def ThinImage(imgPath):
    img = Image.open(imgPath).convert('L')
    
    imgArray = numpy.asarray(img)
    imgBinary =  pymorph.neg(pymorph.binary(imgArray))
    img = pymorph.thin(imgBinary)
    iPrune = pymorph.thin(img,pymorph.endpoints('homotopic'),10)

    Image.fromarray(pymorph.gray(pymorph.neg(iPrune))).save('thinned.png','PNG')
    print "Saving"
Beispiel #2
0
def medial_points(thresh, filepath = '.'):
	#leggo l'immagine e la trasformo in 0 o 255
	(th, im_bw) = cv2.threshold(thresh, 240, 255, cv2.THRESH_BINARY_INV)
	#plt.imshow(cv2.cvtColor(im_bw,cv2.COLOR_GRAY2RGB))
	#plt.show()

	#points = punti dei muri
	points = []
	for y in xrange(0,im_bw.shape[1]):
		for x in xrange(im_bw.shape[0]):
			if im_bw[x, y] == (0):
				points.append([y,x])

	points = np.asarray(points)

	#distance transform
# 	distanceMap = ndimage.distance_transform_edt(im_bw)
# 	plt.title('8.distance map')
# 	plt.imshow(distanceMap)
# 	plt.show()
	#disegno distance transforme
	distanceMap = dsg.disegna_distance_transform(im_bw, filepath = filepath)#plot

	#medial axis sulla distance transform
	skel, distance = medial_axis(distanceMap, return_distance=True)

	#elimino parte delle imprecisioni della skeletonization
	b3 = m.thin(skel, m.endpoints('homotopic'), 15)

	#elimino i punti isolati del medial axis, sono rumore
	for riga in xrange(b3.shape[0]):
		for col in xrange(b3.shape[1]):
			if b3[riga][col]==True and isolato(b3,riga,col):
				b3[riga][col]=False

	#disegno medial axis
# 	plt.title('9.medial axis')
# 	plt.plot(points[:,0],points[:,1],'.')			
# 	plt.imshow(b3,cmap='Greys')
# 	plt.show()
	#disegno medial axis
	dsg.disegna_medial_axis(points, b3, filepath = filepath)

	punti_medial = []
	#salvo in una lista i punti che fanno parte del medial axis
	for riga in xrange(b3.shape[0]):
		for col in xrange(b3.shape[1]):
			if (b3[riga][col]==True):
				punti_medial.append((col,riga))
	punti_medial = np.asarray(punti_medial)
	flip_vertici(punti_medial,b3.shape[0]-1)

	return punti_medial
Beispiel #3
0
    def process(self, im):
        #single pixel restructure element
        elem = np.array([[0, 0, 0], [0, 1, 0], [0, 0, 0]])

        print "starting img process.. binarizing"
        b1 = im > 205  #binarize
        print "removing single pixels"
        #remove single pixels
        singpix = mahotas.morph.hitmiss(b1, elem)
        b1 = (b1 - singpix) > 0
        print "closing holes"
        b1 = m.close_holes(b1)

        print "thinning"
        #b2 = m.thin(b1) #thin
        b2 = self.shitthin(b1)  #thin
        print "pruning"
        b3 = m.thin(b2, m.endpoints('homotopic'), 8)

        #remove single pixels
        singpix = mahotas.morph.hitmiss(b3, elem)
        b3 = b3 - singpix
        b3 = b3 > 0
        struct = np.ndarray((4, 3, 3), dtype=np.uint8)
        struct[0, :, :] = [[1, 2, 1], [0, 1, 0], [0, 1, 0]]
        for i in range(1, 4):
            print "gen %i structure.." % (i)
            struct[i, :, :] = np.rot90(struct[0], i)

        #struct = struct == 1
        print "using struct for branch summing:"
        print struct

        b4 = np.zeros((301, 398), dtype=bool)

        for i in range(0, 4):
            b4 = b4 | mahotas.morph.hitmiss(b3, struct[i])
        b4 = b4 > 0

        imgout = m.overlay(b1, b2, b4)
        mahotas.imsave("thresh.png", imgout)
        return b4
    def process(self, im):
        # single pixel restructure element
        elem = np.array([[0, 0, 0], [0, 1, 0], [0, 0, 0]])

        print "starting img process.. binarizing"
        b1 = im > 205  # binarize
        print "removing single pixels"
        # remove single pixels
        singpix = mahotas.morph.hitmiss(b1, elem)
        b1 = (b1 - singpix) > 0
        print "closing holes"
        b1 = m.close_holes(b1)

        print "thinning"
        # b2 = m.thin(b1) #thin
        b2 = self.shitthin(b1)  # thin
        print "pruning"
        b3 = m.thin(b2, m.endpoints("homotopic"), 8)

