pixel overlap creating black spot- python - python

I am trying to create particles in an image ( and later displace, rotate, shear the image) for PIV. I use the following code to get my particles.
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Tue Sep 12 09:47:24 2017
#author: arun
Program to create synthetic particles.
Makeparticles : Version 1
updates : 1) change particle diameter variation
2) Image transformations using transformation matrix
3) Time saved = 15 seconds faster
"""
import cv2
import numpy as np
import time
from PIL import Image
import mahotas
from affine import Affine
#from skimage import io
#from skimage import transform as tf
#import matplotlib.pyplot as plt
#import math
#import matplotlib as mpl
#import matplotlib.pyplot as plt
#import trackpy as tp
#import pims
"""---------------------make particles--------------------------------"""
class Particles(object):
def __init__(self,n,extra,w,h,r1,r2):
self.x = np.random.uniform(low=0.0, high=1680.0, size=n)
self.y = np.random.uniform(low=0.0, high=1424.0, size=n)
self.rad=np.random.uniform(low=r1, high=r2, size=n)
self.n=n
self.extra=extra
self.w=w
self.h=h
# Initial location of particles. We use floating point ( not integer)
# to specify random location
def randomloc(self) :
for i in range(0,n) :
frame.add_spot((self.x[i], self.y[i]), 255, self.rad[i])
return self.x,self.y
def displacement(self,xdisp=20,ydisp=0):
img = cv2.imread('initial_image.jpg',0)
rows,cols = img.shape
M = np.float32([[1,0,xdisp],[0,1,ydisp]])
dst = cv2.warpAffine(img,M,(cols,rows))
cropped = dst[self.extra:self.w+self.extra, \
self.extra:self.h+self.extra]
return cropped
#plt.imshow(dst)
def rotate(self, ox,oy,angle):
img = cv2.imread('initial_image.jpg',0)
rows,cols = img.shape
M = cv2.getRotationMatrix2D((ox,oy),angle,1)
# the format is cv2.getRotationMatrix2D(center, angle, scale)
dst = cv2.warpAffine(img,M,(cols,rows),flags=cv2.INTER_LANCZOS4)
# area = (200, 200,1480,1224)
# cropped_img = dst.crop(area)
cropped = dst[200:1480, 200:1224]
return cropped
def shear2(self,anglex,angley):
img = cv2.imread('initial_image.jpg',0)
rows,cols = img.shape
M = Affine.shear(anglex, angley)
M=M[0:6]
a = np.array(M).reshape(2,3)
dst = cv2.warpAffine(img,a,(cols,rows),flags=cv2.INTER_LANCZOS4)
cropped = dst[200:1480, 200:1224]
return cropped
#
# def shear0(self,angle):
# image = io.imread("initial_image.jpg")
#
# # Create Afine transform
# afine_tf = tf.AffineTransform(shear=angle)
#
# # Apply transform to image data
# modified = tf.warp(image, inverse_map=afine_tf)
#
# # Display the result
# cropped = modified[200:1480, 200:1224]
# #cropped_img.save('sheared_image.jpg')
# return modified
# def shear1(self,):
# img = cv2.imread("initial_image.jpg")
# rows,cols,ch = img.shape
#
# pts1 = np.float32([[50,50],[200,50],[50,200]])
# pts2 = np.float32([[10,100],[200,50],[100,250]])
# M = cv2.getAffineTransform(pts1,pts2)
# dst = cv2.warpAffine(img,M,(cols,rows))
class SimulatedFrame(object):
def __init__(self, shape, dtype=np.uint8):
self.image = np.zeros(shape, dtype=dtype)
self._saturation = np.iinfo(dtype).max
self.shape = shape
self.dtype =dtype
#""" A gaussian distribution of intensities is obtained. Eccentricity
# (ecc) means how much the particle is elongated . """
def add_spot(self, pos, amplitude, r, ecc=0):
"Add a Gaussian spot to the frame."
