How to crop a square image from normalized vertices - python-3.x

I'm using this code to identify tops and bottoms of photographs:
( as of now I only have it working for tops. one thing at a time ;) )
def get_file(path):
client = vision.ImageAnnotatorClient()
for images in os.listdir(path):
# # Loads the image into memory
with io.open(images, "rb") as image_file:
content = image_file.read()
image = types.Image(content=content)
objects = client.object_localization(image=image).localized_object_annotations
im = Image.open(images)
width, height = im.size
print("Number of objects found: {}".format(len(objects)))
for object_ in objects:
if object_.name == "Top":
print("Top")
l1 = object_.bounding_poly.normalized_vertices[0].x
l2 = object_.bounding_poly.normalized_vertices[0].y
l3 = object_.bounding_poly.normalized_vertices[2].x
l4 = object_.bounding_poly.normalized_vertices[3].y
left = l1 * width
top = l2 * height
right = l3 * width
bottom = l4 * height
im = im.crop((left, top, right, bottom))
im.save('new_test_cropped.tif', 'tiff')
im.show()
if __name__ == '__main__':
parser = argparse.ArgumentParser(description="Script to automatically crop images based on google vision predictions of 'tops' and 'bottoms'")
parser.add_argument('--path', help='Include the path to the images folder')
args = parser.parse_args()
get_file(args.path)
The images are opened, clothing is identified, and then the images are cropped and saved to a new file. (granted as of now they are being overwritten within the loop, but I'll fix that later)
What I cant figure out, is how to make the crop a 1:1 ratio. I need to save them out as square-cropped to be put on our website.
I'll be honest, the normalized_vertices make no sense to me. Hence why I'm having trouble.
Starting image:
Output:
Desired Output:

"Normalized" means the coordinates are divided by the width or height of the image, so normalized coordinates [1, 0.5] would indicate all the way (1) across the image and halfway down (0.5).
For a 1:1 aspect ratio you want right - left to be equal to top - bottom. So you want to find out which dimension (width or height) you need to increase, and by how much.
height = abs(top - bottom)
width = abs(right - left)
extrawidth = max(0, height - width)
extraheight = max(0, width - height)
If height > width, we want to increase width but not height. Since height - width > 0, the correct value will go into extrawidth. But because width - height < 0, extraheight will be 0.
Now let's say we want to increase the dimensions of our image symmetrically around the original crop rectangle.
top -= extraheight // 2
bottom += extraheight // 2
left -= extrawidth // 2
right += extrawidth // 2
And finally, do the crop:
im = im.crop((left, top, right, bottom))
For your image, let's say you get left = 93, right = 215, top = 49, and bottom = 205
Before:
After:

Related

Rasterising only selected area of a CAD DXF file

Given a DXF file (2D CAD drawing), is it somehow possible to rasterise only part of it? Preferably in Python's ezdxf. By the part of it, I mean the selected rectangular area, not a single layer.
Background: I'm struggling to rasterise quite a big DXF file with decent DPI in a reasonable time, so I thought that maybe there's a way to speed up the process by parallelising rasterising different parts of the drawing. I'm using ezdxf with matplotlib backend.
This solution renders the DXF file in 4 tiles including filtering the DXF entities outside the rendering area. But the calculation of the bounding boxes is also costly and the entities in the overlapping area are rendered multiple times, this means this solution takes longer as a single-pass rendering. But it shows the concept. The images fit perfect together the space is left to show that this are 4 images:
import matplotlib.pyplot as plt
import random
import ezdxf
from ezdxf.addons.drawing import RenderContext, Frontend
from ezdxf.addons.drawing.matplotlib import MatplotlibBackend
from ezdxf import bbox
from ezdxf.math import BoundingBox2d
COLORS = list(range(1, 7))
DPI = 300
WIDTH = 400
HEIGHT = 200
LEFT = 0
BOTTOM = 0
doc = ezdxf.new()
msp = doc.modelspace()
def random_points(count):
for _ in range(count):
yield WIDTH * random.random(), HEIGHT * random.random()
for s, e in zip(random_points(100), random_points(100)):
msp.add_line(s, e, dxfattribs={"color": random.choice(COLORS)})
# detecting the drawing extents by ezdxf can take along time for big files!
cache = bbox.Cache() # reuse bounding boxes for entity filtering
rect = bbox.extents(msp, cache=cache)
WIDTH = rect.size.x
HEIGHT = rect.size.y
LEFT = rect.extmin.x
BOTTOM = rect.extmin.y
VIEWPORT_X = [LEFT, LEFT + WIDTH / 2, LEFT, LEFT + WIDTH / 2]
VIEWPORT_Y = [BOTTOM, BOTTOM, BOTTOM + HEIGHT / 2, BOTTOM + HEIGHT / 2]
ctx = RenderContext(doc)
for quarter in [0, 1, 2, 3]:
# setup drawing add-on:
fig = plt.figure(dpi=300)
ax = fig.add_axes([0, 0, 1, 1])
out = MatplotlibBackend(ax)
# calculate and set render borders:
left = VIEWPORT_X[quarter]
bottom = VIEWPORT_Y[quarter]
ax.set_xlim(left, left + WIDTH / 2)
ax.set_ylim(bottom, bottom + HEIGHT / 2)
# set entities outside of the rendering area invisible:
# Bounding box calculation can be very costly, especially for deep nested
# block references! If you did the extents calculation and reuse the cache
# you already have paid the price:
render_area = BoundingBox2d(
[(left, bottom), (left + WIDTH / 2, bottom + HEIGHT / 2)])
for entity in msp:
entity_bbox = bbox.extents([entity], cache=cache)
if render_area.intersect(entity_bbox):
entity.dxf.invisible = 0
else:
entity.dxf.invisible = 1
# finalizing invokes auto-scaling!
Frontend(ctx, out).draw_layout(msp, finalize=False)
# set output size in inches
# width = 6 in x 300 dpi = 1800 px
# height = 3 in x 300 dpi = 900 px
fig.set_size_inches(6, 3, forward=True)
filename = f"lines{quarter}.png"
print(f'saving to "{filename}"')
fig.savefig(filename, dpi=300)
plt.close(fig)
The draw_layout() method has an argument filter_func to specify a function which accepts a DXF entity as argument and returns True or False to render or ignore this entity. This would be an alternative to filter the entities outside of the rendering area without altering the DXF content.
UPDATE: a refined example can be found at github

How to translate points on image after cropping it and resizing it?