        # remove single pixels
        singpix = mahotas.morph.hitmiss(b3, elem)
        b3 = b3 - singpix
        b3 = b3 > 0
        struct = np.ndarray((4, 3, 3), dtype=np.uint8)
        struct[0, :, :] = [[1, 2, 1], [0, 1, 0], [0, 1, 0]]
        for i in range(1, 4):
            print "gen %i structure.." % (i)
            struct[i, :, :] = np.rot90(struct[0], i)

            # struct = struct == 1
        print "using struct for branch summing:"
        print struct

        b4 = np.zeros((301, 398), dtype=bool)

        for i in range(0, 4):
            b4 = b4 | mahotas.morph.hitmiss(b3, struct[i])
        b4 = b4 > 0

        imgout = m.overlay(b1, b2, b4)
        mahotas.imsave("thresh.png", imgout)
        return b4
Beispiel #5
0
def critical_points(metricMap):
    '''
	ottengo i critical points dal medial axis
	'''

    if cv2.__version__[0] == '3':
        flag = cv2.IMREAD_GRAYSCALE
    elif cv2.__version__[0] == '2':
        flag = cv2.CV_LOAD_IMAGE_GRAYSCALE
    else:
        raise EnvironmentError(
            'Opencv Version Error. You should have OpenCv 2.* or 3.*')

    im_gray = cv2.imread(metricMap, flag)
    #leggo l'immagine e la trasformo in 0 o 255
    (thresh, im_bw) = cv2.threshold(im_gray, 240, 255, cv2.THRESH_BINARY_INV)

    (th, im_bw) = cv2.threshold(im_bw, 240, 255, cv2.THRESH_BINARY_INV)

    #points = punti dei muri
    points = []
    for y in xrange(0, im_bw.shape[1]):
        for x in xrange(im_bw.shape[0]):
            if im_bw[x, y] == (0):
                points.append([y, x])

    points = np.asarray(points)

    #distance map
    distanceMap = get_distance_transforme(im_bw)

    #medial axis sulla distance transform
    skel, distance = medial_axis(distanceMap, return_distance=True)

    #elimino parte delle imprecisioni della skeletonization
    #b3 = m.thin(skel, m.endpoints('homotopic'), 15)
    b3 = m.thin(skel, m.endpoints('homotopic'), 500)

    #---
    import copy
    b4 = copy.copy(b3)
    #ottengo solo critical points
    #critical_points = []
    for riga in xrange(b4.shape[0]):
        for col in xrange(b4.shape[1]):
            if b4[riga][col] == True:
                #controllo se in un intorno di quel punto c'è una frontiera
                #creo intorno del pixel
                start_x = riga - 17  #15
                end_x = riga + 17
                start_y = col - 17
                end_y = col + 17
                count = 0
                for x in xrange(start_x, end_x):
                    for y in xrange(start_y, end_y):
                        if im_bw[x, y] <= (
                                200
                        ):  #se almeno una componente rgb di un pixel nell'introno del pixel cha fa parte del medial axis e' un pixel della frontiera
                            count += 1
                if count <= 5:
                    b4[riga][col] = False
                # else:
# 					#è un critical_points
# 					critical_points.append([riga, col])

    critical_points = []
    #salvo in una lista i critical points che fanno parte del medial axis
    for riga in xrange(b4.shape[0]):
        for col in xrange(b4.shape[1]):
            if (b4[riga][col] == True):
                critical_points.append((col, riga))
    critical_points = np.asarray(critical_points)
    flip_vertici(critical_points, b4.shape[0] - 1)
    #------

    return distanceMap, points, b3, b4, critical_points
Beispiel #6
0
import pymorph as m
import mahotas
from numpy import where, reshape

image = mahotas.imread('B.png') # Load image

b1 = image[:,:,0] < 100 # Make a binary image from the thresholded red channel
b2 = m.erode(b1, m.sedisk(4)) # Erode to enhance contrast of the bridge
b3 = m.open(b2,m.sedisk(4)) # Remove the bridge
b4 = b2-b3 # Bridge plus small noise
b5 = m.areaopen(b4,1000) # Remove small areas leaving only a thinned bridge
b6 = m.dilate(b3)*b5 # Extend the non-bridge area slightly and get intersection with the bridge.