x, y = np.meshgrid(*np.array(list(map(np.arange, self.shape))) \
- np.asarray(pos))
spot = amplitude*np.exp(-((x/(1 - ecc))**2 + (y*(1 - ecc))**2)/\
(2*r**2)).T
self.image += np.clip(spot, 0, self._saturation).astype\
(self.dtype)
def save_frame(self, filename='initial_image1.jpg'):
img = Image.fromarray(self.image.astype(np.uint8))
#cropped = img[200:1480, 200:1224]
img.save('initial_image.jpg')
area = (200, 200,1224,1480)
cropped = img.crop(area)
cropped.save(filename)
#-------------------------------------------------------------------------
""" Definition of parameters
This part is used to create an image with particles. This is to verify and
test the program that it works as intended An initial image at time T0,
with the particles having a circular and guassian distribution of their
intensities is made using the Makepart function definition. Then these
particles are displaced through translation, rotation and shear motions,
and this image is used to compute the velocity and vorticity vectors later
by cross correlation .
The variables used in this part are described as follows
w = width of the image
h = height of the image
n = Number of particles
r1 = Radius of Particle in pixels: Lower limit
r2 = Radius of particle in pixels: Upper limit
xdisp = Displacement required in the x direction
ydisp = Displacement required in the y direction
rotangle = Rotation requried in degrees (Anti-clockwise rotation)
ox,oy = location of the point about which rotation occurs
shearx= shear angle in x direction.Positive value indicates bottom side
shift to right
sheary= shear angle in y direction.Positive value indicates right side
shift to down
"""
start1=time.time()
w=1280
h=1024
n=500
r1 =3.0
r2= 5.0
xdisp=20
ydisp=0
rotangle=1
ox=840
oy=712
shearx=1.0
sheary=0
extra=200
"""creating an object for the class SimulatedFrame.
Input - total window size, dtype of image
Output- Black image of the desired pixel size
"""
frame = SimulatedFrame((w+extra, h+extra), dtype=np.int)
#we send the number of particles to the class,
#so that we can make locations
coordinates=Particles(n,extra,w,h,r1,r2)
x,y=coordinates.randomloc()
frame.save_frame()
x1=coordinates.displacement(xdisp,ydisp)
mahotas.imsave('displaced.jpg', x1)
x2=coordinates.rotate(ox,oy,rotangle)
mahotas.imsave('rotated.jpg', x2)
x3=coordinates.shear2(shearx,sheary)
mahotas.imsave('sheared.jpg',x3)
print("--- %s seconds ---" % (time.time() - start1))
however, in the places where two particles overlap, I get a black spot which I would like to avoid. I believe it is due to the pixel light intensity counter going back to 0 once it reaches 255. Is there a way to avoid these black spots?
This is the image output

Related

How would I warp text around an image's edges?

I am trying to create an image with the edges replaced with text, similar to This Youtube video thumbnail but from a source image. I've used OpenCV to get a version of a source image with edges, and Pillow to actually write the text, but I'm not sure where to start when it comes to actually manipulating the text automatically to fit to the edges. The code I have so far is:
import cv2 as cv
from matplotlib import pyplot as plt
from PIL import Image, ImageFont, ImageDraw, ImageShow
font = ImageFont.truetype(r"C:\Users\X\Downloads\Montserrat\Montserrat-Light.ttf", 12)
text = ["text", "other text"]
img = cv.imread(r"C:\Users\X\Pictures\picture.jpg",0)
edges = cv.Canny(img,100,200)
img = cv.cvtColor(img, cv.COLOR_BGR2RGB)
im_pil = Image.fromarray(edges)
This code is just for the edge detection and moving the detected edges to Pillow.
Please help
I am not sure where the "edges" comes in from the canny edge detector.
However, the circular text wrap can be done very simply in Python/Wand that uses ImageMagick. Or one can do that in Python/OpenCV using cv2.remap and custom transformation maps.
