Related
I have a thermal image (with a color bar) from an IR camera. My goal is to get the temperature of any point by clicking on it.
I have already written a script that retrieves the RBG values of any pixel by right-clicking on it.
I figure that using the max and min temperatures of the color bar, I can map pixel values to temperature values.
Is this possible or is there a better way to approach this?
Thank you very much.
from PIL import Image
import cv2
from win32api import GetSystemMetrics
counter = 0
max_value = input('Max Temp Value: ')
min_value = input('Min Temp Value: ')
def mouse_callback(event, x, y, flags, params): # Tracks the pixel the mouse it hovering on. When right click it prints the pixel location and its RBG values.
global counter
if event == 2:
counter += 1
r, g, b = rgb_img.getpixel((x, y))
print(f'{counter}: {[x, y]} value {r} {g} {b}')
else:
print([x, y], end='\t\r', flush=True)
path_image = 'colors.jpg'
img = cv2.imread(path_image)
im = Image.open(path_image)
rgb_img = im.convert('RGB')
width = GetSystemMetrics(0)
height = GetSystemMetrics(1)
scale_width = width / im.size[0]
scale_height = height / im.size[1]
scale = min(scale_width, scale_height)
window_width = int((im.size[0] * scale) * 0.5)
window_height = int((im.size[1] * scale) * 0.5)
cv2.namedWindow('image', cv2.WINDOW_NORMAL)
cv2.resizeWindow('image', window_width, window_height)
cv2.setMouseCallback('image', mouse_callback)
cv2.imshow('image', img)
cv2.waitKey(0)
cv2.destroyAllWindows()
I am using the same code that is provided by the OpenCv tutorial, it was working few weeks ago, today I was trying to run it is says that gray name is not defined!! can some one find me the error?
import numpy as np
#import matplotlib.pyplot as plt
import cv2
import glob
import os
def draw(img, corners, imgpts):
corner = tuple(corners[0].ravel())
img = cv2.line(img, corner, tuple(imgpts[0].ravel()), (255,0,0), 5)
img = cv2.line(img, corner, tuple(imgpts[1].ravel()), (0,255,0), 5)
img = cv2.line(img, corner, tuple(imgpts[2].ravel()), (0,0,255), 5)
return img
# termination criteria
criteria = (cv2.TERM_CRITERIA_EPS + cv2.TERM_CRITERIA_MAX_ITER, 30, 0.001)
# prepare object points, like (0,0,0), (1,0,0), (2,0,0) ....,(6,5,0)
objp = np.zeros((7*7,3), np.float32)
objp[:,:2] = np.mgrid[0:7,0:7].T.reshape(-1,2)
# Arrays to store object points and image points from all the images.
objpoints = [] # 3d point in real world space
imgpoints = [] # 2d points in image plane.
img_dir = "C:\\Hungary\\Biblography\\Rotating Solitary Wave\\My Work\\Final Work\\Experiment1111 \\Camera Calibration\\Image Processing\\chess"
data_path = os.path.join(img_dir,'*bmp')
images = glob.glob(data_path)
for fname in images:
img = cv2.imread(fname)
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
# Find the chess board corners
ret, corners = cv2.findChessboardCorners(gray, (7,7),None)
# If found, add object points, image points (after refining them)
if ret == True:
objpoints.append(objp)
corners2 = cv2.cornerSubPix(gray,corners,(11,11),(-1,-1),criteria)
imgpoints.append(corners2)
# Draw and display the corners
img = cv2.drawChessboardCorners(img, (7,7), corners2,ret)
cv2.imshow('img',img)
cv2.waitKey(500)
cv2.destroyAllWindows()
ret, mtx, dist, rvecs, tvecs = cv2.calibrateCamera(objpoints, imgpoints, gray.shape [::-1],None,None)
print('Rotation Vector, or the Angles For Each Photo: ', rvecs, '\n')
R = cv2.Rodrigues(rvecs[0])
print('The Rotation Matrix is: ', R)
print('Translation Vector: ', tvecs, '\n')
print(mtx, '\n')
