operands could not be broadcast together with shapes (193,261,3) (132,132,1)

Question

I'm doing skin detection in which I took the image and detected the face then on that image I used canny edge detection to detect all the edges and now I want to subtract ie image -canny so that I only get the skin part

gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

faceCascade = cv2.CascadeClassifier(cv2.data.haarcascades + "haarcascade_frontalface_default.xml")
faces = faceCascade.detectMultiScale(
    gray,
    scaleFactor=1.01,
    minNeighbors=3,
    minSize=(60, 60)
)


for (x, y, w, h) in faces:
    cv2.rectangle(image, (x, y), (x + w, y + h), (0, 255, 0), 2)
    roi_color = image[y:y + h, x:x + w] 
    cv2.imwrite(str(w) + str(h) + '_faces.jpg', roi_color)

status = cv2.imwrite('faces_detected.jpg', image)
cv2_imshow(image)

--- then performing canny edge detection

img = cv2.imread("132132_faces.jpg")
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
canny = cv2.Canny(img, 100, 200)

now im trying to  do 
np.subtract(canny,image)
 to get the non skin part but since they have different shape 
canny (132,132)
image (193, 261, 3)
i tried to add a new axis to canny so that they both becomes 3d but still getting the error
operands could not be broadcast together with shapes (193,261,3) (132,132,1)

`image` has 3 channels while `canny` has 1 channel. `np.subtract()` needs two images with same number of channels to work — Jeru Luke, Jun 01 '22 at 11:26
I don't know how far subtracting edges will get you, try color segmentation: https://stackoverflow.com/questions/10948589/choosing-the-correct-upper-and-lower-hsv-boundaries-for-color-detection-withcv/ — Jeru Luke, Jun 01 '22 at 11:36

operands could not be broadcast together with shapes (193,261,3) (132,132,1)

0 Answers0