I am creating a program which allows a user to annotate images with points.
This program allows user to zoom in an image so user can annotate more precisely.
Program zooms in an image doing the following:
Find the center of image
Find minimum and maximum coordinates of new cropped image relative to center
Crop image
Resize the image to original size
For this I have written the following Python code:
import cv2
def zoom_image(original_image, cut_off_percentage, list_of_points):
height, width = original_image.shape[:2]
center_x, center_y = int(width/2), int(height/2)
half_new_width = center_x - int(center_x * cut_off_percentage)
half_new_height = center_y - int(center_y * cut_off_percentage)
min_x, max_x = center_x - half_new_width, center_x + half_new_width
min_y, max_y = center_y - half_new_height, center_y + half_new_height
#I want to include max coordinates in new image, hence +1
cropped = original_image[min_y:max_y+1, min_x:max_x+1]
new_height, new_width = cropped.shape[:2]
resized = cv2.resize(cropped, (width, height))
translate_points(list_of_points, height, width, new_height, new_width, min_x, min_y)
I want to resize the image to original width and height so user always works on same "surface"
regardless of how zoomed image is.
The problem I encounter is how to correctly scale points (annotations) when doing this. My algorithm to do so was following:
Translate points on original image by subtracting min_x from x coordinate and min_y from y coordinate
Calculate constants for scaling x and y coordinates of points
Multiply coordinates by constants
For this I use the following Python code:
import cv2
def translate_points(list_of_points, height, width, new_height, new_width, min_x, min_y):
#Calculate constants for scaling points
scale_x, scale_y = width / new_width, height / new_height
#Translate and scale points
for point in list_of_points:
point.x = (point.x - min_x) * scale_x
point.y = (point.y - min_y) * scale_y
This code doesn't work. If I zoom in once, it is hard to detect the offset of pixels but it happens. If I keep zooming in, it will be much easier to detect the "drift" of points. Here are images to provide examples. On original image (1440x850) I places a point in the middle of blue crosshair. The more I zoom in the image it is easier to see that algorithm doesn't work with bigger cut-ofs.
Original image. Blue crosshair is middle point of an image. Red angles indicate what will be borders after image is zoomed once
Image after zooming in once.
Image after zooming in 5 times. Clearly, green point is no longer in the middle of image
The cut_off_percentage I used is 15% (meaning that I keep 85% of width and height of original image, calculated from the center).
I have also tried the following library: Augmentit python library
Library has functions for cropping images and resizing them together with points. Library also causes the points to drift. This is expected since the code I implemented and library's functions use the same algorithm.
Additionally, I have checked whether this is a rounding problem. It is not. Library rounds the points after multiplying coordinates with scales. Regardless on how they are rounded, points are still off by 4-5 px. This increases the more I zoom in the picture.
EDIT: A more detailed explanation is given here since I didn't understand a given answer.
The following is an image of right human hand.
Image of a hand in my program
Original dimension of this image is 1440 pixels in width and 850 pixels in height. As you can see in this image, I have annotated right wrist at location (756.0, 685.0). To check whether my program works correctly, I have opened this exact image in GIMP and placed a white point at location (756.0, 685.0). The result is following:
Image of a hand in GIMP
Coordinates in program work correctly. Now, if I were to calculate parameters given in first answer according to code given in first answer I get following:
vec = [756, 685]
hh = 425
hw = 720
cov = [720, 425]
These parameters make sense to me. Now I want to zoom the image to scale of 1.15. I crop the image by choosing center point and calculating low and high values which indicate what rectangle of image to keep and what to cut. On the following image you can see what is kept after cutting (everything inside red rectangle).
What is kept when cutting
Lows and highs when cutting are:
xb = [95,1349]
yb = [56,794]
Size of cropped image: 1254 x 738
This cropped image will be resized back to original image. However, when I do that my annotation gets completely wrong coordinates when using parameters described above.
After zoom
This is the code I used to crop, resize and rescale points, based on the first answer:
width, height = image.shape[:2]
center_x, center_y = int(width / 2), int(height / 2)
scale = 1.15
scaled_width = int(center_x / scale)
scaled_height = int(center_y / scale)
xlow = center_x - scaled_width
xhigh = center_x + scaled_width
ylow = center_y - scaled_height
yhigh = center_y + scaled_height
xb = [xlow, xhigh]
yb = [ylow, yhigh]
cropped = image[yb[0]:yb[1], xb[0]:xb[1]]
resized = cv2.resize(cropped, (width, height), cv2.INTER_CUBIC)
#Rescaling poitns
cov = (width / 2, height / 2)
width, height = resized.shape[:2]
hw = width / 2
hh = height / 2
for point in points:
x, y = point.scx, point.scy
x -= xlow
y -= ylow
x -= cov[0] - (hw / scale)
y -= cov[1] - (hh / scale)
x *= scale
y *= scale
x = int(x)
y = int(y)
point.set_coordinates(x, y)
So this really is an integer rounding issue. It's magnified at high zoom levels because being off by 1 pixel at 20x zoom throws you off much further. I tried out two versions of my crop-n-zoom gui. One with int rounding, another without.