print('Distortion Coefficients ', dist, '\n')
img = cv2.imread('00000274.bmp')
h, w = img.shape[:2]
newcameramtx, roi=cv2.getOptimalNewCameraMatrix(mtx,dist,(w,h),1,(w,h))
print('Camera Matrix', newcameramtx, '\n')
# undistort
dst = cv2.undistort(img, mtx, dist) #, None, newcameramtx)
p = np.ones_like(dst)
# crop the image
x,y,w,h = roi
dst = dst[y:y+h, x:x+w]
# undistort
mapx,mapy = cv2.initUndistortRectifyMap(mtx,dist,None,newcameramtx,(w,h),5)
dst = cv2.remap(img,mapx,mapy,cv2.INTER_LINEAR)
# crop the image
x,y,w,h = roi
dst = dst[y:y+h, x:x+w]
cv2.imwrite('calibresult.png',dst)
mean_error = 0
for i in range(len(objpoints)):
imgpoints2, _ = cv2.projectPoints(objpoints[i], rvecs[i], tvecs[i], mtx, dist)
error = cv2.norm(imgpoints[i],imgpoints2, cv2.NORM_L2)/len(imgpoints2)
mean_error += error
print("total error: ", mean_error/len(objpoints))
If you read the opencv document you will find that I did little changes on the code and it was working but today it is raising this error about the gray name is not defined!
Check your path once, and see if images is an empty list. In that case, for loop will not be executed where the gray variable is defined.
I'm trying to remove numbers which are laying inside the circular part of image, numbers are in black in color and background varies between red,yellow, blue and green.
I am using opencv to remove those numbers. I used a mask which extracts numbers from image, with help of cv2.inpaint tried to remove those numbers from images.
For my further analysis I required to have clear image. But my current approach gives distorted image and numbers are not completely removed.
I tried changing the threshold values, lowering will neglect numbers from dark shaded area such as from green and red.
import cv2
img = cv2.imread('scan_1.jpg')
mask = cv2.threshold(img,50,255,cv2.THRESH_BINARY_INV)[1][:,:,0]
cv2.imshow('mask', mask)
cv2.waitKey(0)
cv2.destroyAllWindows()
dst = cv2.inpaint(img, mask, 5, cv2.INPAINT_TELEA)
cv2.imshow('dst',dst)
cv2.waitKey(0)
cv2.destroyAllWindows()
cv2.imwrite('ost_1.jpg',dst)
Input images: a) scan_1.jpg
b) scan_2.jpg
Output images: a) ost_1.jpg
b) ost_2.jpg
Expected Image: Circles can ignored, but something similar to it is required.
Here is my attempt, a better/easier solution might be acquired if you do not care about preserving texts outside of your circle.
import cv2
import numpy as np
# connectivity method used for finding connected components, 4 vs 8
CONNECTIVITY = 4
# HSV threshold for finding black pixels
H_THRESHOLD = 179
S_THRESHOLD = 255
V_THRESHOLD = 150
# read image
img = cv2.imread("a1.jpg")
img_height = img.shape[0]
img_width = img.shape[1]
# save a copy for creating resulting image
result = img.copy()
# convert image to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# found the circle in the image
circles = cv2.HoughCircles(gray, cv2.HOUGH_GRADIENT, 1.7, minDist= 100, param1 = 48, param2 = 100, minRadius=70, maxRadius=100)
# draw found circle, for visual only
circle_output = img.copy()
# check if we found exactly 1 circle
num_circles = len(circles)
print("Number of found circles:{}".format(num_circles))
if (num_circles != 1):
print("invalid number of circles found ({}), should be 1".format(num_circles))
exit(0)
# save center position and radius of found circle
circle_x = 0
circle_y = 0
circle_radius = 0
if circles is not None:
# convert the (x, y) coordinates and radius of the circles to integers
circles = np.round(circles[0, :]).astype("int")
for (x, y, radius) in circles:
circle_x, circle_y, circle_radius = (x, y, radius)
