I have an image of mathematical formula and I need to parse symbols of it, but also save where they were (center of each symbol). For example image like this needs to be transformed into 15 different images 75x75, 1 per each symbol.
What I have tried is:
Transform to gray and then binary: pixels close to white(> 250) becomes 255 and other become 0
Use BNF to find all components and then transform them into images (with rescaling and everything else)
But I am sure it is not the best way to do it, maybe there is standard approach for this problem exist?
Here is my code:
class Parser:
def init(self, targetSizes=(75, 75), binaryThreshold=cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU,
scaleFully=False, scaleFullyRate=0.9, whiteThreshold=249, blackThreshold=0,
rescalingInterpolation=cv2.INTER_AREA, pixelsInImageThreshold=20,
rescaleOriginalImage=True, rescaleToAtLeast=200, rescaleToAtMaximum=1000):
self.targetWidth = targetSizes[0]
self.targetHeight = targetSizes[1]
self.binaryThreshold = binaryThreshold
self.scaleFully = scaleFully
self.scaleFullyRate = scaleFullyRate
self.whiteThreshold = whiteThreshold
self.blackThreshold = blackThreshold
self.rescalingInterpolation = rescalingInterpolation
self.pixelsInIMageThreshold = pixelsInImageThreshold
self.rescaleOriginalImage = rescaleOriginalImage
self.rescaleOriginalMin = rescaleToAtLeast
self.rescaleOriginalMax = rescaleToAtMaximum
self.parseMode = 1
def _imageToBinary(self, image, zeroValueTrash=0, oneValueTrash=253):
grayImage = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
ret, binary = cv2.threshold(grayImage, self.blackThreshold, self.whiteThreshold, self.binaryThreshold)
# cv2.imwrite("Test.png", binary)
return binary
def _BNF(self, binaryImage):
Q = MyQueue()
whitePixels = []
gg = 0
for i in range(len(binaryImage)):
for j in range(len(binaryImage[i])):
if binaryImage[i][j] > self.whiteThreshold-1:
Q.put((i, j))
binaryImage[i][j] = 0
obj = []
gg += 1
while not Q.empty():
i, j = Q.pop()
obj.append((i, j))
if i + 1 < len(binaryImage) and binaryImage[i + 1][j] != 0:
Q.put((i + 1, j))
binaryImage[i + 1][j] = 0
if j - 1 > 0 and binaryImage[i][j - 1] != 0:
Q.put((i, j - 1))
binaryImage[i][j - 1] = 0
if i - 1 > 0 and binaryImage[i - 1][j] != 0:
Q.put((i - 1, j))
binaryImage[i - 1][j] = 0
if j + 1 < len(binaryImage[i]) and binaryImage[i][j + 1] != 0:
Q.put((i, j + 1))
binaryImage[i][j + 1] = 0
if self.parseMode == 1:
if i + 1 < len(binaryImage) and j+1 < len(binaryImage[i+1]) and binaryImage[i + 1][j+1] != 0:
Q.put((i + 1, j+1))
binaryImage[i + 1][j+1] = 0
if i + 1 < len(binaryImage) and j - 1 > 0 and binaryImage[i + 1][j-1] != 0:
Q.put((i + 1, j-1))
binaryImage[i + 1][j-1] = 0
if i - 1 > 0 and j - 1 > 0 and binaryImage[i - 1][j - 1] != 0:
Q.put((i - 1, j - 1))
binaryImage[i - 1][j - 1] = 0
if i - 1 > 0 and j + 1 < len(binaryImage[i-1]) and binaryImage[i - 1][j + 1] != 0:
Q.put((i - 1, j + 1))
binaryImage[i - 1][j + 1] = 0
cv2.imwrite("tmp/{}.png".format(gg), binaryImage)
whitePixels.append(obj)
return whitePixels
def parseImage(self, image_path: str) -> list:
image = cv2.imread(image_path)
if self.rescaleOriginalImage:
image = self.scaleOriginal(image)
binary = self._imageToBinary(image)
whitePixels = self._BNF(binary)
return whitePixels
def isScaleable(self, imageShape):
return True
def scaleOriginal(self, image: np.ndarray):
# To be created
return image
#staticmethod
def _getImageAndCenterFromDotes(Dotes, originalImage=None):
i_mx, j_mx = -1, -1
i_mn, j_mn = 100500, 100500 # just big numbers
# finding upper right and lower left corner of image
for el in Dotes:
i, j = el
if i_mx < i:
i_mx = i
if j_mx < j:
j_mx = j
if j_mn > j:
j_mn = j
if i_mn > i:
i_mn = i
# updating image center
imageCenter = Point((i_mx + i_mn) // 2, (j_mx + j_mn) // 2)
# finding out size of image
width, height = i_mx - i_mn + 1, j_mx - j_mn + 1
image = np.zeros((width, height)) if originalImage is None else np.zeros((width, height, 3))
# recreating image from dotes
if originalImage is not None:
for el in Dotes:
i, j = el
image[i - i_mn][j - j_mn] = originalImage[i][j]
else:
for el in Dotes:
i, j = el
image[i - i_mn][j - j_mn] = 255
return image, imageCenter
def scaleParsedImage(self, image: np.ndarray):
"""
:param image: np.ndarray
:return: scaledImage np.ndarray
"""
width, height = image.shape if len(image.shape) == 2 else image.shape[0], image.shape[1]
newWidth = self.targetWidth if width > self.targetHeight else width
newHeight = self.targetHeight if height > self.targetHeight else height
if self.scaleFully and newHeight < self.targetHeight * self.scaleFullyRate and newWidth * self.scaleFullyRate:
scaleRate = min((self.targetWidth * self.scaleFullyRate / newWidth), (
self.targetHeight * self.scaleFullyRate / newHeight))
newWidth = math.ceil(newWidth * scaleRate)
newHeight = math.ceil(newHeight * scaleRate)
scaled = cv2.resize(image, (newHeight, newWidth), interpolation=self.rescalingInterpolation)
# pasting our scaled image in the middle
x_add, y_add = (self.targetWidth - newWidth) // 2, (self.targetHeight - newHeight) // 2
resized = np.zeros((self.targetWidth, self.targetHeight)) if len(image.shape) == 2 else np.zeros((self.targetWidth, self.targetHeight, 3))
for x in range(newWidth):
for y in range(newHeight):
resized[x + x_add][y + y_add] = scaled[x][y]
return resized
def parseAndConvert(self, image_name: str) -> list:
imagesInDotes = self.parseImage(image_name)
original = 255 - cv2.imread(image_name)
images = []
for dotes in imagesInDotes:
image = self._getImageAndCenterFromDotes(dotes, original)
images.append([self.scaleParsedImage(image[0]), image[1]])
rawImages = []
for image, center in images:
rawImages.append(RawImage(image, center))
return rawImages
Have a look at the (imho not all too intuitively named) function cv.findContours():
https://docs.opencv.org/3.4/d4/d73/tutorial_py_contours_begin.html
It should do most things that you are doing by hand right now out of the box, which is extracting and measuring binary objects.