Input:
1. Python Wand
(output size determined automatically from input size)
from wand.image import Image
from wand.font import Font
from wand.display import display
with Image(filename='some_text.png') as img:
img.background_color = 'white'
img.virtual_pixel = 'white'
# 360 degree arc, rotated 0 degrees
img.distort('arc', (360,0))
img.save(filename='some_text_arc.png')
img.format = 'png'
display(img)
Result:
2. Python/OpenCV
import numpy as np
import cv2
import math
# read input
img = cv2.imread("some_text.png")
hin, win = img.shape[:2]
win2 = win / 2
# specify desired square output dimensions and center
hout = 100
wout = 100
xcent = wout / 2
ycent = hout / 2
hwout = max(hout,wout)
hwout2 = hwout / 2
# set up the x and y maps as float32
map_x = np.zeros((hout, wout), np.float32)
map_y = np.zeros((hout, wout), np.float32)
# create map with the arc distortion formula --- angle and radius
for y in range(hout):
Y = (y - ycent)
for x in range(wout):
X = (x - xcent)
XX = (math.atan2(Y,X)+math.pi/2)/(2*math.pi)
XX = XX - int(XX+0.5)
XX = XX * win + win2
map_x[y, x] = XX
map_y[y, x] = hwout2 - math.hypot(X,Y)
# do the remap this is where the magic happens
result = cv2.remap(img, map_x, map_y, cv2.INTER_CUBIC, borderMode = cv2.BORDER_CONSTANT, borderValue=(255,255,255))
# save results
cv2.imwrite("some_text_arc.jpg", result)
# display images
cv2.imshow('img', img)
cv2.imshow('result', result)
cv2.waitKey(0)
cv2.destroyAllWindows()
Result:
Neither OpenCV nor PIL has a way to do that, but you can use ImageMagick.
How to warp an image to take shape of path with python?

Webcam color calibration using OpenCV

Having ordered half a dozen webcams online for a project I notice that the colors on the output are not consistent.
In order to compensate for this I have attempted to take a template image and extract the R,G and B histograms and tried to match the target images's RGB histograms based on this.
This was inspired from the description of the solution for a very similar problem Comparative color calibration
The perfect solution will look like this :
In order to try to solve this I wrote the following script which performed poorly:
EDIT (Thanks to #DanMašek and #api55)
import numpy as np
def show_image(title, image, width = 300):
# resize the image to have a constant width, just to
# make displaying the images take up less screen real
# estate
r = width / float(image.shape[1])
dim = (width, int(image.shape[0] * r))
resized = cv2.resize(image, dim, interpolation = cv2.INTER_AREA)
# show the resized image
cv2.imshow(title, resized)
def hist_match(source, template):
"""
Adjust the pixel values of a grayscale image such that its histogram
matches that of a target image
Arguments:
-----------
source: np.ndarray
Image to transform; the histogram is computed over the flattened
array
template: np.ndarray
Template image; can have different dimensions to source
Returns:
-----------
matched: np.ndarray
The transformed output image
"""
oldshape = source.shape
source = source.ravel()
template = template.ravel()
# get the set of unique pixel values and their corresponding indices and
# counts
s_values, bin_idx, s_counts = np.unique(source, return_inverse=True,
return_counts=True)
t_values, t_counts = np.unique(template, return_counts=True)
# take the cumsum of the counts and normalize by the number of pixels to
# get the empirical cumulative distribution functions for the source and
# template images (maps pixel value --> quantile)
s_quantiles = np.cumsum(s_counts).astype(np.float64)
s_quantiles /= s_quantiles[-1]
t_quantiles = np.cumsum(t_counts).astype(np.float64)
t_quantiles /= t_quantiles[-1]
# interpolate linearly to find the pixel values in the template image
# that correspond most closely to the quantiles in the source image
interp_t_values = np.interp(s_quantiles, t_quantiles, t_values)
return interp_t_values[bin_idx].reshape(oldshape)
from matplotlib import pyplot as plt
from scipy.misc import lena, ascent
import cv2
source = cv2.imread('/media/somadetect/Lexar/color_transfer_data/1/frame10.png')
s_b = source[:,:,0]
s_g = source[:,:,1]
s_r = source[:,:,2]
template = cv2.imread('/media/somadetect/Lexar/color_transfer_data/5/frame6.png')
t_b = source[:,:,0]
t_r = source[:,:,1]
t_g = source[:,:,2]
matched_b = hist_match(s_b, t_b)
matched_g = hist_match(s_g, t_g)
matched_r = hist_match(s_r, t_r)
y,x,c = source.shape
transfer = np.empty((y,x,c), dtype=np.uint8)
transfer[:,:,0] = matched_r
transfer[:,:,1] = matched_g
transfer[:,:,2] = matched_b
show_image("Template", template)
show_image("Target", source)
show_image("Transfer", transfer)
cv2.waitKey(0)
Template image :
Target Image:
The Matched Image:
Then I found Adrian's (pyimagesearch) attempt to solve a very similar problem in the following link
Fast Color Transfer
The results seem to be fairly good with some saturation defects. I would welcome any suggestions or pointers on how to address this issue so all web cam outputs could be calibrated to output similar colors based on one template image.
