I've written a program about color detection by using python. But always there's an error around the 'Erode' sentence. Here's part of my program. Thank you.
# Convert the image to a Numpy array since most cv2 functions
# require Numpy arrays.
frame = np.array(frame, dtype=np.uint8)
threshold = 0.05
#blur the image
frame=cv2.blur(frame, (5,5))
#Convert from BGR to HSV
hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)
#split into 3
h, s, v= cv2.split(hsv)
#red color
s = cv2.threshold(h, 15, 1, cv2.THRESH_BINARY_INV)#1-15,x>15 y=0
h = cv2.threshold(h, 245, 1, cv2.THRESH_BINARY)#245-255 x>245 y=1
h = h + s
kernel = cv2.getStructuringElement(cv2.MORPH_RECT,(3, 3))
h = cv2.erode(h, kernel)
v = cv2.sumElems(h)
Try:
_,h = cv2.threshold(h, 245, 1, cv2.THRESH_BINARY) #245-255 x>245 y=1
_,s = cv2.threshold(h, 15, 1, cv2.THRESH_BINARY_INV) #1-15,x>15 y=0
cv2.threshold
returns two values:
http://docs.opencv.org/modules/imgproc/doc/miscellaneous_transformations.html#cv2.threshold
cv2.threshold(src, thresh, maxval, type[, dst]) → retval, dst
You miss the second value dst
, omitting that in the expression, you're only getting the retval
value which is not an image.
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With