If you encouter problems where a single symbol is made up of several objects (like i, % or "), look into the morphological operations to merge them into a single one: erode(), dilate(), or open and close via morphologyEx() (Tutorial here: https://docs.opencv.org/4.x/d9/d61/tutorial_py_morphological_ops.html).
Related
I am trying to calculate RSI using simple functions.
The general formula for it is:
RSI = 100/(1+RS), where RS = Exponential Moving Average of gains / -||- of losses.
Here is what I am getting:
enter image description here
Here it is how should it look like:
enter image description here
I have everything double checked or even triple checked, but I can't find any mistake.
Thus I need your help, I know that the question is very simple though I need some help, I have no idea where I have made the mistake.
The general idea of RSI is that it should be low where the price is "low" and high, where the price is high, and generally no matter what I try I have it upside down.
def EMA(close_price_arr, n):
a = (2/n + 1)
EMA_n = np.empty((1, len(close_price_arr)))
for i in range(len(close_price_arr)):
if i < n:
# creating NaN values where it is impossible to calculate EMA to drop it later after connecting the whole database
EMA_n[0, i] = 'NaN'
if i >= n:
# Calaculating nominator and denominator of EMA
for j in range(n):
nominator_ema += close_price_arr[i - j] * a**(j)
denominator_ema += a**(j)
EMA_n[0, i] = nominator_ema / denominator_ema
nominator_ema = 0
denominator_ema = 0
return EMA_n
def gains(close_price_arr):
gain_arr = np.empty((len(close_price_arr) - 1))
for i in range(len(close_price_arr)):
if i == 0:
pass
if i >= 1:
if close_price_arr[i] > close_price_arr[i - 1]:
gain_arr[i - 1] = (close_price_arr[i] - close_price_arr[i-1])
else:
gain_arr[i - 1] = 0
return gain_arr
def losses(close_price_arr):
loss_arr = np.empty((len(close_price_arr) - 1))
for i in range(len(close_price_arr)):
if i == 0:
pass
if i >= 1:
if close_price_arr[i] < close_price_arr[i - 1]:
loss_arr[i - 1] = abs(close_price_arr[i] - close_price_arr[i - 1])
else:
loss_arr[i - 1] = 0
return loss_arr
def RSI(gain_arr, loss_arr, n):
EMA_u = EMA(gain_arr, n)
EMA_d = EMA(loss_arr, n)
EMA_diff = EMA_u / EMA_d
x,y = EMA_diff.shape
print(x, y)
RSI_n = np.empty((1, y))
for i in range(y):
if EMA_diff[0, i] == 'NaN':
RSI_n[0, i] = 'NaN'
print(i)
else:
RSI_n[0, i] = 100 / (1 + EMA_diff[0, i])
return RSI_n
#contextmanager
def show_complete_array():
oldoptions = np.get_printoptions()
np.set_printoptions(threshold=np.inf)
try:
yield
finally:
np.set_printoptions(**oldoptions)
np.set_printoptions(linewidth=3000)
pd.set_option('display.max_columns', None)
# Specyfying root folder, file folder and file
FILE = 'TVC_SILVER, 5.csv'
FOLDER = 'src'
PROJECT_ROOT_DIR = '.'
