问题
A project I have been working about for some time is a unsupervised leaf segmentation. The leaves are captured on a white or colored paper, and some of them has shadows.
I want to be able to threshold the leaf and also remove the shadow (while reserving the leaf's details); however I cannot use fixed threshold values due to diseases changing the color of the leaf.
Then, I begin to research and find out a proposal by Horprasert et. al. (1999) in "A Statistical Approach for Real-time Robust Background Subtraction and Shadow Detection", which compare areas in the image with colour of the now-known background using the chromacity distortion measure. This measure takes account of the fact that for desaturated colours, hue is not a relevant measure.
Based on it, I was able to achieve the following results:
However, the leaves that are captured on a white paper need to change the Mask V cv2.bitwise_not() giving me the below result:
I'm thinking that I'm forgetting some step to get a complete mask that will work for all or most of my leaves. Samples can be found here.
My Code:
import numpy as np
import cv2
import matplotlib.pyplot as plot
import scipy.ndimage as ndimage
def brightness_distortion(I, mu, sigma):
return np.sum(I*mu/sigma**2, axis=-1) / np.sum((mu/sigma)**2, axis=-1)
def chromacity_distortion(I, mu, sigma):
alpha = brightness_distortion(I, mu, sigma)[...,None]
return np.sqrt(np.sum(((I - alpha * mu)/sigma)**2, axis=-1))
def bwareafilt ( image ):
image = image.astype(np.uint8)
nb_components, output, stats, centroids = cv2.connectedComponentsWithStats(image, connectivity=4)
sizes = stats[:, -1]
max_label = 1
max_size = sizes[1]
for i in range(2, nb_components):
if sizes[i] > max_size:
max_label = i
max_size = sizes[i]
img2 = np.zeros(output.shape)
img2[output == max_label] = 255
return img2
img = cv2.imread("Amostra03.jpeg")
sat = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)[:,:,1]
val = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)[:,:,2]
sat = cv2.medianBlur(sat, 11)
val = cv2.medianBlur(val, 11)
thresh_S = cv2.adaptiveThreshold(sat , 255, cv2.ADAPTIVE_THRESH_MEAN_C, cv2.THRESH_BINARY, 401, 10);
thresh_V = cv2.adaptiveThreshold(val , 255, cv2.ADAPTIVE_THRESH_MEAN_C, cv2.THRESH_BINARY, 401, 10);
mean_S, stdev_S = cv2.meanStdDev(img, mask = 255 - thresh_S)
mean_S = mean_S.ravel().flatten()
stdev_S = stdev_S.ravel()
chrom_S = chromacity_distortion(img, mean_S, stdev_S)
chrom255_S = cv2.normalize(chrom_S, chrom_S, alpha=0, beta=255, norm_type=cv2.NORM_MINMAX).astype(np.uint8)[:,:,None]
mean_V, stdev_V = cv2.meanStdDev(img, mask = 255 - thresh_V)
mean_V = mean_V.ravel().flatten()
stdev_V = stdev_V.ravel()
chrom_V = chromacity_distortion(img, mean_V, stdev_V)
chrom255_V = cv2.normalize(chrom_V, chrom_V, alpha=0, beta=255, norm_type=cv2.NORM_MINMAX).astype(np.uint8)[:,:,None]
thresh2_S = cv2.adaptiveThreshold(chrom255_S , 255, cv2.ADAPTIVE_THRESH_MEAN_C, cv2.THRESH_BINARY, 401, 10);
thresh2_V = cv2.adaptiveThreshold(chrom255_V , 255, cv2.ADAPTIVE_THRESH_MEAN_C, cv2.THRESH_BINARY, 401, 10);
images = [img, thresh_S, thresh_V, cv2.bitwise_and(thresh2_S, cv2.bitwise_not(thresh2_V))]
titles = ['Original Image', 'Mask S', 'Mask V', 'S + V']
for i in range(4):
plot.subplot(2,2,i+1),
if i == 0 :
plot.imshow(images[i])
else :
plot.imshow(images[i], cmap='gray')
plot.title(titles[i])
plot.xticks([]),plot.yticks([])
plot.show()
Any idea to solve this issue?
