Related
I used the following code to select nose in OpenCV and Python i searched a lot of to find a way to change the size of nose and save as a other image but i didn't find anything is there anybody to help me to do this.
import cv2
import numpy as np
import dlib
img = cv2.imread('1.jpg')
img = cv2.resize(img,(0,0),None,0.5,0.5)
imgOriginal = img.copy()
detector = dlib.get_frontal_face_detector()
predictor = dlib.shape_predictor("shape_predictor_68_face_landmarks.dat")
def createBox(img,points,scale=5):
bbox = cv2.boundingRect(points)
x,y,w,h = bbox
imgCrop = img[y:y+h,x:x+w]
imgCrop = cv2.resize(imgCrop,(0,0),None,scale,scale)
return imgCrop
imgGray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
faces = detector(imgGray)
for face in faces:
x1,y1 = face.left(),face.top()
x2,y2 = face.right(),face.bottom()
imgOriginal = cv2.rectangle(img,(x1,y1),(x2,y2),(0,255,0),1)
landmarks = predictor(imgGray,face)
myPoints=[]
for n in range(68):
x = landmarks.part(n).x
y = landmarks.part(n).y
myPoints.append([x,y])
#cv2.circle(imgOriginal,(x,y),5,(50,50,255),cv2.FILLED)
#cv2.putText(imgOriginal,str(n),(x,y-10),cv2.FONT_HERSHEY_COMPLEX_SMALL,0.8,(0,0,255),1)
myPoints = np.array(myPoints)
#nose points to select
#nose_points = myPoints[27:35]
print(myPoints)
cv2_imshow(imgOriginal)
cv2.waitKey(0)
thanks in advance
Here is one way using a spherical (bubble) warp in a local region in Python/OpenCV.
- Define region center and radius and amount of spherical distortion
- Crop the image for that center and radius
- Compute the spherical distortion x and y displacement maps and a binary mask
- Apply the distortion maps using cv2.remap
- Antialias the mask
- Merge the distorted and cropped image using the mask
- Insert that merged image into the original image
- Save the results
Input:
import numpy as np
import cv2
import math
import skimage.exposure
img = cv2.imread("portrait_of_mussorgsky2.jpg")
# set location and radius
cx = 130
cy = 109
radius = 30
# set distortion gain
gain = 1.5
# crop image
crop = img[cy-radius:cy+radius, cx-radius:cx+radius]
# get dimensions
ht, wd = crop.shape[:2]
xcent = wd / 2
ycent = ht / 2
rad = min(xcent,ycent)
# set up the x and y maps as float32
map_x = np.zeros((ht, wd), np.float32)
map_y = np.zeros((ht, wd), np.float32)
mask = np.zeros((ht, wd), np.uint8)
# create map with the spherize distortion formula --- arcsin(r)
# xcomp = arcsin(r)*x/r; ycomp = arsin(r)*y/r
for y in range(ht):
Y = (y - ycent)/ycent
for x in range(wd):
X = (x - xcent)/xcent
R = math.hypot(X,Y)
if R == 0:
map_x[y, x] = x
map_y[y, x] = y
mask[y,x] = 255
elif R >= .90: # avoid extreme blurring near R = 1
map_x[y, x] = x
map_y[y, x] = y
mask[y,x] = 0
elif gain >= 0:
map_x[y, x] = xcent*X*math.pow((2/math.pi)*(math.asin(R)/R), gain) + xcent
map_y[y, x] = ycent*Y*math.pow((2/math.pi)*(math.asin(R)/R), gain) + ycent
mask[y,x] = 255
elif gain < 0:
gain2 = -gain
map_x[y, x] = xcent*X*math.pow((math.sin(math.pi*R/2)/R), gain2) + xcent
map_y[y, x] = ycent*Y*math.pow((math.sin(math.pi*R/2)/R), gain2) + ycent
mask[y,x] = 255
# remap using map_x and map_y
bump = cv2.remap(crop, map_x, map_y, cv2.INTER_LINEAR, borderMode = cv2.BORDER_CONSTANT, borderValue=(0,0,0))
# antialias edge of mask
# (pad so blur does not extend to edges of image, then crop later)
blur = 7
mask = cv2.copyMakeBorder(mask, blur,blur,blur,blur, borderType=cv2.BORDER_CONSTANT, value=(0))