csv_path = os.path.join(PROJECT_ROOT_DIR, FOLDER, FILE)
# reading csv
price_data = pd.read_csv(csv_path, delimiter=',')
price_data_copy = price_data.copy()
price_data_nodate = price_data.copy().drop('time', axis=1)
price_data_np = price_data_nodate.to_numpy(dtype='float32')
close_price = price_data_np[:, 3]
EMA15 = EMA(close_price_arr=close_price, n=15)
EMA55 = EMA(close_price_arr=close_price, n=55)
gain = gains(close_price_arr=close_price)
loss = losses(close_price_arr=close_price)
RSI14 = RSI(gain_arr=gain, loss_arr=loss, n=14)
Try this:
"""dataset is a dataframe"""
def RSI(dataset, n=14):
delta = dataset.diff()
dUp, dDown = delta.copy(), delta.copy()
dUp[dUp < 0] = 0
dDown[dDown > 0] = 0
RolUp = pd.Series(dUp).rolling(window=n).mean()
RolDown = pd.Series(dDown).rolling(window=n).mean().abs()
RS = RolUp / RolDown
rsi= 100.0 - (100.0 / (1.0 + RS))
return rsi
I want to draw parallel line to given X,Y coordinate below code helps to draw ,
import numpy as np
import matplotlib.pyplot as plt
x = [187, 879, 722, 322]
y = [341, 344, 112, 112]
newX = []
newY = []
def findIntesection(p1x, p1y, p2x, p2y, p3x,p3y, p4x, p4y):
dx12 = p2x - p1x
dy12 = p2y - p1y
dx34 = p4x - p3x
dy34 = p4y - p3y
denominator = (dy12*dx34-dx12*dy34)
t1 = ((p1x - p3x) * dy34 + (p3y - p1y) * dx34)/ denominator
t2 = ((p3x - p1x) * dy12 + (p1y - p3y) * dx12)/ -denominator;
intersectX = p1x + dx12 * t1
intersectY = p1y + dy12 * t1
if (t1 < 0): t1 = 0
elif (t1 > 1): t1 = 1
if (t2 < 0): t2 = 0
elif (t2 > 1): t2 = 1
return intersectX,intersectY
def normalizeVec(x,y):
distance = np.sqrt(x*x+y*y)
return x/distance, y/distance
def getEnlarged(oldX, oldY, offset):
num_points = len(oldX)
for j in range(num_points):
i = j - 1
if i < 0:
i += num_points
k = (j + 1) % num_points
vec1X = oldX[j] - oldX[i]
vec1Y = oldY[j] - oldY[i]
v1normX, v1normY = normalizeVec(vec1X,vec1Y)
v1normX *= offset
v1normY *= offset
n1X = -v1normY
n1Y = v1normX
pij1X = oldX[i] + n1X
pij1Y = oldY[i] + n1Y
pij2X = oldX[j] + n1X
pij2Y = oldY[j] + n1Y
vec2X = oldX[k] - oldX[j]
vec2Y = oldY[k] - oldY[j]
v2normX, v2normY = normalizeVec(vec2X,vec2Y)
v2normX *= offset
v2normY *= offset
n2X = -v2normY
n2Y = v2normX
pjk1X = oldX[j] + n2X
pjk1Y = oldY[j] + n2Y
pjk2X = oldX[k] + n2X
pjk2Y = oldY[k] + n2Y
intersectX,intersetY = findIntesection(pij1X,pij1Y,pij2X,pij2Y,pjk1X,pjk1Y,pjk2X,pjk2Y)
#print(intersectX,intersetY)
newX.append(intersectX)
newY.append(intersetY)
getEnlarged(x, y, 20)
plt.plot(x, y)
plt.plot(newX, newY)
plt.show()
This gives result as below
Here it is giving good result by drawing parallel line to each line of our trapezoidal shaped , but i want it to be a closed shape in place of open shape
i want to join the 1st and last coordinate so that it should form a closed shape. Any help will be appreciated .
Using approach from here
outer_ccw parameters combines vertex order and desired offset direction. For CCW order and outer polygon it is 1, for inner polygon it should be -1.
def makeOffsetPoly(oldX, oldY, offset, outer_ccw = 1):
num_points = len(oldX)
for curr in range(num_points):
prev = (curr + num_points - 1) % num_points
next = (curr + 1) % num_points
vnX = oldX[next] - oldX[curr]
vnY = oldY[next] - oldY[curr]
vnnX, vnnY = normalizeVec(vnX,vnY)
nnnX = vnnY
nnnY = -vnnX
vpX = oldX[curr] - oldX[prev]
vpY = oldY[curr] - oldY[prev]
vpnX, vpnY = normalizeVec(vpX,vpY)
npnX = vpnY * outer_ccw
npnY = -vpnX * outer_ccw
bisX = (nnnX + npnX) * outer_ccw
bisY = (nnnY + npnY) * outer_ccw
bisnX, bisnY = normalizeVec(bisX, bisY)
bislen = offset / np.sqrt((1 + nnnX*npnX + nnnY*npnY)/2)
newX.append(oldX[curr] + bislen * bisnX)
newY.append(oldY[curr] + bislen * bisnY)
x = [0, 100, 60, 40]
y = [0, 0, 50, 50]
makeOffsetPoly(x, y, 20)
print(newX, newY)
>>>[-29.424478775259594, 129.4244787752596, 66.79706177729007, 33.202938222709925]
[-14.14213562373095, -14.14213562373095, 64.14213562373095, 64.14213562373095]
Just append the first coordinates to the end of your lists.
x.append(x[0])
y.append(y[0])
newX.append(newX[0])
newY.append(newY[0])
Place this right before you plot. Here's my output
I recently tried the new fingerprint feature extractor library by Utkarsh-Deshmukh (https://github.com/Utkarsh-Deshmukh/Fingerprint-Feature-Extraction) and it works like wonder. The problem is I need to extract terminations and bifurcations value from the library. I used this code that's included in the github link to get features bifurcations and terminations:
import fingerprint_feature_extractor
img = cv2.imread('image_path', 0)
FeaturesTerminations, FeaturesBifurcations = fingerprint_feature_extractor.extract_minutiae_features(img, showResult=True, spuriousMinutiaeThresh=10)
I tried using print() command to see what's inside FeaturesBifurcations and I can't understand what the output means.