#b6 is image of end of bridge, now find single points
b7 = m.thin(b6, m.endpoints('homotopic')) # Narrow regions to single points.
labelled = m.label(b7) # Label endpoints.

x1, y1 = reshape(where(labelled == 1),(1,2))[0]
x2, y2 = reshape(where(labelled == 2),(1,2))[0]

outputimage = m.overlay(b1, m.dilate(b7,m.sedisk(5)))
mahotas.imsave('output.png', outputimage)
Beispiel #7
0
def medial_points(thresh):
    #leggo l'immagine e la trasformo in 0 o 255

    (th, im_bw) = cv2.threshold(thresh, 240, 255, cv2.THRESH_BINARY_INV)
    #plt.imshow(cv2.cvtColor(im_bw,cv2.COLOR_GRAY2RGB))
    #plt.show()

    #points = punti dei muri
    points = []
    for y in xrange(0, im_bw.shape[1]):
        for x in xrange(im_bw.shape[0]):
            if im_bw[x, y] == (0):
                points.append([y, x])

    points = np.asarray(points)

    #distance transform
    # 	distanceMap = ndimage.distance_transform_edt(im_bw)
    # 	plt.title('8.distance map')
    # 	plt.imshow(distanceMap)
    # 	plt.show()
    #disegno distance transforme

    #distanceMap = dsg.disegna_distance_transform(im_bw, filepath = filepath)#plot
    distanceMap = get_distance_transforme(im_bw)

    #medial axis sulla distance transform
    skel, distance = medial_axis(distanceMap, return_distance=True)

    #elimino parte delle imprecisioni della skeletonization
    #b3 = m.thin(skel, m.endpoints('homotopic'), 15)
    b3 = m.thin(skel, m.endpoints('homotopic'), 500)
    '''
	#------
	import copy
	b4 = copy.copy(b3)
	#ottengo solo critical points
	#critical_points = []
	for riga in xrange(b4.shape[0]):
		for col in xrange(b4.shape[1]):
			if b4[riga][col]==True:
				#controllo se in un intorno di quel punto c'è una frontiera
				#creo intorno del pixel 
				start_x = riga-17 #15
				end_x = riga+17
				start_y = col-17
				end_y = col+17
				count = 0
				for x in xrange(start_x,end_x):
					for y in xrange(start_y, end_y):
						if im_bw[x, y] <= (200): #se almeno una componente rgb di un pixel nell'introno del pixel cha fa parte del medial axis e' un pixel della frontiera
							count+=1
				if count <= 5:
					b4[riga][col]=False
				# else:
# 					#è un critical_points
# 					critical_points.append([riga, col])

	critical_points = []
	#salvo in una lista i critical points che fanno parte del medial axis
	for riga in xrange(b4.shape[0]):
		for col in xrange(b4.shape[1]):
			if (b4[riga][col]==True):
				critical_points.append((col,riga))
	critical_points = np.asarray(critical_points)
	flip_vertici(critical_points,b4.shape[0]-1)
	#------
	'''

    #elimino i punti isolati del medial axis, sono rumore
    for riga in xrange(b3.shape[0]):
        for col in xrange(b3.shape[1]):
            if b3[riga][col] == True and isolato(b3, riga, col):
                b3[riga][col] = False

    #disegno medial axis


# 	plt.title('9.medial axis')
# 	plt.plot(points[:,0],points[:,1],'.')
# 	plt.imshow(b3,cmap='Greys')
# 	plt.show()
#disegno medial axis
#dsg.disegna_medial_axis(points, b3, filepath = filepath)#quiiiiiiiii

    punti_medial = []
    #salvo in una lista i punti che fanno parte del medial axis
    for riga in xrange(b3.shape[0]):
        for col in xrange(b3.shape[1]):
            if (b3[riga][col] == True):
                punti_medial.append((col, riga))
    punti_medial = np.asarray(punti_medial)
    flip_vertici(punti_medial, b3.shape[0] - 1)

    return punti_medial, distanceMap, points, b3, distance