mask = cv2.GaussianBlur(mask, (0,0), sigmaX=blur, sigmaY=blur, borderType = cv2.BORDER_DEFAULT)
h, w = mask.shape
mask = mask[blur:h-blur, blur:w-blur]
mask = cv2.cvtColor(mask, cv2.COLOR_GRAY2BGR)
mask = skimage.exposure.rescale_intensity(mask, in_range=(127.5,255), out_range=(0,1))
# merge bump with crop using grayscale (not binary) mask
bumped = (bump * mask + crop * (1-mask)).clip(0,255).astype(np.uint8)
# insert bumped image into original
result = img.copy()
result[cy-radius:cy+radius, cx-radius:cx+radius] = bumped
# save results
cv2.imwrite("portrait_of_mussorgsky2_bump.jpg", result)
# display images
cv2.imshow('img', img)
cv2.imshow('crop', crop)
cv2.imshow('bump', bump)
cv2.imshow('mask', mask)
cv2.imshow('bumped', bumped)
cv2.imshow('result', result)
cv2.waitKey(0)
cv2.destroyAllWindows()
Resulting Image:
I think you need "Bulge" effects such as implode and explode. There are no implementation of these filters in OpenCV but, you can find other tools such as Wand(a python binding for ImageMagick) that have implode/explode.
Example (wand):
from wand.image import Image
with Image(filename="test.jpg") as img:
img.implode(amount = -0.2)
img.save(filename="destination.jpg")
# img_array = numpy.asarray(img) --> you can convert wand.image.Image to numpy array for further uses
passing negative values into implode functions is equal to doing explode. So for magnifying effect use negative values.
There is one problem though: img.implode performs on the center of the image, so after you've found the face features(eye, nose, ...) you need to move your picture somehow to make the eye or nose to lie on the center of the image. After that you can simply use implode function.
I am trying to detect a grainy printed line on a paper with cv2. I need the angle of the line. I dont have much knowledge in image processing and I only need to detect the line. I tried to play with the parameters but the angle is always detected wrong. Could someone help me. This is my code:
import cv2
import numpy as np
import matplotlib.pylab as plt
from matplotlib.pyplot import figure
img = cv2.imread('CamXY1_1.bmp')
crop_img = img[100:800, 300:900]
blur = cv2.GaussianBlur(crop_img, (1,1), 0)
ret,thresh = cv2.threshold(blur,150,255,cv2.THRESH_BINARY)
gray = cv2.cvtColor(thresh,cv2.COLOR_BGR2GRAY)
edges = cv2.Canny(gray, 60, 150)
figure(figsize=(15, 15), dpi=150)
plt.imshow(edges, 'gray')
lines = cv2.HoughLines(edges,1,np.pi/180,200)
for rho,theta in lines[0]:
a = np.cos(theta)
b = np.sin(theta)
x0 = a*rho
y0 = b*rho
x1 = int(x0 + 3000*(-b))
y1 = int(y0 + 3000*(a))
x2 = int(x0 - 3000*(-b))
y2 = int(y0 - 3000*(a))
cv2.line(img,(x1,y1),(x2,y2),(0, 255, 0),2)
imagetobedetected
Here's a possible solution to estimate the line (and its angle) without using the Hough line transform. The idea is to locate the start and ending points of the line using the reduce function. This function can reduce an image to a single column or row. If we reduce the image we can also get the total SUM of all the pixels across the reduced image. Using this info we can estimate the extreme points of the line and calculate its angle. This are the steps:
Resize your image because it is way too big
Get a binary image via adaptive thresholding
Define two extreme regions of the image and crop them
Reduce the ROIs to a column using the SUM mode, which is the sum of all rows
Accumulate the total values above a threshold value
Estimate the starting and ending points of the line