print() command on FeaturesBifurcations
What I needed is values that looks like this where first and second column indicates xy coordinates, third column indicates orientations, and fourth column indicate type:
minutiaes bifurcations (marked with 1 in the last column) and terminations (marked with 0 in the last column) values extracted from fingerprint
I tried reading the classes in the library and I figure I could get those values (features locations, orientations, and type is explicitly stated in the library), but i do not know how to extract those values. This is what is inside the fingerprint-feature-extractor library:
import cv2
import numpy as np
import skimage.morphology
from skimage.morphology import convex_hull_image, erosion
from skimage.morphology import square
import math
class MinutiaeFeature(object):
def __init__(self, locX, locY, Orientation, Type):
self.locX = locX;
self.locY = locY;
self.Orientation = Orientation;
self.Type = Type;
class FingerprintFeatureExtractor(object):
def __init__(self):
self._mask = []
self._skel = []
self.minutiaeTerm = []
self.minutiaeBif = []
def __skeletonize(self, img):
img = np.uint8(img > 128)
self._skel = skimage.morphology.skeletonize(img)
self._skel = np.uint8(self._skel) * 255
self._mask = img * 255
def __computeAngle(self, block, minutiaeType):
angle = []
(blkRows, blkCols) = np.shape(block);
CenterX, CenterY = (blkRows - 1) / 2, (blkCols - 1) / 2
if (minutiaeType.lower() == 'termination'):
sumVal = 0;
for i in range(blkRows):
for j in range(blkCols):
if ((i == 0 or i == blkRows - 1 or j == 0 or j == blkCols - 1) and block[i][j] != 0):
angle.append(-math.degrees(math.atan2(i - CenterY, j - CenterX)))
sumVal += 1
if (sumVal > 1):
angle.append(float('nan'))
return (angle)
elif (minutiaeType.lower() == 'bifurcation'):
(blkRows, blkCols) = np.shape(block);
CenterX, CenterY = (blkRows - 1) / 2, (blkCols - 1) / 2
angle = []
sumVal = 0;
for i in range(blkRows):
for j in range(blkCols):
if ((i == 0 or i == blkRows - 1 or j == 0 or j == blkCols - 1) and block[i][j] != 0):
angle.append(-math.degrees(math.atan2(i - CenterY, j - CenterX)))
sumVal += 1
if (sumVal != 3):
angle.append(float('nan'))
return (angle)
def __getTerminationBifurcation(self):
self._skel = self._skel == 255;
(rows, cols) = self._skel.shape;
self.minutiaeTerm = np.zeros(self._skel.shape);
self.minutiaeBif = np.zeros(self._skel.shape);
for i in range(1, rows - 1):
for j in range(1, cols - 1):
if (self._skel[i][j] == 1):
block = self._skel[i - 1:i + 2, j - 1:j + 2];
block_val = np.sum(block);
if (block_val == 2):
self.minutiaeTerm[i, j] = 1;
elif (block_val == 4):
self.minutiaeBif[i, j] = 1;
self._mask = convex_hull_image(self._mask > 0)
self._mask = erosion(self._mask, square(5)) # Structuing element for mask erosion = square(5)
self.minutiaeTerm = np.uint8(self._mask) * self.minutiaeTerm
def __removeSpuriousMinutiae(self, minutiaeList, img, thresh):
img = img * 0;
SpuriousMin = [];
numPoints = len(minutiaeList);
D = np.zeros((numPoints, numPoints))
for i in range(1,numPoints):
for j in range(0, i):
(X1,Y1) = minutiaeList[i]['centroid']
(X2,Y2) = minutiaeList[j]['centroid']
dist = np.sqrt((X2-X1)**2 + (Y2-Y1)**2);
D[i][j] = dist
if(dist < thresh):
SpuriousMin.append(i)
SpuriousMin.append(j)
SpuriousMin = np.unique(SpuriousMin)
for i in range(0,numPoints):
if(not i in SpuriousMin):
(X,Y) = np.int16(minutiaeList[i]['centroid']);
img[X,Y] = 1;
img = np.uint8(img);
return(img)
def __cleanMinutiae(self, img):
self.minutiaeTerm = skimage.measure.label(self.minutiaeTerm, connectivity=2);
RP = skimage.measure.regionprops(self.minutiaeTerm)
self.minutiaeTerm = self.__removeSpuriousMinutiae(RP, np.uint8(img), 10);
def __performFeatureExtraction(self):
FeaturesTerm = []
self.minutiaeTerm = skimage.measure.label(self.minutiaeTerm, connectivity=2);
RP = skimage.measure.regionprops(np.uint8(self.minutiaeTerm))
WindowSize = 2 # --> For Termination, the block size must can be 3x3, or 5x5. Hence the window selected is 1 or 2
FeaturesTerm = []
for num, i in enumerate(RP):
print(num)
(row, col) = np.int16(np.round(i['Centroid']))
block = self._skel[row - WindowSize:row + WindowSize + 1, col - WindowSize:col + WindowSize + 1]
angle = self.__computeAngle(block, 'Termination')
if(len(angle) == 1):
FeaturesTerm.append(MinutiaeFeature(row, col, angle, 'Termination'))
FeaturesBif = []
self.minutiaeBif = skimage.measure.label(self.minutiaeBif, connectivity=2);
RP = skimage.measure.regionprops(np.uint8(self.minutiaeBif))
WindowSize = 1 # --> For Bifurcation, the block size must be 3x3. Hence the window selected is 1
for i in RP:
(row, col) = np.int16(np.round(i['Centroid']))
block = self._skel[row - WindowSize:row + WindowSize + 1, col - WindowSize:col + WindowSize + 1]
angle = self.__computeAngle(block, 'Bifurcation')
if(len(angle) == 3):