Your script performs poorly because you are using the wrong index.
OpenCV images are BGR, so this was correct in your code:
source = cv2.imread('/media/somadetect/Lexar/color_transfer_data/1/frame10.png')
s_b = source[:,:,0]
s_g = source[:,:,1]
s_r = source[:,:,2]
template = cv2.imread('/media/somadetect/Lexar/color_transfer_data/5/frame6.png')
t_b = source[:,:,0]
t_r = source[:,:,1]
t_g = source[:,:,2]
but this is wrong
transfer[:,:,0] = matched_r
transfer[:,:,1] = matched_g
transfer[:,:,2] = matched_b
since here you are using RGB and not BGR, so the color changes and your OpenCV still thinks it is BGR. That is why it looks weird.
It should be:
transfer[:,:,0] = matched_b
transfer[:,:,1] = matched_g
transfer[:,:,2] = matched_r
As other possible solutions, you may try to look which parameters can be set in your camera. Sometimes they have some auto parameters which you can set manually for all of them to match. Also, beware of this auto parameters, usually white balance and focus and others are set auto and they may change quite a lot in the same camera from one time to another (depending on illumination, etc etc).
UPDATE:
As DanMašek points out, also
t_b = source[:,:,0]
t_r = source[:,:,1]
t_g = source[:,:,2]
is wrong, since the r should be index 2 and g index 1
t_b = source[:,:,0]
t_g = source[:,:,1]
t_r = source[:,:,2]
I have attempted a white patch based calibration routine. Here is the link https://theiszm.wordpress.com/tag/white-balance/.
The code snippet follows:
import cv2
import math
import numpy as np
import sys
from matplotlib import pyplot as plt
def hist_match(source, template):
"""
Adjust the pixel values of a grayscale image such that its histogram
matches that of a target image
Arguments:
-----------
source: np.ndarray
Image to transform; the histogram is computed over the flattened
array
template: np.ndarray
Template image; can have different dimensions to source
Returns:
-----------
matched: np.ndarray
The transformed output image
"""
oldshape = source.shape
source = source.ravel()
template = template.ravel()
# get the set of unique pixel values and their corresponding indices and
# counts
s_values, bin_idx, s_counts = np.unique(source, return_inverse=True,
return_counts=True)
t_values, t_counts = np.unique(template, return_counts=True)
# take the cumsum of the counts and normalize by the number of pixels to
# get the empirical cumulative distribution functions for the source and
# template images (maps pixel value --> quantile)
s_quantiles = np.cumsum(s_counts).astype(np.float64)
s_quantiles /= s_quantiles[-1]
t_quantiles = np.cumsum(t_counts).astype(np.float64)
t_quantiles /= t_quantiles[-1]
# interpolate linearly to find the pixel values in the template image
# that correspond most closely to the quantiles in the source image
interp_t_values = np.interp(s_quantiles, t_quantiles, t_values)
return interp_t_values[bin_idx].reshape(oldshape)
# Read original image
im_o = cv2.imread('/media/Lexar/color_transfer_data/5/frame10.png')
im = im_o
cv2.imshow('Org',im)
cv2.waitKey()
B = im[:,:, 0]
G = im[:,:, 1]
R = im[:,:, 2]
R= np.array(R).astype('float')
G= np.array(G).astype('float')
B= np.array(B).astype('float')
# Extract pixels that correspond to pure white R = 255,G = 255,B = 255
B_white = R[168, 351]
G_white = G[168, 351]
R_white = B[168, 351]
print B_white
print G_white
print R_white
# Compensate for the bias using normalization statistics
R_balanced = R / R_white
G_balanced = G / G_white
B_balanced = B / B_white
R_balanced[np.where(R_balanced > 1)] = 1
G_balanced[np.where(G_balanced > 1)] = 1