Get the angle of the line
Here's the code:
# imports:
import cv2
import numpy as np
import math
# image path
path = "D://opencvImages//"
fileName = "mmCAb.jpg"
# Reading an image in default mode:
inputImage = cv2.imread(path + fileName)
# Scale your BIG image into a small one:
scalePercent = 0.3
# Calculate the new dimensions
width = int(inputImage.shape[1] * scalePercent)
height = int(inputImage.shape[0] * scalePercent)
newSize = (width, height)
# Resize the image:
inputImage = cv2.resize(inputImage, newSize, None, None, None, cv2.INTER_AREA)
# Deep copy for results:
inputImageCopy = inputImage.copy()
# Convert BGR to grayscale:
grayInput = cv2.cvtColor(inputImage, cv2.COLOR_BGR2GRAY)
# Adaptive Thresholding:
windowSize = 51
windowConstant = 11
binaryImage = cv2.adaptiveThreshold(grayInput, 255, cv2.ADAPTIVE_THRESH_MEAN_C, cv2.THRESH_BINARY_INV, windowSize, windowConstant)
The first step is to get the binary image. Note that I previously downscaled your input because it is too big and we don't need all that info. This is the binary mask:
Now, we don't need most of the image. In fact, since the line is across the whole image, we can only "trim" the first and last column and check out where the white pixels begin. I'll crop a column a little bit wider, though, so we can ensure we have enough data and as less noise as possible. I'll define two Regions of Interest (ROIs) and crop them. Then, I'll reduce each ROI to a column using the SUM mode, this will give me the summation of all intensity across each row. After that, I can accumulate the locations where the sum exceeds a certain threshold and approximate the location of the line, like this:
# Define the regions that will be cropped
# from the original image:
lineWidth = 5
cropPoints = [(0, 0, lineWidth, height), (width-lineWidth, 0, lineWidth, height)]
# Store the line points here:
linePoints = []
# Loop through the crop points and
# crop de ROI:
for p in range(len(cropPoints)):
# Get the ROI:
(x,y,w,h) = cropPoints[p]
# Crop the ROI:
imageROI = binaryImage[y:y+h, x:x+w]
# Reduce the ROI to a n row x 1 columns matrix:
reducedImg = cv2.reduce(imageROI, 1, cv2.REDUCE_SUM, dtype=cv2.CV_32S)
# Get the height (or lenght) of the arry:
reducedHeight = reducedImg.shape[0]
# Define a threshold and accumulate
# the coordinate of the points:
threshValue = 100
pointSum = 0
pointCount = 0
for i in range(reducedHeight):
currentValue = reducedImg[i]
if currentValue > threshValue:
pointSum = pointSum + i
pointCount = pointCount + 1
# Get average coordinate of the line:
y = int(accX / pixelCount)
# Store in list:
linePoints.append((x, y))
The red rectangles show the regions I cropped from the input image:
Note that I've stored both points in the linePoints list. Let's check out our approximation by drawing a line that connects both points:
# Get the two points:
p0 = linePoints[0]
p1 = linePoints[1]
# Draw the line:
cv2.line(inputImageCopy, (p0[0], p0[1]), (p1[0], p1[1]), (255, 0, 0), 1)
cv2.imshow("Line", inputImageCopy)
cv2.waitKey(0)
Which yields:
Not bad, huh? Now that we have both points, we can estimate the angle of this line:
# Get angle:
adjacentSide = p1[0] - p0[0]
oppositeSide = p0[1] - p1[1]
# Compute the angle alpha:
alpha = math.degrees(math.atan(oppositeSide / adjacentSide))
print("Angle: "+str(alpha))
This prints:
Angle: 0.534210901840831
I have a set of arbitrary images. Half the images are pictures, half are masks defining ROIS.