cv2.circle(circle_output, (circle_x, circle_y), circle_radius, (255, 0, 0), 4)
print("circle center:({},{}), radius:{}".format(x,y,radius))
# keep a median filtered version of image, will be used later
median_filtered = cv2.medianBlur(img, 21)
# Convert BGR to HSV
hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
# define range of black color in HSV
lower_val = np.array([0,0,0])
upper_val = np.array([H_THRESHOLD,S_THRESHOLD,V_THRESHOLD])
# Threshold the HSV image to get only black colors
mask = cv2.inRange(hsv, lower_val, upper_val)
# find connected components
components = cv2.connectedComponentsWithStats(mask, CONNECTIVITY, cv2.CV_32S)
# apply median filtering to found components
#centers = components[3]
num_components = components[0]
print("Number of found connected components:{}".format(num_components))
labels = components[1]
stats = components[2]
for i in range(1, num_components):
left = stats[i, cv2.CC_STAT_LEFT] - 10
top = stats[i, cv2.CC_STAT_TOP] - 10
width = stats[i, cv2.CC_STAT_WIDTH] + 10
height = stats[i, cv2.CC_STAT_HEIGHT] + 10
# iterate each pixel and replace them if
#they are inside circle
for row in range(top, top+height+1):
for col in range(left, left+width+1):
dx = col - circle_x
dy = row - circle_y
if (dx*dx + dy*dy <= circle_radius * circle_radius):
result[row, col] = median_filtered[row, col]
# smooth the image, may be necessary?
#result = cv2.blur(result, (3,3))
# display image(s)
cv2.imshow("img", img)
cv2.imshow("gray", gray)
cv2.imshow("found circle:", circle_output)
cv2.imshow("mask", mask)
cv2.imshow("result", result)
cv2.waitKey(0)
cv2.destroyAllWindows()
Result for a1:
I wanna convert this shape to triangles mesh using shapely in order to be used later as a 3d surface in unity3d, but the result seems is not good, because the triangles mesh cover areas outside this shape.
def get_complex_shape(nb_points = 10):
nb_shifts = 2
nb_lines = 0
shift_parameter = 2
r = 1
xy = get_points(0, 0, r, nb_points)
xy = np.array(xy)
shifts_indices = np.random.randint(0, nb_points ,nb_shifts) # choose random points
if(nb_shifts > 0):
xy[shifts_indices] = get_shifted_points(shifts_indices, nb_points, r + shift_parameter, 0, 0)
xy = np.append(xy, [xy[0]], axis = 0) # close the circle
x = xy[:,0]
y = xy[:,1]
if(nb_lines < 1): # normal circles
tck, u = interpolate.splprep([x, y], s=0)
unew = np.arange(0, 1.01, 0.01) # from 0 to 1.01 with step 0.01 [the number of points]
out = interpolate.splev(unew, tck) # a circle of 101 points
out = np.array(out).T
else: # lines and curves
out = new_add_random_lines(xy, nb_lines)
return out
enter code here
data = get_complex_shape(8)
points = MultiPoint(data)
union_points = cascaded_union(points)
triangles = triangulate(union_points)
This link is for the picture:
the blue picture is the polygon that I want to convert it to mesh of triangles, the right picture is the mesh of triangles which cover more than the inner area of the polygon. How could I cover just the inner area of the polygon?
Template matching in OpenCV is great. And you can pass a mask to cv2.minMaxLoc so that you only search (sort of) in part of the image for the template you want. You can also use a mask at the matchTemplate operation, but this only masks the template.
I want to find a template and I want to be assured that this template is within some other region of my image.
Calculating the mask for minMaxLoc seems kind of heavy. That is, calculating an accurate mask feels heavy. If you calculate a mask the easy way, it ignores the size of the template.
