cropping images in python

Question

I'm trying to detect a face and then crop it to use it in a face recognition algorithm. Here is my code.

import numpy as np
import cv2
import Image

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

img = cv2.imread('xD.jpg')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
faces = face_cascade.detectMultiScale(gray, 1.3, 5)
for (x,y,w,h) in faces:
    img = cv2.rectangle(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]
    print x
    print y
    print w
    print h
    img.crop((x,y,w,h))
cv2.imshow('img',img)
cv2.waitKey(0)
cv2.destroyAllWindows()

When I print (x,y,w,h), it gives precise coordinates, but when I crop it, it gives me this error.

img.crop((x,y,w,h))
AttributeError: 'numpy.ndarray' object has no attribute 'crop'

roi_color = img[y:y+h, x:x+w] is the cropped image already. — berak
– berak, Commented Feb 29, 2016 at 22:40

Mr Mohamed · Accepted Answer · 2016-02-29 23:16:50Z

1

import numpy as np
import cv2
from PIL import Image

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

img = cv2.imread('xD.jpg')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
faces = face_cascade.detectMultiScale(gray, 1.3, 5)
for (x,y,w,h) in faces:
    img = cv2.rectangle(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]
    cropped = img[y:y+h, x:x+w]
cv2.imwrite("thumbnail.png", cropped)
cv2.imshow("cropped", cropped)
cv2.waitKey(0)

answered Feb 29, 2016 at 23:16

Mr Mohamed

4641 gold badge5 silver badges12 bronze badges

Sign up to request clarification or add additional context in comments.

Collectives™ on Stack Overflow

cropping images in python

1 Answer 1

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

Comments

Your Answer

Sign up or log in

Post as a guest

Related