FeaturesBif.append(MinutiaeFeature(row, col, angle, 'Bifurcation'))
return (FeaturesTerm, FeaturesBif)
def extractMinutiaeFeatures(self, img):
self.__skeletonize(img)
self.__getTerminationBifurcation()
self.__cleanMinutiae(img)
FeaturesTerm, FeaturesBif = self.__performFeatureExtraction()
return(FeaturesTerm, FeaturesBif)
def showResults(self):
BifLabel = skimage.measure.label(self.minutiaeBif, connectivity=2);
TermLabel = skimage.measure.label(self.minutiaeTerm, connectivity=2);
minutiaeBif = TermLabel * 0;
minutiaeTerm = BifLabel * 0;
(rows, cols) = self._skel.shape
DispImg = np.zeros((rows, cols, 3), np.uint8)
DispImg[:, :, 0] = 255*self._skel;
DispImg[:, :, 1] = 255*self._skel;
DispImg[:, :, 2] = 255*self._skel;
RP = skimage.measure.regionprops(BifLabel)
for idx, i in enumerate(RP):
(row, col) = np.int16(np.round(i['Centroid']))
minutiaeBif[row, col] = 1;
(rr, cc) = skimage.draw.circle_perimeter(row, col, 3);
skimage.draw.set_color(DispImg, (rr, cc), (255, 0, 0));
RP = skimage.measure.regionprops(TermLabel)
for idx, i in enumerate(RP):
(row, col) = np.int16(np.round(i['Centroid']))
minutiaeTerm[row, col] = 1;
(rr, cc) = skimage.draw.circle_perimeter(row, col, 3);
skimage.draw.set_color(DispImg, (rr, cc), (0, 0, 255));
cv2.imshow('a', DispImg);
cv2.waitKey(0)
def extract_minutiae_features(img, showResult=False):
feature_extractor = FingerprintFeatureExtractor()
FeaturesTerm, FeaturesBif = feature_extractor.extractMinutiaeFeatures(img)
if(showResult):
feature_extractor.showResults()
return(FeaturesTerm, FeaturesBif)
Is there a way to extract locations, orientations, and type float (and/or integer) values from this library? or is there a way or library to plot those lists to cartesian or polar coordinates?
I know this is not an ideal place for questions of this scope, but I'm not sure where else to ask this or how to break it down. I've been working on a function for the past couple weeks, that runs, but for it to be feasible for my purposes, I need to speed it up 200-300x.
I have an image array, where all pixels of similar color have been averaged and set to that average value. Then I have a 2D array of the same height and width, which labels each unique and non-contiguous feature of the image.
Using these I need to assess the size of each feature and its level of contrast to each of its neighbors. These values are used in an equation and if the output of that equation is below a certain threshold, that feature is merged with its most similar neighbor.
I've uploaded the image and the feature label array (printed with numpy.savetext()) to OneDrive and attached links
code:
def textureRemover(pix, labeledPix, ratio = 1.0):
numElements = numpy.amax(labeledPix)
maxSize = numpy.count_nonzero(labeledPix)
MAXIMUMCONTRAST = 443.405
for regionID in range(numElements):
start = time.clock()
regionID += 1
if regionID not in labeledPix:
continue
#print(regionID)
#print((regionID / numElements) * 100, '%')
neighborIDs = getNeighbors(labeledPix, regionID)
if 0 in neighborIDs:
neighborIDs.remove(0) #remove white value
regionMask = labeledPix == regionID
region = pix[regionMask]
size = numpy.count_nonzero(regionMask)
contrastMin = (ratio - (size / maxSize)) * MAXIMUMCONTRAST
regionMean = region.mean(axis = 0)
if len(neighborIDs) > 200:
contrast = numpy.zeros(labeledPix.shape)
contrast[labeledPix!=0] = numpy.sqrt(numpy.sum((regionMean - pix[labeledPix!=0])**2, axis = -1))
significantMask = (contrast < contrastMin)
significantContrasts = list(numpy.unique(contrast[significantMask]))
significantNeighbors = {}
for significantContrast in significantContrasts:
minContrast = min(significantContrasts)
if labeledPix[contrast == minContrast][0] in neighborIDs:
significantNeighbors[minContrast] = labeledPix[contrast == minContrast][0]
else:
significantContrasts.pop(significantContrasts.index(minContrast))
else:
significantNeighbors = {}
for neighborID in neighborIDs:
neighborMask = labeledPix == neighborID
neighbor = pix[neighborMask]
neighborMean = neighbor.mean(axis = 0)
contrast = numpy.sqrt(numpy.sum((regionMean - neighborMean)**2, axis = -1))
if contrast < contrastMin:
significantNeighbors[contrast] = neighborID
if significantNeighbors:
contrasts = significantNeighbors.keys()
minContrast = min(contrasts)
minNeighbor = significantNeighbors[minContrast]
neighborMask = labeledPix == minNeighbor
neighborSize = numpy.count_nonzero(neighborMask)
if neighborSize <= size:
labeledPix[neighborMask] = regionID
pix[neighborMask] = regionMean
else:
labeledPix[regionMask] = minNeighbor
pix[regionMask] = pix[neighborMask].mean(axis = 0)
print(time.clock() - start)
return pix
pix
labeledPix
I know I'm asking for a lot of help, but I've been stuck on this for a few weeks and am unsure what else I can do. Any help will be greatly appreciated!
