https://code.visualstudio.com/updates/v1_8#_node-debugging
https://code.visualstudio.com/updates/v1_8#_node-debugging
https://code.visualstudio.com/updates/v1_8#_node-debugging
https://code.visualstudio.com/updates/v1_8#_node-debugging
import cv2
import numpy as np
#== Parameters =======================================================================
BLUR = 21
CANNY_THRESH_1 = 10
CANNY_THRESH_2 = 200
MASK_DILATE_ITER = 10
MASK_ERODE_ITER = 10
MASK_COLOR = (0.0,0.0,1.0) # In BGR format
#== Processing =======================================================================
#-- Read image -----------------------------------------------------------------------
img = cv2.imread('C:/Temp/person.jpg')
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
#-- Edge detection -------------------------------------------------------------------
edges = cv2.Canny(gray, CANNY_THRESH_1, CANNY_THRESH_2)
edges = cv2.dilate(edges, None)
edges = cv2.erode(edges, None)
#-- Find contours in edges, sort by area ---------------------------------------------
contour_info = []
_, contours, _ = cv2.findContours(edges, cv2.RETR_LIST, cv2.CHAIN_APPROX_NONE)
# Previously, for a previous version of cv2, this line was:
# contours, _ = cv2.findContours(edges, cv2.RETR_LIST, cv2.CHAIN_APPROX_NONE)
# Thanks to notes from commenters, I've updated the code but left this note
for c in contours:
contour_info.append((
c,
cv2.isContourConvex(c),
cv2.contourArea(c),
))
contour_info = sorted(contour_info, key=lambda c: c[2], reverse=True)
max_contour = contour_info[0]
#-- Create empty mask, draw filled polygon on it corresponding to largest contour ----
# Mask is black, polygon is white
mask = np.zeros(edges.shape)
cv2.fillConvexPoly(mask, max_contour[0], (255))
#-- Smooth mask, then blur it --------------------------------------------------------
mask = cv2.dilate(mask, None, iterations=MASK_DILATE_ITER)
mask = cv2.erode(mask, None, iterations=MASK_ERODE_ITER)
mask = cv2.GaussianBlur(mask, (BLUR, BLUR), 0)
mask_stack = np.dstack([mask]*3) # Create 3-channel alpha mask
#-- Blend masked img into MASK_COLOR background --------------------------------------
mask_stack = mask_stack.astype('float32') / 255.0 # Use float matrices,
img = img.astype('float32') / 255.0 # for easy blending
masked = (mask_stack * img) + ((1-mask_stack) * MASK_COLOR) # Blend
masked = (masked * 255).astype('uint8') # Convert back to 8-bit
cv2.imshow('img', masked) # Display
cv2.waitKey()
#cv2.imwrite('C:/Temp/person-masked.jpg', masked) # Save
import cv2
import numpy as np
img = cv2.imread("C:/my_pics/rahul.png")
blurred_img = cv2.GaussianBlur(img, (21, 21), 0)
mask = np.zeros((512, 512, 3), dtype=np.uint8)
mask = cv2.circle(mask, (258, 258), 100, np.array([255, 255, 255]), -1)
out = np.where(mask==np.array([255, 255, 255]), img, blurred_img)
cv2.imwrite("./out.png", out)
The decimal keyword indicates a 128-bit data type. Compared to floating-point types, the decimal type has more precision and a smaller range, which makes it appropriate for financial and monetary calculations.
You can use a decimal as follows:
decimal myMoney = 300.5m;
class MyClass
{
public string A { get; set; }
public string B { get; set; }
public string C { get; set; }
public MyClass()
{
int count = this.GetType().GetProperties().Count();
// or
count = typeof(MyClass).GetProperties().Count();
}
}
Certainly! Here are 10 advanced .NET Core interview questions covering various topics: 1. **ASP.NET Core Middleware Pipeline**: Explain the...