B_balanced[np.where(B_balanced > 1)] = 1
B_balanced=B_balanced * 255
G_balanced=G_balanced * 255
R_balanced=R_balanced * 255
B_balanced= np.array(B_balanced).astype('uint8')
G_balanced= np.array(G_balanced).astype('uint8')
R_balanced= np.array(R_balanced).astype('uint8')
im[:,:, 0] = (B_balanced)
im[:,:, 1] = (G_balanced)
im[:,:, 2] = (R_balanced)
# Notice saturation artifacts
cv2.imshow('frame',im)
cv2.waitKey()
# Extract the Y plane in original image and match it to the transformed image
im_o = cv2.cvtColor(im_o, cv2.COLOR_BGR2YCR_CB)
im_o_Y = im_o[:,:,0]
im = cv2.cvtColor(im, cv2.COLOR_BGR2YCR_CB)
im_Y = im[:,:,0]
matched_y = hist_match(im_o_Y, im_Y)
matched_y= np.array(matched_y).astype('uint8')
im[:,:,0] = matched_y
im_final = cv2.cvtColor(im, cv2.COLOR_YCR_CB2BGR)
cv2.imshow('frame',im_final)
cv2.waitKey()
The input image is:
The result of the script is:
Thank you all for suggestions and pointers!!

10 Pin Bowling score capture

I want to use OCR to capture the bowling scores from the monitor at the lances. I had a look at this sudoku solver, as I think its pretty similar - numbers and grids right? It has trouble finding the horizontal lines. Has anyone got any tips for pre-processing this image to make it easier to detect the lines (or numbers!). Also any tips for how to deal with the split (the orange ellipse around some of the 8's int he image)?
So far I have got the outline of the score area and cropped it.
import matplotlib
matplotlib.use('TkAgg')
from skimage import io
import numpy as np
import matplotlib.pyplot as plt
from skimage import measure
from skimage.color import rgb2gray
# import pytesseract
from matplotlib.path import Path
from qhd import *
def polygonArea(poly):
"""
Return area of an unclosed polygon.
:see: https://stackoverflow.com/a/451482
:param poly: (n,2)-array
"""
# we need a plain list for the following operations
if isinstance(poly, np.ndarray):
poly = poly.tolist()
segments = zip(poly, poly[1:] + [poly[0]])
return 0.5 * abs(sum(x0*y1 - x1*y0
for ((x0, y0), (x1, y1)) in segments))
filename = 'good.jpg'
image = io.imread(filename)
image = rgb2gray(image)
# Find contours at a constant value of 0.8
contours = measure.find_contours(image, 0.4)
# Display the image and plot all contours found
fig, ax = plt.subplots()
c = 0
biggest = None
biggest_size = 0
for n, contour in enumerate(contours):
curr_size = polygonArea(contour)
if curr_size > biggest_size:
biggest = contour
biggest_size = curr_size
biggest = qhull2D(biggest)
# Approximate that so we just get a rectangle.
biggest = measure.approximate_polygon(biggest, 500)
# vertices of the cropping polygon
yc = biggest[:,0]
xc = biggest[:,1]
xycrop = np.vstack((xc, yc)).T
# xy coordinates for each pixel in the image
nr, nc = image.shape
ygrid, xgrid = np.mgrid[:nr, :nc]
xypix = np.vstack((xgrid.ravel(), ygrid.ravel())).T
# construct a Path from the vertices
pth = Path(xycrop, closed=False)
# test which pixels fall within the path
mask = pth.contains_points(xypix)
# reshape to the same size as the image
mask = mask.reshape(image.shape)
# create a masked array
masked = np.ma.masked_array(image, ~mask)
# if you want to get rid of the blank space above and below the cropped
# region, use the min and max x, y values of the cropping polygon:
xmin, xmax = int(xc.min()), int(np.ceil(xc.max()))
ymin, ymax = int(yc.min()), int(np.ceil(yc.max()))
trimmed = masked[ymin:ymax, xmin:xmax]
plt.imshow(trimmed, cmap=plt.cm.gray), plt.title('trimmed')
plt.show()
https://imgur.com/LijB85I is an example of how the score is displayed.