Here is an optimized version of most of your logic (I underestimated the amount of work that would be...). I skipped the >200 branch and am using fake data because I couldn't access your link. When I switch off your >200 branch your and my code appear to give the same result but mine is quite a bit faster on the fake example.
Sample output:
original
26.056154000000003
optimized
0.763613000000003
equal
True
Code:
import numpy as np
from numpy.lib.stride_tricks import as_strided
def mockdata(m, n, k):
colors = np.random.random((m, n, 3))
i, j = np.ogrid[:m, :n]
labels = np.round(k*k * (np.sin(0.05 * i) + np.sin(0.05 * j)**2)).astype(int) % k
return colors, labels
DIAG_NEIGHBORS = True
MAXIMUMCONTRAST = 443.405
def textureRemover2(pix, labeledPix, ratio=1.0):
start = time.clock()
pix, labeledPix = pix.copy(), labeledPix.copy()
pixf, labeledPixf = pix.reshape(-1, 3), labeledPix.ravel()
m, n = labeledPix.shape
s, t = labeledPix.strides
# find all sizes in O(n)
sizes = np.bincount(labeledPixf)
n_ids = len(sizes)
# make index for quick access to labeled areas
lblidx = np.split(np.argsort(labeledPixf), np.cumsum(sizes[:-1]))
lblidx[0] = None
# find all mean colors in O(n)
regionMeans = np.transpose([np.bincount(labeledPix.ravel(), px)
/ np.maximum(sizes, 1)
for px in pix.reshape(-1, 3).T])
# find all neighbors in O(n)
horz = set(frozenset(p) for bl in as_strided(labeledPix, (m,n-1,2), (s,t,t))
for p in bl)
vert = set(frozenset(p) for bl in as_strided(labeledPix, (m-1,n,2), (s,t,s))
for p in bl)
nb = horz|vert
if DIAG_NEIGHBORS:
dwnrgt = set(frozenset(p) for bl in as_strided(
labeledPix, (m-1,n-1,2), (s,t,s+t)) for p in bl)
dwnlft = set(frozenset(p) for bl in as_strided(
labeledPix[::-1], (m-1,n-1,2), (-s,t,t-s)) for p in bl)
nb = nb|dwnrgt|dwnlft
nb = {p for p in nb if len(p) == 2 and not 0 in p}
nb_dict = {}
for a, b in nb:
nb_dict.setdefault(a, set()).add(b)
nb_dict.setdefault(b, set()).add(a)
maxSize = labeledPix.size - sizes[0]
for id_ in range(1, n_ids):
nbs = list(nb_dict.get(id_, set()))
if not nbs:
continue
d = regionMeans[id_] - regionMeans[nbs]
d = np.einsum('ij,ij->i', d, d)
mnd = np.argmin(d)
if d[mnd] < ((ratio - sizes[id_]/maxSize) * MAXIMUMCONTRAST)**2:
mn = nbs[mnd]
lrg, sml = (id_, mn) if sizes[id_] >= sizes[mn] else (mn, id_)
sizes[lrg], sizes[sml] = sizes[lrg] + sizes[sml], 0
for nb in nb_dict[sml]:
nb_dict[nb].remove(sml)
nb_dict[nb].add(lrg)
nb_dict[lrg].update(nb_dict[sml])
nb_dict[lrg].remove(lrg)
nb_dict[sml] = set()
pixf[lblidx[sml]] = regionMeans[lrg]
labeledPixf[lblidx[sml]] = lrg
lblidx[lrg], lblidx[sml] = np.r_[lblidx[lrg],lblidx[sml]], None
print(time.clock() - start)
return pix
from scipy.ndimage.morphology import binary_dilation
import time
STRUCTEL = np.ones((3,3), int) if DIAG_NEIGHBORS else np.array([[0,1,0],[1,1,1],[0,1,0]], int)
def getNeighbors(labeledPix, regionID):
nb = set(labeledPix[binary_dilation(labeledPix == regionID, structure=STRUCTEL)])
nb.remove(regionID)
return sorted(nb)
numpy = np
def textureRemover(pix, labeledPix, ratio = 1.0):
pix, labeledPix = pix.copy(), labeledPix.copy()
numElements = numpy.amax(labeledPix)
maxSize = numpy.count_nonzero(labeledPix)
MAXIMUMCONTRAST = 443.405
start = time.clock()
for regionID in range(numElements):
regionID += 1
if regionID not in labeledPix:
continue
#print(regionID)
#print((regionID / numElements) * 100, '%')
neighborIDs = getNeighbors(labeledPix, regionID)
if 0 in neighborIDs:
neighborIDs.remove(0) #remove white value
regionMask = labeledPix == regionID
region = pix[regionMask]
size = numpy.count_nonzero(regionMask)
contrastMin = (ratio - (size / maxSize)) * MAXIMUMCONTRAST
regionMean = region.mean(axis = 0)
if len(neighborIDs) > 20000:
contrast = numpy.zeros(labeledPix.shape)
contrast[labeledPix!=0] = numpy.sqrt(numpy.sum((regionMean - pix[labeledPix!=0])**2, axis = -1))
significantMask = (contrast < contrastMin)
significantContrasts = list(numpy.unique(contrast[significantMask]))
significantNeighbors = {}
for significantContrast in significantContrasts:
minContrast = min(significantContrasts)
if labeledPix[contrast == minContrast][0] in neighborIDs:
significantNeighbors[minContrast] = labeledPix[contrast == minContrast][0]
else:
significantContrasts.pop(significantContrasts.index(minContrast))
else:
significantNeighbors = {}
for neighborID in neighborIDs:
neighborMask = labeledPix == neighborID
neighbor = pix[neighborMask]
neighborMean = neighbor.mean(axis = 0)
contrast = numpy.sqrt(numpy.sum((regionMean - neighborMean)**2, axis = -1))
if contrast < contrastMin:
significantNeighbors[contrast] = neighborID
if significantNeighbors:
contrasts = significantNeighbors.keys()
minContrast = min(contrasts)
minNeighbor = significantNeighbors[minContrast]
neighborMask = labeledPix == minNeighbor
neighborSize = numpy.count_nonzero(neighborMask)
if neighborSize <= size:
labeledPix[neighborMask] = regionID
pix[neighborMask] = regionMean
else:
labeledPix[regionMask] = minNeighbor
pix[regionMask] = pix[neighborMask].mean(axis = 0)
print(time.clock() - start)
return pix
data = mockdata(200, 200, 1000)
print('original')
res0 = textureRemover(*data)
print('optimized')
res2 = textureRemover2(*data)
print('equal')
print(np.allclose(res0, res2))
I am trying to triangulate a bitmap (to produce levels for my 2d game), and I am stuck. I am using the Triangle library by Jonathan Shewchuk using this wrapper.