You can see that the one with int rounding keeps approaching the correct position as the zoom grows, but as soon as the zoom takes another step, it rebounds back to being wrong. The non-rounded version sticks right up against the mid-lines (denoting the proper position) the whole time.
Note that the resized rectangle (the one drawn on the non-zoomed image) blurs past the midlines. This is because of the resize interpolation from OpenCV. The yellow rectangle that I'm using to check that my points are correctly scaling is redrawn on the zoomed frame so it stays crisp.
With Int Rounding
Without Int Rounding
I have the center-of-view locked to the bottom right corner of the rectangle for this demo.
import cv2
import numpy as np
# clamp value
def clamp(val, low, high):
if val < low:
return low;
if val > high:
return high;
return val;
# bound the center-of-view
def boundCenter(cov, scale, hh, hw):
# scale half res
scaled_hw = int(hw / scale);
scaled_hh = int(hh / scale);
# bound
xlow = scaled_hw;
xhigh = (2*hw) - scaled_hw;
ylow = scaled_hh;
yhigh = (2*hh) - scaled_hh;
cov[0] = clamp(cov[0], xlow, xhigh);
cov[1] = clamp(cov[1], ylow, yhigh);
# do a zoomed view
def zoomView(orig, cov, scale, hh, hw):
# calculate crop
scaled_hh = int(hh / scale);
scaled_hw = int(hw / scale);
xlow = cov[0] - scaled_hw;
xhigh = cov[0] + scaled_hw;
ylow = cov[1] - scaled_hh;
yhigh = cov[1] + scaled_hh;
xb = [xlow, xhigh];
yb = [ylow, yhigh];
# crop and resize
copy = np.copy(orig);
crop = copy[yb[0]:yb[1], xb[0]:xb[1]];
display = cv2.resize(crop, (width, height), cv2.INTER_CUBIC);
return display;
# draw vector shape
def drawVec(img, vec, pos, cov, hh, hw, scale):
con = [];
for point in vec:
# unpack point
x,y = point;
x += pos[0];
y += pos[1];
# here's the int version
# Note: this is the same as xlow and ylow from the above function
# x -= cov[0] - int(hw / scale);
# y -= cov[1] - int(hh / scale);
# rescale point
x -= cov[0] - (hw / scale);
y -= cov[1] - (hh / scale);
x *= scale;
y *= scale;
x = int(x);
y = int(y);
# add
con.append([x,y]);
con = np.array(con);
cv2.drawContours(img, [con], -1, (0,200,200), -1);
# font stuff
font = cv2.FONT_HERSHEY_SIMPLEX;
fontScale = 1;
fontColor = (255, 100, 0);
thickness = 2;
# draw blank
res = (800,1200,3);
blank = np.zeros(res, np.uint8);
print(blank.shape);
# draw a rectangle on the original
cv2.rectangle(blank, (100,100), (400,200), (200,150,0), -1);
# vectored shape
# comparison shape
bshape = [[100,100], [400,100], [400,200], [100,200]];
bpos = [0,0]; # offset
# random shape
vshape = [[148, 89], [245, 179], [299, 67], [326, 171], [385, 222], [291, 235], [291, 340], [229, 267], [89, 358], [151, 251], [57, 167], [167, 164]];
vpos = [100,100]; # offset
# get original image res
height, width = blank.shape[:2];
hh = int(height / 2);
hw = int(width / 2);
# center of view
cov = [600, 400];
camera_spd = 5;
# scale
scale = 1;
scale_step = 0.2;
# loop
done = False;
while not done:
# crop and show image
display = zoomView(blank, cov, scale, hh, hw);
# drawVec(display, vshape, vpos, cov, hh, hw, scale);
drawVec(display, bshape, bpos, cov, hh, hw, scale);
# draw a dot in the middle
cv2.circle(display, (hw, hh), 4, (0,0,255), -1);
# draw center lines
cv2.line(display, (hw,0), (hw,height), (0,0,255), 1);
cv2.line(display, (0,hh), (width,hh), (0,0,255), 1);
# draw zoom text
cv2.putText(display, "Zoom: " + str(scale), (15,40), font,
fontScale, fontColor, thickness, cv2.LINE_AA);
# show
cv2.imshow("Display", display);
key = cv2.waitKey(1);
# check keys
done = key == ord('q');
# Note: if you're actually gonna make a GUI
# use the keyboard module or something else for this
# wasd to move center-of-view
if key == ord('d'):
cov[0] += camera_spd;
if key == ord('a'):
cov[0] -= camera_spd;
if key == ord('w'):
cov[1] -= camera_spd;
if key == ord('s'):
cov[1] += camera_spd;
# z,x to decrease/increase zoom (lower bound is 1.0)
if key == ord('x'):
scale += scale_step;
if key == ord('z'):
scale -= scale_step;
scale = round(scale, 2);
# bound cov
boundCenter(cov, scale, hh, hw);
Edit: Explanation of the drawVec parameters
img: The OpenCV image to be drawn on
vec: A list of [x,y] points
pos: The offset to draw those points at
cov: Center-Of-View, where the middle of our zoomed display is pointed at
hh: Half-Height, the height of "img" divided by 2
hw: Half-Width, the width of "img" divided by 2
I have looked through my code and realized where I was making a mistake which caused points to be offset.
In my program, I have a canvas of specific size. The size of canvas is a constant and is always larger than images being drawn on canvas. When program draws an image on canvas it first resizes that image so it could fit on canvas. The size of resized image is somewhat smaller than size of canvas. Image is usually drawn starting from top left corner of canvas. Since I wanted to always draw image in the center of canvas, I shifted the location from top left corner of canvas to another point. This is what I didn't account when doing image zooming.
def zoom(image, ratio, points, canvas_off_x, canvas_off_y):
width, height = image.shape[:2]
new_width, new_height = int(ratio * width), int(ratio * height)
center_x, center_y = int(new_width / 2), int(new_height / 2)
radius_x, radius_y = int(width / 2), int(height / 2)
min_x, max_x = center_x - radius_x, center_x + radius_x
min_y, max_y = center_y - radius_y, center_y + radius_y
img_resized = cv2.resize(image, (new_width,new_height), interpolation=cv2.INTER_LINEAR)
img_cropped = img_resized[min_y:max_y+1, min_x:max_x+1]
for point in points:
x, y = point.get_original_coordinates()
x -= canvas_off_x
y -= canvas_off_y
x = int((x * ratio) - min_x + canvas_off_x)
y = int((y * ratio) - min_y + canvas_off_y)
point.set_scaled_coordinates(x, y)
In the code below canvas_off_x and canvas_off_y is the location of offset from top left corner of canvas

