我们从Python开源项目中，提取了以下5个代码示例，用于说明如何使用skimage.morphology.remove_small_objects()。
def remove_conn_components(pred_mask, num_cc): labels = label(pred_mask) if num_cc == 1: maxArea = 0 for region in regionprops(labels): if region.area > maxArea: maxArea = region.area print(maxArea) mask = remove_small_objects(labels, maxArea - 1) else: mask = remove_small_objects(labels, 3000, connectivity=2) return mask
def removeSmallObject(filledImg, minSize = 20000): biImgRsize = filledImg.shape[0] * 0.1 biImgCsize = filledImg.shape[1] * 0.1 biImg = filledImg[biImgRsize:-biImgRsize, biImgCsize:-biImgCsize] cleanedImg = morphology.remove_small_objects(biImg, minSize) return cleanedImg
def localization(x, y): """Simple post-processing and get IVDs positons. Return: positons: calculated by `ndimage.measurements.center_of_mass` y: after fill holes and remove small objects. """ labels, nums = label(y, return_num=True) areas = np.array([prop.filled_area for prop in regionprops(labels)]) assert nums >= 7, 'Fail in this test, should detect at least seven regions.' # Segment a joint region which should be separate (if any). while np.max(areas) > 10000: y = ndimage.binary_opening(y, structure=np.ones((3, 3, 3))) areas = np.array([prop.filled_area for prop in regionprops(label(y))]) # Remove small objects. threshold = sorted(areas, reverse=True)[7] y = morphology.remove_small_objects(y, threshold + 1) # Fill holes. y = ndimage.binary_closing(y, structure=np.ones((3, 3, 3))) y = morphology.remove_small_holes(y, min_size=512, connectivity=3) positions = ndimage.measurements.center_of_mass(x, label(y), range(1, 8)) return np.array(positions), y
def compute_binary_mask_lasseck(spectrogram, threshold): # normalize to [0, 1) norm_spectrogram = normalize(spectrogram) # median clipping binary_image = median_clipping(norm_spectrogram, threshold) # closing binary image (dilation followed by erosion) binary_image = morphology.binary_closing(binary_image, selem=np.ones((4, 4))) # dialate binary image binary_image = morphology.binary_dilation(binary_image, selem=np.ones((4, 4))) # apply median filter binary_image = filters.median(binary_image, selem=np.ones((2, 2))) # remove small objects binary_image = morphology.remove_small_objects(binary_image, min_size=32, connectivity=1) mask = np.array([np.max(col) for col in binary_image.T]) mask = smooth_mask(mask) return mask # TODO: This method needs some real testing
def find_peaks_regionprops(z, min_sigma=4, max_sigma=5, threshold=1, min_size=50, return_props=False): """ Finds peaks using regionprops. Uses the difference of two gaussian convolutions to separate signal from background, and then uses the skimage.measure.regionprops function to find connected islands (peaks). Small blobs can be rejected using `min_size`. Parameters ---------- z : ndarray Array of image intensities. min_sigma : int, float Standard deviation for the minimum gaussian convolution max_sigma : int, float Standard deviation for the maximum gaussian convolution threshold : int, float Minimum difference in intensity min_size : int Minimum size in pixels of blob return_props : bool Return skimage.measure.regionprops Returns ------- ndarray (n_peaks, 2) Array of peak coordinates. """ from skimage import morphology, measure difference = ndi.gaussian_filter(z, min_sigma) - ndi.gaussian_filter(z, max_sigma) labels, numlabels = ndi.label(difference > threshold) labels = morphology.remove_small_objects(labels, min_size) props = measure.regionprops(labels, z) if return_props: return props else: peaks = np.array([prop.centroid for prop in props]) return clean_peaks(peaks)