I start with an image,
then I detect edges and determine which vertices are holes. I picked every fourth for triangulation,
then I passed those points to triangulation, but I end up with something like this
where my hole has disappeared. What am I doing wrong?
Also, why am i getting somewhat convex hull instead of triangulated polygon?
Here is my code so far:
#here i am loading all data, that i will use later on but i had to insert that, just in case
mapfg = glob(path.join(pathtomapfolder, "Foreground.png"))[0] #Getting map foreground image
mapob = glob(path.join(pathtomapfolder, "Obstacles.png"))[0] #Getting map file
mappr = glob(path.join(pathtomapfolder, "Properties.txt"))[0] #Getting map info file
self.mapprops = [mapob, mapfg, mappr]
#getting ground and obstacles
obsbitmap = Image.open(self.mapprops[0])
lockBitmap = obsbitmap.load()
compareClr = (0, 0, 0)
for y in xrange(obsbitmap.size[1]):
tmp = []
for x in xrange(obsbitmap.size[0]):
if lockBitmap[x, y][0] == compareClr[0] and lockBitmap[x, y][6] == compareClr[1] and lockBitmap[x, y][7] == compareClr[2]:
tmp.append(1)
else:
tmp.append(0)
self.obs.append(tmp)
#detecting edges
for y in xrange(len(self.obs)):
tmphit = []
for x in xrange(len(self.obs[0])):
if (self.obs[y][x] == 0 and (self.obs[MinMax.NoOver(y - 1, len(self.obs) - 1, 0)][x] == 1 or self.obs[y][MinMax.NoOver(x - 1, len(self.obs[0]) - 1, 0)] == 1 or self.obs[y][MinMax.NoOver(x + 1, len(self.obs[0]) - 1, 0)] == 1 or self.obs[MinMax.NoOver(y + 1, len(self.obs) - 1, 0)][x] == 1)) or (self.obs[y][x] == 1 and (MinMax.WillOver(y - 1, len(self.obs) - 1, 0) or MinMax.WillOver(x - 1, len(self.obs[0]) - 1, 0) or MinMax.WillOver(x + 1, len(self.obs[0]) - 1, 0) or MinMax.WillOver(y + 1, len(self.obs) - 1, 0))):
tmphit.append(True)
else:
tmphit.append(False)
self.hit.append(tmphit)
#here it starts, first of all i search for vertice, then go CW or CCW and get all vertices from edge of one polygon, i also detect, whether it is hole or not and to which polygon is related to.
xcirc = ycirc = 0
coords = []
coordvalues = []
parentid = []
self.allverts = [coords, coordvalues, parentid]
polyID = 0
for y in xrange(len(self.obs)):
for x in xrange(len(self.obs[0])):
if self.hit[y][x] and not (x, y) in self.allverts[0]:
left = []
right = []
up = []
down = []
numobjects = numholes = 0
type = ""
parentid = -1
for v in xrange(len(self.allverts[0])):
if self.allverts[0][v][8] == y and self.allverts[0][v][0] < x: left.append(self.allverts[1][v])
if self.allverts[0][v][9] == y and self.allverts[0][v][0] > x: right.append(self.allverts[1][v])
if self.allverts[0][v][0] == x and self.allverts[0][v][10] < y: up.append(self.allverts[1][v])
if self.allverts[0][v][0] == x and self.allverts[0][v][11] > y: down.append(self.allverts[1][v])
for id in xrange(polyID):
if ("not hole", id) in left and ("not hole", id) in right and ("not hole", id) in up and ("not hole", id) in down:
numobjects += 1
parentid = id
elif ("hole", id) in left and ("hole", id) in right and ("hole", id) in up and ("hole", id) in down:
numholes += 1
if numobjects == 0 or numobjects == numholes: type = "not hole"
elif numobjects > numholes: type = "hole"
found = False
lastangle = -90
self.allverts[0].append((x, y))
self.allverts[1].append((type, polyID))
self.allverts[2].append(parentid)
v = 1
while not found:
angle = MinMax.Overflow(lastangle - 45, 180, -179)
lastangle = angle
xcirc = int(round(math.cos((math.pi / 180) * angle)))
ycirc = int(round(math.sin((math.pi / 180) * angle)))
if self.hit[MinMax.NoOver(self.allverts[0][-1][12] + ycirc, len(self.hit) - 1, 0)][MinMax.NoOver(self.allverts[0][-1][0] + xcirc, len(self.hit[0]) - 1, 0)] and (MinMax.WontOver(self.allverts[0][-1][13] + ycirc, len(self.hit) - 1, 0) and MinMax.WontOver(self.allverts[0][-1][0] + xcirc, len(self.hit[0]) - 1, 0)):
if not (self.allverts[0][-1][0] + xcirc, self.allverts[0][-1][14] + ycirc) in self.allverts[0]:
self.allverts[0].append((self.allverts[0][-1][0] + xcirc, self.allverts[0][-1][15] + ycirc))
self.allverts[1].append((type, polyID))
self.allverts[2].append(parentid)
v += 1
else:
#self.allverts.append((self.allverts[-1][0] + xcirc, self.allverts[-1][16] + ycirc))
found = True
if v < 4:
polyID -= 1
for d in xrange(v):
del self.allverts[0][-1]
del self.allverts[1][-1]
del self.allverts[2][-1]
lastangle = MinMax.Overflow(lastangle + 135, 180, -179)
polyID += 1
# now i have to convert that data structure to something i can pass to triangulate function
objects = []
objectpoints = []
idtoindexobj = []
holes = []
holepoints = []
holecoords = []
holeleft = len(self.hit[0])
holetop = len(self.hit)
holeright = holebottom = 0
idtoindexhole = []
prevvert = (self.allverts[0][0], self.allverts[1][0], self.allverts[2][0])
d = 0
for u in xrange(len(self.allverts[0])):
vert = (self.allverts[0][u], self.allverts[1][u], self.allverts[2][u])
if vert[1][17] != prevvert[1][18]:
d = 0
if prevvert[1][0] == "not hole":
objects.append(objectpoints)
objectpoints = []
idtoindexobj.append(prevvert[1][19])
else:
holes.append(holepoints)
holepoints = []
holecoords.append((holeleft + (MinMax.AminB(holeleft, holeright)/2), holetop + (MinMax.AminB(holetop, holebottom)/2)))
idtoindexhole.append(prevvert[2])
holeleft = len(self.hit[0])
holetop = len(self.hit)
holeright = holebottom = 0
if vert[1][0] == "not hole":
if d % 4 == 0:
objectpoints.append((vert[0][0], vert[0][20]))
else:
if d % 4 == 0:
holepoints.append((vert[0][0], vert[0][21]))
if vert[0][0] < holeleft: holeleft = vert[0][0]
if vert[0][0] > holeright: holeright = vert[0][0]
if vert[0][22] < holetop: holetop = vert[0][23]
if vert[0][24] > holebottom: holebottom = vert[0][25]
d+=1
prevvert = vert
if prevvert[1][0] == "not hole":
objects.append(objectpoints)
objectpoints = []
idtoindexobj.append(prevvert[1][26])
else:
holes.append(holepoints)
holepoints = []
holecoords.append((holeleft + (MinMax.AminB(holeleft, holeright)/2), holetop + (MinMax.AminB(holetop, holebottom)/2)))
idtoindexhole.append(prevvert[2])
holeleft = len(self.hit[0])
holetop = len(self.hit)
holeright = holebottom = 0
objectpoints.append((vert[0][0], vert[0][27]))
self.polygons = []
for ind, id in enumerate(idtoindexobj):
holecoordlist = []
segments = []
for k, l in enumerate(idtoindexhole):
if l == id:
holecoordlist.append(holecoords[k])
prevsegpart = False
for segpart in holes[k]:
if not prevsegpart:
prevsegpart = segpart
continue
segments.append((prevsegpart[0], prevsegpart[1], segpart[0], segpart[1]))
prevsegpart = segpart
segments.append((prevsegpart[0], prevsegpart[1], holes[k][0][0], holes[k][0][1]))
if segments:
self.polygons.append({"vertices":objects[ind], "segments":segments, "holes":holecoordlist})
else:
self.polygons.append({"vertices":objects[ind]})
indtripolylist = []
for pol in self.polygons:
#here i am calling that triangulate function
indtripolylist.append(triangle.triangulate(pol, opts="q"))
#and finally convert what has been returned to coordinates of triangles (because it returns list of vertices and touples of indexes pointing to vertices)
self.tripolylist = []
for po in indtripolylist:
tmptriangles = []
for tr in po["triangles"]:
tmptriangles.append((po["vertices"][tr[0]], po["vertices"][tr[1]], po["vertices"][tr[2]]))
self.tripolylist.append(tmptriangles)
Thank you for your help.
This had me scratching my head for a while, your comments helped me get it working.
to see an example of the data you need to pass:
triangle.get_data('face')
to stop a polygon being "filled in" and keep it concave you can pass along the segments like this
segments = []
for i in range(len(verts)-1):
segments.append([int(i),int(i+1)])
segments.append([int(i+1),int(0)])
A = {'vertices':array(verts), 'segments':array(segments)}
to add a hole, you need to mark the verts and segments seperatly (warning: untested code)
vertmarks = []
for i in range(len(verts)):
vertmarks.append([2])
for i in range(len(hole)):
vertmarks.append([4])
segmarks = []
for i in range(len(segments)):
segmarks.append([2])
for i in range(len(holesegments)):
segmarks.append([4])
A = {'vertices':array(verts), 'segments':array(segments),
'segment_markers':array(segmarks), 'vertex_markers':array(vertmarks)}
'holes' should also be passed as a list of [x,y] locations - one inside each hole