error: (-215) scn == 3 || scn == 4 in function cv::cvtColor

python

asked 2016-10-22 00:15:51 -0600

ALOMGEER
11 ●1 ●1 ●2

updated 2016-10-22 01:08:01 -0600

berak
32993 ●7 ●81 ●312

using:

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

i get:

error: ..\..\..\..\opencv\modules\imgproc\src\color.cpp:3739: error: (-215) scn == 3 || scn == 4 in function cv::cvtColor

here's the whole code:

import cv2
import numpy as np

face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
eye_cascade = cv2.CascadeClassifier('haarcascade_eye.xml')

cap = cv2.VideoCapture(1)

while True:
    ret, img = cap.read()
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    faces = face_cascade.detectMultiScale(gray, 1.3, 5)
    for (x, y, w, h) in faces:
        cv2.rectange(img, (x, y), (x+w, y+h), (255, 0, 0), 2)
        roi_gray = gray[y:y+h, x:x+w]
        roi_color = img[y:y+h, x:x+w]
        eyes = eye_cascade.detectMultiScale(roi_gray)
        for (ex, ey, ew, eh) in eyes:
            cv2.rectangle(roi_color, (ex, ey), (ex+ew, ey+eh), (0, 255, 0), 2)
    cv2.imshow('img', img)
    k = cv2.waitKey(30) & 0xFF
    if k == 27:
        break
cap.release()
cv2.destroyALLWindows()

edit retag flag offensive close merge delete

add a comment

3 answers

Sort by » oldest newest most voted

answered 2016-10-22 01:14:19 -0600

berak
32993 ●7 ●81 ●312

updated 2016-10-22 01:25:58 -0600

your img is most likely invalid.

some things to check:

did the capture open ? is 1 the correct id ? (i doubt so, rather try 0). please check:

cap.isOpened() #should return True
did you get a valid frame from your capture ? please check if ret==True

(older webcams might need some "warmup", and you might need to continue, until you receive a valid image)

in general, please make it a habit , to always check, if resources got read/loaded, like from imread(), and also you need to check, if the cascade xml files get ead properly with cascade.empty()

edit flag offensive delete link

Comments

as berak said you need to add a delay before enter the while loop import numpy as np import cv2 import time

cap = cv2.VideoCapture(0)
print(cap.isOpened())
time.sleep(5)
while(True):
# Capture frame-by-frame
ret, frame = cap.read()
print(ret)
# Our operations on the frame come here
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)

# Display the resulting frame
cv2.imshow('frame',gray)
if cv2.waitKey(1) & 0xFF == ord('q'):
    break
When everything done, release the capture
cap.release()
cv2.destroyAllWindows()

VonFausto ( 2017-07-21 17:14:15 -0600 )edit

^^ no , i never said that

also, sleeping will give you a problem, as input images get stuck in the internal queue. (latency)

berak ( 2017-07-21 17:58:12 -0600 )edit

add a comment

answered 2016-10-30 02:05:55 -0600

xiaoerlaigeid
1 ●1

face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
eye_cascade = cv2.CascadeClassifier('haarcascade_eye.xml')

these two is wrong. you should add the path .

 face_cascade =   
 cv2.CascadeClassifier(r'D:\OpenCV\opencv\sources\data\haarcascades\haarcascade_frontalface_default.xml')
 eye_cascade = cv2.CascadeClassifier(r'D:\OpenCV\opencv\sources\data\haarcascades\haarcascade_eye.xml')