Examples are in order. My input images are show below. They're a bit contrived. I want to find the candy bar, but only if it's completely inside the white circle of the clock face.
clock1
clock2
template
In clock1, the candy bar is inside the circular clock face and it's a "PASS". But in clock2, the candy bar is only partially inside the face and I want it to be a "FAIL". Here's a code sample for doing it the easy way. I use cv.HoughCircles to find the clock face.
import numpy as np
import cv2
img = cv2.imread('clock1.jpg')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
template = cv2.imread('template.png')
t_h, t_w = template.shape[0:2] # template height and width
# find circle in gray image using Hough transform
circles = cv2.HoughCircles(gray, method = cv2.HOUGH_GRADIENT, dp = 1,
minDist = 150, param1 = 50, param2 = 70,
minRadius = 131, maxRadius = 200)
i = circles[0,0]
x0 = i[0]
y0 = i[1]
r = i[2]
# display circle on color image
cv2.circle(img,(x0, y0), r,(0,255,0),2)
# do the template match
result = cv2.matchTemplate(img, template, cv2.TM_CCOEFF_NORMED)
# finally, here is the part that gets tricky. we want to find highest
# rated match inside circle and we'd like to use minMaxLoc
# make mask by drawing circle on zero array
mask = np.zeros(result.shape, dtype = np.uint8) # minMaxLoc will throw
# error w/o np.uint8
cv2.circle(mask, (x0, y0), r, color = 1, thickness = -1)
# call minMaxLoc
min_val, max_val, min_loc, max_loc = cv2.minMaxLoc(result, mask = mask)
# draw found rectangle on img
if max_val > 0.4: # use 0.4 as threshold for finding candy bar
cv2.rectangle(img, max_loc, (max_loc[0]+t_w, max_loc[1]+t_h), (0,255,0), 4)
cv2.imwrite('output.jpg', img)
output using clock1
output using clock2
finds candy bar even
though part of it is outside circle
So to properly make a mask, I use a bunch of NumPy operations. I make four separate masks (one for each corner of the template bounding box) and then AND them together. I'm not aware of any convenience functions in OpenCV that would do the mask for me. I'm a little nervous that all of the array operations will be expensive. Is there a better way to do this?
h, w = result.shape[0:2]
# make arrays that hold x,y coords
grid = np.indices((h, w))
x = grid[1]
y = grid[0]
top_left_mask = np.hypot(x - x0, y - y0) - r < 0
top_right_mask = np.hypot(x + t_w - x0, y - y0) - r < 0
bot_left_mask = np.hypot(x - x0, y + t_h - y0) - r < 0
bot_right_mask = np.hypot(x + t_w - x0, y + t_h - y0) - r < 0
mask = np.logical_and.reduce((top_left_mask, top_right_mask,
bot_left_mask, bot_right_mask))
mask = mask.astype(np.uint8)
cv2.imwrite('mask.png', mask*255)
Here's what the "fancy" mask looks like:
Seems about right. It cannot be circular because of the template shape. If I run clock2.jpg with this mask I get:
It works. No candy bars are identified. But I wish I could do it in fewer lines of code...
EDIT:
I've done some profiling. I ran 100 cycles of the "easy" way and the "accurate" way and calculated frames per second (fps):
easy way: 12.7 fps
accurate way: 7.8 fps
so there is some price to pay for making the mask with NumPy. These tests were done on a relatively powerful workstation. It could get uglier on more modest hardware...
Method 1: 'mask' image before cv2.matchTemplate
Just for kicks, I tried to make my own mask of the image that I pass to cv2.matchTemplate to see what kind of performance I can achieve. To be clear, this isn't a proper mask -- I set all of the pixels to ignore to one color (black or white). This is to get around the fact only TM_SQDIFF and TM_CORR_NORMED support a proper mask.
#Alexander Reynolds makes a very good point in the comments that some care must be taken if the template image (the thing we're trying to find) has lots of black or lots of white. For many problems, we will know a priori what the template looks like and we can specify a white background or black background.