In the current version of my program I use the ROI to crop the image (i.e I extract the rectangle in the image matching the bounding box of the ROI mask). The problem is, the ROI mask isn't perfect and it's better to over predict than under predict in my case.
So I want to copy more than the ROI rectangle, but if I do this, I may be trying to crop out of the image.
i.e:
x, y, w, h = cv2.boundingRect(mask_contour)
img = img[int(y-h*0.05):int(y + h * 1.05), int(x-w*0.05):int(x + w * 1.05)]
can fail because it tries to access out of bounds pixels. I could just clamp the values, but I wanted to know if there is a better approach
You can add a boarder using OpenCV
import cv2 as cv
import random
src = cv.imread('/home/stephen/lenna.png')
borderType = cv.BORDER_REPLICATE
boarderSize = .5
top = int(boarderSize * src.shape[0]) # shape[0] = rows
bottom = top
left = int(boarderSize * src.shape[1]) # shape[1] = cols
right = left
value = [random.randint(0,255), random.randint(0,255), random.randint(0,255)]
dst = cv.copyMakeBorder(src, top, bottom, left, right, borderType, None, value)
cv.imshow('img', dst)
c = cv.waitKey(0)
Maybe you could try to limit the coordinates beforehand. Please see the code below:
[ymin, ymax] = [max(0,int(y-h*0.05)), min(h, int(y+h*1.05))]
[xmin, xmax] = [max(0,int(x-w*1.05)), min(w, int(x+w*1.05))]
img = img[ymin:ymax, xmin:xmax]
I work with logos and other simple graphics, in which there are no gradients or complex patterns. My task is to extract from the logo segments with letters and other elements.
To do this, I define the background color, and then I go through the picture in order to segment the images. Here is my code for more understanding:
MAXIMUM_COLOR_TRANSITION_DELTA = 100 # 0 - 765
def expand_segment_recursive(image, unexplored_foreground, segment, point, color):
height, width, _ = image.shape
# Unpack coordinates from point
py, px = point
# Create list of pixels to check
neighbourhood_pixels = [(py, px + 1), (py, px - 1), (py + 1, px), (py - 1, px)]
allowed_zone = unexplored_foreground & np.invert(segment)
for y, x in neighbourhood_pixels:
# Add pixel to segment if its coordinates within the image shape and its color differs from segment color no
# more than MAXIMUM_COLOR_TRANSITION_DELTA
if y in range(height) and x in range(width) and allowed_zone[y, x]:
color_delta = np.sum(np.abs(image[y, x].astype(np.int) - color.astype(np.int)))
print(color_delta)
if color_delta <= MAXIMUM_COLOR_TRANSITION_DELTA:
segment[y, x] = True
segment = expand_segment_recursive(image, unexplored_foreground, segment, (y, x), color)
allowed_zone = unexplored_foreground & np.invert(segment)
return segment
if __name__ == "__main__":
if len(sys.argv) < 2:
print("Pass image as the argument to use the tool")
exit(-1)
IMAGE_FILENAME = sys.argv[1]
print(IMAGE_FILENAME)
image = cv.imread(IMAGE_FILENAME)
height, width, _ = image.shape
# To filter the background I use median value of the image, as background in most cases takes > 50% of image area.
background_color = np.median(image, axis=(0, 1))
print("Background color: ", background_color)
# Create foreground mask to find segments in it (TODO: Optimize this part)
foreground = np.zeros(shape=(height, width, 1), dtype=np.bool)
for y in range(height):
for x in range(width):
if not np.array_equal(image[y, x], background_color):
foreground[y, x] = True
unexplored_foreground = foreground
for y in range(height):
for x in range(width):
if unexplored_foreground[y, x]:
segment = np.zeros(foreground.shape, foreground.dtype)
segment[y, x] = True
segment = expand_segment_recursive(image, unexplored_foreground, segment, (y, x), image[y, x])
cv.imshow("segment", segment.astype(np.uint8) * 255)
while cv.waitKey(0) != 27:
continue
Here is the desired result:
In the end of run-time I expect 13 extracted separated segments (for this particular image). But instead I got RecursionError: maximum recursion depth exceeded, which is not surprising as expand_segment_recursive() can be called for every pixel of the image. And since even with small image resolution of 600x500 i got at maximum 300K calls.