How to resize image by mainitaining aspect ratio in python3?

I have an image with image.shape=(20,10)and I want to resize this image so that new image size would be image.size = 90.
I want to use np.resize(image,(new_width, new_height)), but how can I calculate new_width and new_height, so that it maintains aspect_ratio as same as in original image.
Well, you choose which dimension you want to enforce and then you adjust the other one by calculating either new_width = new_height*aspect_ratio or new_height = new_width/aspect_ratio.
You might want to round those numbers and convert them to int too.
The height of your image is 20 and the width is 10, so the height is 2x the width, i.e.
h = 2 * w
You want your new image to have an area of 90 pixels, and the area (A) is:
A = h * w
90 = 2 * w * w
w = sqrt(45)
So the sides of your image need to be 6.7 and 13.4
I hope that helps, even if I doubt it will.
You can use this simple function for finding the new height of an image with width as an input
def findHeight(original_width, original_height, new_width):
area = original_width * original_height
new_height = area/new_width
return new_height

Template Matching: efficient way to create mask for minMaxLoc?

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.

Centering a rotated image using Reportlab

I'm trying to center a rotated image on Reportlab, but I'm having issues using the correct calculation for the placement.
Here's the current code:
from reportlab.pdfgen import canvas
from reportlab.lib.utils import ImageReader
from PIL import Image as PILImage
import requests
import math
def main(rotation):
# create a new PDF with Reportlab
a4 = (595.275590551181, 841.8897637795275)
c = canvas.Canvas('output.pdf', pagesize=a4)
c.saveState()
# loading the image:
img = requests.get('https://i.stack.imgur.com/dI5Rj.png', stream=True)
img = PILImage.open(img.raw)
width, height = img.size
# We calculate the bouding box of a rotated rectangle
angle_radians = rotation * (math.pi / 180)
bounding_height = abs(width * math.sin(angle_radians)) + abs(height * math.cos(angle_radians))
bounding_width = abs(width * math.cos(angle_radians)) + abs(height * math.sin(angle_radians))
a4_pixels = [x * (100 / 75) for x in a4]
offset_x = (a4_pixels[0] / 2) - (bounding_width / 2)
offset_y = (a4_pixels[1] / 2) - (bounding_height / 2)
c.translate(offset_x, offset_y)
c.rotate(rotation)
c.drawImage(ImageReader(img), 0, 0, width, height, 'auto')
c.restoreState()
c.save()
if __name__ == '__main__':
main(45)
So far, here's what I did:
Calculating the boundaries of a rotated rectangle (since it will be bigger)
Using these to calculate the position of the center of the image (size / 2 - image / 2) for width and height.
Two issues appears that I can't explain:
The "a4" variable is in points, everything else is in pixels. If I change them to pixels for calculating the position (which is logical, using a4_pixels = [x * (100 / 75) for x in a4]). The placement is incorrect for a rotation of 0 degree. If I keep the a4 in points, it works ... ?
If I change the rotation, it breaks even more.
So my final question: How can I calculate the offset_x and offset_y values to ensure it's always centered regardless of the rotation?
Thank you! :)
When you translate the canvas, you are literally moving the origin (0,0) point and all draw operations will be relative to that.
So in the code below, I moved the origin to the middle of the page.
Then I rotated the "page" and drew the image on the "page". No need to rotate the image since its canvas axes have rotated.
from reportlab.pdfgen import canvas
from reportlab.lib.utils import ImageReader
from reportlab.lib.pagesizes import A4
from PIL import Image as PILImage
import requests
def main(rotation):
c = canvas.Canvas('output.pdf', pagesize=A4)
c.saveState()
# loading the image:
img = requests.get('https://i.stack.imgur.com/dI5Rj.png', stream=True)
img = PILImage.open(img.raw)
# The image dimensions in cm
width, height = img.size
# now move the canvas origin to the middle of the page
c.translate(A4[0] / 2, A4[1] / 2)
# and rotate it
c.rotate(rotation)
# now draw the image relative to the origin
c.drawImage(ImageReader(img), -width/2, -height/2, width, height, 'auto')
c.restoreState()
c.save()
if __name__ == '__main__':
main(45)

Resources