OpenCV Python rotate image by X degrees around specific point

I'm having a hard time finding examples for rotating an image around a specific point by a specific (often very small) angle in Python using OpenCV.
This is what I have so far, but it produces a very strange resulting image, but it is rotated somewhat:
def rotateImage( image, angle ):
if image != None:
dst_image = cv.CloneImage( image )
rotate_around = (0,0)
transl = cv.CreateMat(2, 3, cv.CV_32FC1 )
matrix = cv.GetRotationMatrix2D( rotate_around, angle, 1.0, transl )
cv.GetQuadrangleSubPix( image, dst_image, transl )
cv.GetRectSubPix( dst_image, image, rotate_around )
return dst_image
import numpy as np
import cv2
def rotate_image(image, angle):
image_center = tuple(np.array(image.shape[1::-1]) / 2)
rot_mat = cv2.getRotationMatrix2D(image_center, angle, 1.0)
result = cv2.warpAffine(image, rot_mat, image.shape[1::-1], flags=cv2.INTER_LINEAR)
return result
Assuming you're using the cv2 version, that code finds the center of the image you want to rotate, calculates the transformation matrix and applies to the image.
Or much easier use
SciPy
from scipy import ndimage
#rotation angle in degree
rotated = ndimage.rotate(image_to_rotate, 45)
see
here
for more usage info.
def rotate(image, angle, center = None, scale = 1.0):
(h, w) = image.shape[:2]
if center is None:
center = (w / 2, h / 2)
# Perform the rotation
M = cv2.getRotationMatrix2D(center, angle, scale)
rotated = cv2.warpAffine(image, M, (w, h))
return rotated
I had issues with some of the above solutions, with getting the correct "bounding_box" or new size of the image. Therefore here is my version
def rotation(image, angleInDegrees):
h, w = image.shape[:2]
img_c = (w / 2, h / 2)
rot = cv2.getRotationMatrix2D(img_c, angleInDegrees, 1)
rad = math.radians(angleInDegrees)
sin = math.sin(rad)
cos = math.cos(rad)
b_w = int((h * abs(sin)) + (w * abs(cos)))
b_h = int((h * abs(cos)) + (w * abs(sin)))
rot[0, 2] += ((b_w / 2) - img_c[0])
rot[1, 2] += ((b_h / 2) - img_c[1])
outImg = cv2.warpAffine(image, rot, (b_w, b_h), flags=cv2.INTER_LINEAR)
return outImg
The cv2.warpAffine function takes the shape parameter in reverse order: (col,row) which the answers above do not mention. Here is what worked for me:
import numpy as np
def rotateImage(image, angle):
row,col = image.shape
center=tuple(np.array([row,col])/2)
rot_mat = cv2.getRotationMatrix2D(center,angle,1.0)
new_image = cv2.warpAffine(image, rot_mat, (col,row))
return new_image
import imutils
vs = VideoStream(src=0).start()
...
while (1):
frame = vs.read()
...
frame = imutils.rotate(frame, 45)
More: https://github.com/jrosebr1/imutils
You can simply use the imutils package to do the rotation. it has two methods
rotate: rotate the image at specified angle. however the drawback is image might get cropped if it is not a square image.
rotate_bound: it overcomes the problem happened with rotate. It adjusts the size of the image accordingly while rotating the image.
more info you can get on this blog:
https://www.pyimagesearch.com/2017/01/02/rotate-images-correctly-with-opencv-and-python/
Quick tweak to #alex-rodrigues answer... deals with shape including the number of channels.
import cv2
import numpy as np
def rotateImage(image, angle):
center=tuple(np.array(image.shape[0:2])/2)
rot_mat = cv2.getRotationMatrix2D(center,angle,1.0)
return cv2.warpAffine(image, rot_mat, image.shape[0:2],flags=cv2.INTER_LINEAR)
You need a homogenous matrix of size 2x3. First 2x2 is the rotation matrix and last column is a translation vector.