My question is how can I get rid of recursion in this case and possibly optimize the algorithm with Numpy or OpenCV algorithms?
You can actually use a thresholded image (binary) and connectedComponents to do this job in a couple of steps. Also, you may use findContours or other methods.
Here is the code:
import numpy as np
import cv2
# load image as greyscale
img = cv2.imread("hp.png", 0)
# puts 0 to the white (background) and 255 in other places (greyscale value < 250)
_, thresholded = cv2.threshold(img, 250, 255, cv2.THRESH_BINARY_INV)
# gets the labels and the amount of labels, label 0 is the background
amount, labels = cv2.connectedComponents(thresholded)
# lets draw it for visualization purposes
preview = np.zeros((img.shape[0], img.shape[2], 3), dtype=np.uint8)
print (amount) #should be 3 -> two components + background
# draw label 1 blue and label 2 green
preview[labels == 1] = (255, 0, 0)
preview[labels == 2] = (0, 255, 0)
cv2.imshow("frame", preview)
cv2.waitKey(0)
At the end, the thresholded image will look like this:
and the preview image (the one with the colored segments) will look like this:
With the mask you can always use numpy functions to get things like, coordinates of the segments you want or to color them (like I did with preview)
UPDATE
To get different colored segments, you may try to create a "border" between the segments. Since they are plain colors and not gradients, you can try to do an edge detector like canny and then put it black in the image....
import numpy as np
import cv2
img = cv2.imread("total.png", 0)
# background to black
img[img>=200] = 0
# get edges
canny = cv2.Canny(img, 60, 180)
# make them thicker
kernel = np.ones((3,3),np.uint8)
canny = cv2.morphologyEx(canny, cv2.MORPH_DILATE, kernel)
# apply edges as border in the image
img[canny==255] = 0
# same as before
amount, labels = cv2.connectedComponents(img)
preview = np.zeros((img.shape[0], img.shape[1], 3), dtype=np.uint8)
print (amount) #should be 14 -> 13 components + background
# color them randomly
for i in range(1, amount):
preview[labels == i] = np.random.randint(0,255, size=3, dtype=np.uint8)
cv2.imshow("frame", preview )
cv2.waitKey(0)
The result is:
I'm trying to find the tilt angle in a series of images which look like the created example data below. There should be a clear edge which is visible by eye. However I'm struggling in extracting the edges so far. Is Canny the right way of finding the edge here or is there a better way of finding the edge?
import cv2 as cv
import numpy as np
import matplotlib.pyplot as plt
from scipy.ndimage.filters import gaussian_filter
# create data
xvals = np.arange(0,2000)
yvals = 10000 * np.exp((xvals - 1600)/200) + 100
yvals[1600:] = 100
blurred = gaussian_filter(yvals, sigma=20)
# create image
img = np.tile(blurred,(2000,1))
img = np.swapaxes(img,0,1)
# rotate image
rows,cols = img.shape
M = cv.getRotationMatrix2D((cols/2,rows/2),3.7,1)
img = cv.warpAffine(img,M,(cols,rows))
# convert to uint8 for Canny
img_8 = cv.convertScaleAbs(img,alpha=(255.0/65535.0))
fig,ax = plt.subplots(3)
ax[0].plot(xvals,blurred)
ax[1].imshow(img)
# find edge
ax[2].imshow(cv.Canny(img_8, 20, 100, apertureSize=5))
You can find the angle by transforming your image to binary (cv2.threshold(cv2.THRESH_BINARY)) then search for contours.