I use cv2.multiply, which seems to be faster than numpy.multiply. cv2.multiply has the added advantage that it automatically clips the results to the range 0 to 255.
import numpy as np
import cv2
import time
img = cv2.imread('clock1.jpg')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
template = cv2.imread('target.jpg')
t_h, t_w = template.shape[0:2] # template height and width
mask_background = 'WHITE'
start_time = time.time()
for i in range(100): # do 100 cycles for timing
# find circle in gray image using Hough transform
circles = cv2.HoughCircles(gray, method = cv2.HOUGH_GRADIENT, dp = 1,
minDist = 150, param1 = 50, param2 = 70,
minRadius = 131, maxRadius = 200)
i = circles[0,0]
x0 = i[0]
y0 = i[1]
r = i[2]
# display circle on color image
cv2.circle(img,(x0, y0), r,(0,255,0),2)
if mask_background == 'BLACK': # black = 0, white = 255 on grayscale
mask = np.zeros(img.shape, dtype = np.uint8)
elif mask_background == 'WHITE':
mask = 255*np.ones(img.shape, dtype = np.uint8)
cv2.circle(mask, (x0, y0), r, color = (1,1,1), thickness = -1)
img2 = cv2.multiply(img, mask) # element wise multiplication
# values > 255 are truncated at 255
# do the template match
result = cv2.matchTemplate(img2, template, cv2.TM_CCOEFF_NORMED)
# call minMaxLoc
min_val, max_val, min_loc, max_loc = cv2.minMaxLoc(result)
# draw found rectangle on img
if max_val > 0.4:
cv2.rectangle(img, max_loc, (max_loc[0]+t_w, max_loc[1]+t_h), (0,255,0), 4)
fps = 100/(time.time()-start_time)
print('fps ', fps)
cv2.imwrite('output.jpg', img)
Profiling results:
BLACK background 12.3 fps
WHITE background 12.1 fps
Using this method has very little performance hit relative to 12.7 fps in original question. However, it has the drawback that it will still find templates that still stick over the edge a little bit. Depending on the exact nature of the problem, this may be acceptable in many applications.
Method 2: use cv2.boxFilter to create mask for minMaxLoc
In this technique, we start with a circular mask (as in OP), but then modify it with cv2.boxFilter. We change the anchor from default center of kernel to the top left corner (0, 0)
import numpy as np
import cv2
import time
img = cv2.imread('clock1.jpg')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
template = cv2.imread('target.jpg')
t_h, t_w = template.shape[0:2] # template height and width
print('t_h, t_w ', t_h, ' ', t_w)
start_time = time.time()
for i in range(100):
# find circle in gray image using Hough transform
circles = cv2.HoughCircles(gray, method = cv2.HOUGH_GRADIENT, dp = 1,
minDist = 150, param1 = 50, param2 = 70,
minRadius = 131, maxRadius = 200)
i = circles[0,0]
x0 = i[0]
y0 = i[1]
r = i[2]
# display circle on color image
cv2.circle(img,(x0, y0), r,(0,255,0),2)
# do the template match
result = cv2.matchTemplate(img, template, cv2.TM_CCOEFF_NORMED)
# finally, here is the part that gets tricky. we want to find highest
# rated match inside circle and we'd like to use minMaxLoc
# start to make mask by drawing circle on zero array
mask = np.zeros(result.shape, dtype = np.float)
cv2.circle(mask, (x0, y0), r, color = 1, thickness = -1)
mask = cv2.boxFilter(mask,
ddepth = -1,
ksize = (t_w, t_h),
anchor = (0,0),
normalize = True,
borderType = cv2.BORDER_ISOLATED)
# mask now contains values from zero to 1. we want to make anything
# less than 1 equal to zero
_, mask = cv2.threshold(mask, thresh = 0.9999,
maxval = 1.0, type = cv2.THRESH_BINARY)
mask = mask.astype(np.uint8)
# call minMaxLoc
min_val, max_val, min_loc, max_loc = cv2.minMaxLoc(result, mask = mask)
# draw found rectangle on img
if max_val > 0.4:
cv2.rectangle(img, max_loc, (max_loc[0]+t_w, max_loc[1]+t_h), (0,255,0), 4)
fps = 100/(time.time()-start_time)
print('fps ', fps)
cv2.imwrite('output.jpg', img)
This code gives a mask identical to OP, but at 11.89 fps. This technique gives us more accuracy with slightly more performance hit than Method 1.