Here's how to build your transformation matrix:
# Exemple with img center point:
# angle = np.pi/6
# specific_point = np.array(img.shape[:2][::-1])/2
def rotate(img: np.ndarray, angle: float, specific_point: np.ndarray) -> np.ndarray:
warp_mat = np.zeros((2,3))
cos, sin = np.cos(angle), np.sin(angle)
warp_mat[:2,:2] = [[cos, -sin],[sin, cos]]
warp_mat[:2,2] = specific_point - np.matmul(warp_mat[:2,:2], specific_point)
return cv2.warpAffine(img, warp_mat, img.shape[:2][::-1])
You can easily rotate the images using opencv python-
def funcRotate(degree=0):
degree = cv2.getTrackbarPos('degree','Frame')
rotation_matrix = cv2.getRotationMatrix2D((width / 2, height / 2), degree, 1)
rotated_image = cv2.warpAffine(original, rotation_matrix, (width, height))
cv2.imshow('Rotate', rotated_image)
If you are thinking of creating a trackbar, then simply create a trackbar using cv2.createTrackbar() and the call the funcRotate()fucntion from your main script. Then you can easily rotate it to any degree you want. Full details about the implementation can be found here as well- Rotate images at any degree using Trackbars in opencv
Here's an example for rotating about an arbitrary point (x,y) using only openCV
def rotate_about_point(x, y, degree, image):
rot_mtx = cv.getRotationMatrix2D((x, y), angle, 1)
abs_cos = abs(rot_mtx[0, 0])
abs_sin = abs(rot_mtx[0, 1])
rot_wdt = int(frm_hgt * abs_sin + frm_wdt * abs_cos)
rot_hgt = int(frm_hgt * abs_cos + frm_wdt * abs_sin)
rot_mtx += np.asarray([[0, 0, -lftmost_x],
[0, 0, -topmost_y]])
rot_img = cv.warpAffine(image, rot_mtx, (rot_wdt, rot_hgt),
borderMode=cv.BORDER_CONSTANT)
return rot_img
you can use the following code:
import numpy as np
from PIL import Image
import math
def shear(angle,x,y):
tangent=math.tan(angle/2)
new_x=round(x-y*tangent)
new_y=y
#shear 2
new_y=round(new_x*math.sin(angle)+new_y)
#since there is no change in new_x according to the shear matrix
#shear 3
new_x=round(new_x-new_y*tangent)
#since there is no change in new_y according to the shear matrix
return new_y,new_x
image = np.array(Image.open("test.png"))
# Load the image
angle=-int(input("Enter the angle :- "))
# Ask the user to enter the angle of rotation
# Define the most occuring variables
angle=math.radians(angle)
#converting degrees to radians
cosine=math.cos(angle)
sine=math.sin(angle)
height=image.shape[0]
#define the height of the image
width=image.shape[1]
#define the width of the image
# Define the height and width of the new image that is to be formed
new_height = round(abs(image.shape[0]*cosine)+abs(image.shape[1]*sine))+1
new_width = round(abs(image.shape[1]*cosine)+abs(image.shape[0]*sine))+1
output=np.zeros((new_height,new_width,image.shape[2]))
image_copy=output.copy()
# Find the centre of the image about which we have to rotate the image
original_centre_height = round(((image.shape[0]+1)/2)-1)
#with respect to the original image
original_centre_width = round(((image.shape[1]+1)/2)-1)
#with respect to the original image
# Find the centre of the new image that will be obtained
new_centre_height= round(((new_height+1)/2)-1)
#with respect to the new image
new_centre_width= round(((new_width+1)/2)-1)
#with respect to the new image
for i in range(height):
for j in range(width):
#co-ordinates of pixel with respect to the centre of original image
y=image.shape[0]-1-i-original_centre_height
x=image.shape[1]-1-j-original_centre_width
#Applying shear Transformation
new_y,new_x=shear(angle,x,y)
new_y=new_centre_height-new_y
new_x=new_centre_width-new_x
output[new_y,new_x,:]=image[i,j,:]
pil_img=Image.fromarray((output).astype(np.uint8))
pil_img.save("rotated_image.png")

Intensity normalization of image using Python+PIL - Speed issues

I'm working on a little problem in my sparetime involving analysis of some images obtained through a microscope. It is a wafer with some stuff here and there, and ultimately I want to make a program to detect when certain materials show up.