When you locate your contour (line) then you can fit a line on your contour cv2.fitLine() and get two points of your line. My math is not very good but I think that in linear equation the formula goes f(x) = k*x + n and you can get k out of those two points (k = (y2-y1)/(x2-x1)) and finally the angle phi = arctan(k). (If I'm wrong please correct it)
You can also use the rotated bounding rectangle - cv2.minAreaRect() - which already returns the angle of the rectangle (rect = cv2.minAreaRect() --> rect[2]). Hope it helps. Cheers!
Here is an example code:
import cv2
import numpy as np
import math
img = cv2.imread('angle.png')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
ret, threshold = cv2.threshold(gray,170,255,cv2.THRESH_BINARY)
im, contours, hierarchy = cv2.findContours(threshold,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
for c in contours:
area = cv2.contourArea(c)
perimeter = cv2.arcLength(c, False)
if area < 10001 and 100 < perimeter < 1000:
# first approach - fitting line and calculate with y=kx+n --> angle=tan^(-1)k
rows,cols = img.shape[:2]
[vx,vy,x,y] = cv2.fitLine(c, cv2.DIST_L2,0,0.01,0.01)
lefty = int((-x*vy/vx) + y)
righty = int(((cols-x)*vy/vx)+y)
cv2.line(img,(cols-1,righty),(0,lefty),(0,255,0),2)
(x1, y1) = (cols-1, righty)
(x2, y2) = (0, lefty)
k = (y2-y1)/(x2-x1)
angle = math.atan(k)*180/math.pi
print(angle)
#second approch - cv2.minAreaRect --> returns center (x,y), (width, height), angle of rotation )
rect = cv2.minAreaRect(c)
box = cv2.boxPoints(rect)
box = np.int0(box)
cv2.drawContours(img,[box],0,(0,0,255),2)
print(rect[2])
cv2.imshow('img2', img)
Original image:
Output:
-3.8493663478518627
-3.7022125720977783
tribol,
it seems like you can take the gradient image G = |Gx| + |Gy| (normalize it to some known range), calc its Histogram and take the top bins of it. it will give you approx mask of the line. Then you can do line fitting. It'll give you a good initial guess.
A very simple way of doing it is as follows... adjust my numbers to suit your knowledge of the data.
Normalise your image to a scale of 0-255.
Choose two points A and B, where A is 10% of the image width in from the left side and B is 10% in from the right side. The distance AB is now 0.8 x 2000, or 1600 px.
Go North from point A sampling your image till you exceed some sensible threshold that means you have met the tilted line. Note the Y value at this point, as YA.
Do the same, going North from point B till you meet the tilted line. Note the Y value at this point, as YB.
The angle you seek is:
tan-1((YB-YA)/1600)
Thresholding as suggested by kavko didn't work that well, as the intensity varied from image to image (I could of course consider the histogram for each image to imrove this approach). I ended up with taking the maximum of the gradient in the y-direction:
def rotate_image(image):
blur = ndimage.gaussian_filter(image, sigma=10) # blur image first
grad = np.gradient(blur, axis= 0) # take gradient along y-axis
grad[grad>10000]=0 # filter unreasonable high values
idx_maxline = np.argmax(grad, axis=0) # get y-indices of max slope = indices of edge
mean = np.mean(idx_maxline)
std = np.std(idx_maxline)
idx = np.arange(idx_maxline.shape[0])
idx_filtered = idx[(idx_maxline < mean+std) & (idx_maxline > mean - std)] # filter positions where highest slope is at different position(blobs)
slope, intercept, r_value, p_value, std_err = stats.linregress(idx_filtered, idx_maxline[idx_filtered])
out = ndimage.rotate(image,slope*180/np.pi, reshape = False)
return out
out = rotate_image(img)
plt.imshow(out)