回答1:
Try this on...I'm using "grabCut" from the openCV lib. It's not perfect, but it might be a good start.
import cv2
import numpy as np
from matplotlib import pyplot as plt
import matplotlib
#%matplotlib inline #uncomment if in notebook
def mask_leaf(im_name, external_mask=None):
im = cv2.imread(im_name)
im = cv2.blur(im, (5,5))
height, width = im.shape[:2]
mask = np.ones(im.shape[:2], dtype=np.uint8) * 2 #start all possible background
'''
#from docs:
0 GC_BGD defines an obvious background pixels.
1 GC_FGD defines an obvious foreground (object) pixel.
2 GC_PR_BGD defines a possible background pixel.
3 GC_PR_FGD defines a possible foreground pixel.
'''
#2 circles are "drawn" on mask. a smaller centered one I assume all pixels are definite foreground. a bigger circle, probably foreground.
r = 100
cv2.circle(mask, (int(width/2.), int(height/2.)), 2*r, 3, -3) #possible fg
#next 2 are greens...dark and bright to increase the number of fg pixels.
mask[(im[:,:,0] < 45) & (im[:,:,1] > 55) & (im[:,:,2] < 55)] = 1 #dark green
mask[(im[:,:,0] < 190) & (im[:,:,1] > 190) & (im[:,:,2] < 200)] = 1 #bright green
mask[(im[:,:,0] > 200) & (im[:,:,1] > 200) & (im[:,:,2] > 200) & (mask != 1)] = 0 #pretty white
cv2.circle(mask, (int(width/2.), int(height/2.)), r, 1, -3) #fg
#if you pass in an external mask derived from some other operation it is factored in here.
if external_mask is not None:
mask[external_mask == 1] = 1
bgdmodel = np.zeros((1,65), np.float64)
fgdmodel = np.zeros((1,65), np.float64)
cv2.grabCut(im, mask, None, bgdmodel, fgdmodel, 1, cv2.GC_INIT_WITH_MASK)
#show mask
plt.figure(figsize=(10,10))
plt.imshow(mask)
plt.show()
#mask image
mask2 = np.where((mask==1) + (mask==3), 255, 0).astype('uint8')
output = cv2.bitwise_and(im, im, mask=mask2)
plt.figure(figsize=(10,10))
plt.imshow(output)
plt.show()
mask_leaf('leaf1.jpg', external_mask=None)
mask_leaf('leaf2.jpg', external_mask=None)
Addressing the external mask. Here's an example of HDBSCAN clustering...I'm not going to go into the details...you can look up the docs and change it or use as-is.
import hdbscan
from collections import Counter
def hdbscan_mask(im_name):
im = cv2.imread(im_name)
im = cv2.blur(im, (5,5))
indices = np.dstack(np.indices(im.shape[:2]))
data = np.concatenate((indices, im), axis=-1)
data = data[:,2:]
data = imb.reshape(im.shape[0]*im.shape[1], 3)
clusterer = hdbscan.HDBSCAN(min_cluster_size=1000, min_samples=20)
clusterer.fit(data)
plt.figure(figsize=(10,10))
plt.imshow(clusterer.labels_.reshape(im.shape[0:2]))
plt.show()
height, width = im.shape[:2]
mask = np.ones(im.shape[:2], dtype=np.uint8) * 2 #start all possible background
cv2.circle(mask, (int(width/2.), int(height/2.)), 100, 1, -3) #possible fg
#grab cluster number for circle
vals_im = clusterer.labels_.reshape(im.shape[0:2])
vals = vals_im[mask == 1]
commonvals = []
cnts = Counter(vals)
for v, count in cnts.most_common(20):
#print '%i: %7d' % (v, count)
if v == -1:
continue
commonvals.append(v)
tst = np.in1d(vals_im, np.array(commonvals))
tst = tst.reshape(vals_im.shape)
hmask = tst.astype(np.uint8)
plt.figure(figsize=(10,10))
plt.imshow(hmask)
plt.show()
return hmask
hmask = hdbscan_mask('leaf1.jpg')
then to use the initial function with the new mask (output suppressed):
mask_leaf('leaf1.jpg', external_mask=hmask)
This was all made in a notebook from scratch so hopefully there's no errant variables that choke it up when running it somewhere else. (note: I did NOT swap BGR to RGB for plt display, sorry)
来源：https://stackoverflow.com/questions/51031733/detection-of-leaf-on-unpredictable-background