Anyways, first step is to normalize the intensity across the image, since the lens does not give uniform lightning. Currently I use an image, with no stuff on, only the substrate, as a background, or reference, image. I find the maximum of the three (intensity) values for RGB.
from PIL import Image
from PIL import ImageDraw
rmax = 0;gmax = 0;bmax = 0;rmin = 300;gmin = 300;bmin = 300
im_old = Image.open("test_image.png")
im_back = Image.open("background.png")
maxx = im_old.size[0] #Import the size of the image
maxy = im_old.size[1]
im_new = Image.new("RGB", (maxx,maxy))
pixback = im_back.load()
for x in range(maxx):
for y in range(maxy):
if pixback[x,y][0] > rmax:
rmax = pixback[x,y][0]
if pixback[x,y][1] > gmax:
gmax = pixback[x,y][1]
if pixback[x,y][2] > bmax:
bmax = pixback[x,y][2]
pixnew = im_new.load()
pixold = im_old.load()
for x in range(maxx):
for y in range(maxy):
r = float(pixold[x,y][0]) / ( float(pixback[x,y][0])*rmax )
g = float(pixold[x,y][1]) / ( float(pixback[x,y][1])*gmax )
b = float(pixold[x,y][2]) / ( float(pixback[x,y][2])*bmax )
pixnew[x,y] = (r,g,b)
The first part of the code determines the maximum intensity of the RED, GREEN and BLUE channels, pixel by pixel, of the background image, but needs only be done once.
The second part takes the "real" image (with stuff on it), and normalizes the RED, GREEN and BLUE channels, pixel by pixel, according to the background. This takes some time, 5-10 seconds for an 1280x960 image, which is way too slow if I need to do this to several images.
What can I do to improve the speed? I thought of moving all the images to numpy arrays, but I can't seem to find a fast way to do that for RGB images.
I'd rather not move away from python, since my C++ is quite low-level, and getting a working FORTRAN code would probably take longer than I could ever save in terms of speed :P
import numpy as np
from PIL import Image
def normalize(arr):
"""
Linear normalization
http://en.wikipedia.org/wiki/Normalization_%28image_processing%29
"""
arr = arr.astype('float')
# Do not touch the alpha channel
for i in range(3):
minval = arr[...,i].min()
maxval = arr[...,i].max()
if minval != maxval:
arr[...,i] -= minval
arr[...,i] *= (255.0/(maxval-minval))
return arr
def demo_normalize():
img = Image.open(FILENAME).convert('RGBA')
arr = np.array(img)
new_img = Image.fromarray(normalize(arr).astype('uint8'),'RGBA')
new_img.save('/tmp/normalized.png')
See http://docs.scipy.org/doc/scipy/reference/generated/scipy.misc.fromimage.html#scipy.misc.fromimage
You can say
databack = scipy.misc.fromimage(pixback)
rmax = numpy.max(databack[:,:,0])
gmax = numpy.max(databack[:,:,1])
bmax = numpy.max(databack[:,:,2])
which should be much faster than looping over all (r,g,b) triplets of your image.
Then you can do
dataold = scip.misc.fromimage(pixold)
r = dataold[:,:,0] / (pixback[:,:,0] * rmax )
g = dataold[:,:,1] / (pixback[:,:,1] * gmax )
b = dataold[:,:,2] / (pixback[:,:,2] * bmax )
datanew = numpy.array((r,g,b))
imnew = scipy.misc.toimage(datanew)
The code is not tested, but should work somehow with minor modifications.
This is partially from FolksTalk webpage:
from PIL import Image
import numpy as np
# Read image file
in_file = "my_image.png"
# convert('RGB') for PNG file type
image = Image.open(in_file).convert('RGB')
pixels = np.asarray(image)
# Convert from integers to floats
pixels = pixels.astype('float32')
# Normalize to the range 0-1
pixels /= 255.0

Categories

Resources