['out_snr'], function=_estimate_snr), name='EstimateSNR') denoise = pe.Node(Denoise(), name='Denoise') gradient = pe.Node(niu.Function( input_names=['in_file', 'snr'], output_names=['out_file'], function=image_gradient), name='Grad') thresh = pe.Node(niu.Function( input_names=['in_file', 'in_segm'], output_names=['out_file'], function=gradient_threshold), name='GradientThreshold') workflow.connect([ (inputnode, estsnr, [('in_file', 'in_file'), ('in_segm', 'seg_file')]), (estsnr, denoise, [('out_snr', 'snr')]), (inputnode, enhance, [('in_file', 'in_file')]), (enhance, denoise, [('out_file', 'in_file')]), (estsnr, gradient, [('out_snr', 'snr')]), (denoise, gradient, [('out_file', 'in_file')]), (inputnode, thresh, [('in_segm', 'in_segm')]), (gradient, thresh, [('out_file', 'in_file')]), (thresh, outputnode, [('out_file', 'out_file')]) ]) return workflow
def gradient_threshold(in_file, in_segm, thresh=1.0, out_file=None): """ Compute a threshold from the histogram of the magnitude gradient image """ import os.path as op import numpy as np import nibabel as nb from scipy import ndimage as sim struc = sim.iterate_structure(sim.generate_binary_structure(3, 2), 2) if out_file is None: fname, ext = op.splitext(op.basename(in_file)) if ext == '.gz': fname, ext2 = op.splitext(fname) ext = ext2 + ext out_file = op.abspath('{}_gradmask{}'.format(fname, ext)) imnii = nb.load(in_file) hdr = imnii.get_header().copy() hdr.set_data_dtype(np.uint8) # pylint: disable=no-member data = imnii.get_data().astype(np.float32) mask = np.zeros_like(data, dtype=np.uint8) # pylint: disable=no-member mask[data > 15.] = 1 segdata = nb.load(in_segm).get_data().astype(np.uint8) segdata[segdata > 0] = 1 segdata = sim.binary_dilation(segdata, struc, iterations=2, border_value=1).astype(np.uint8) # pylint: disable=no-member mask[segdata > 0] = 1 mask = sim.binary_closing(mask, struc, iterations=2).astype(np.uint8) # pylint: disable=no-member # Remove small objects label_im, nb_labels = sim.label(mask) artmsk = np.zeros_like(mask) if nb_labels > 2: sizes = sim.sum(mask, label_im, list(range(nb_labels + 1))) ordered = list(reversed(sorted(zip(sizes, list(range(nb_labels + 1)))))) for _, label in ordered[2:]: mask[label_im == label] = 0 artmsk[label_im == label] = 1 mask = sim.binary_fill_holes(mask, struc).astype(np.uint8) # pylint: disable=no-member nb.Nifti1Image(mask, imnii.get_affine(), hdr).to_filename(out_file) return out_file
