如何在OpenCV中使用Python裁剪图像

如何裁剪图像,就像我以前在PIL中所做的那样,使用OpenCV。

PIL工作示例

im = Image.open('0.png').convert('L')
im = im.crop((1, 1, 98, 33))
im.save('_0.png')

但是我怎么在OpenCV上做呢?

这就是我所尝试的:

im = cv.imread('0.png', cv.CV_LOAD_IMAGE_GRAYSCALE)
(thresh, im_bw) = cv.threshold(im, 128, 255, cv.THRESH_OTSU)
im = cv.getRectSubPix(im_bw, (98, 33), (1, 1))
cv.imshow('Img', im)
cv.waitKey(0)

但这并不奏效。

我想我错误地使用了getRectSubPix。如果是这样,请解释我如何正确使用这个功能。

912202 次浏览

这很简单。使用numpy切片。

import cv2
img = cv2.imread("lenna.png")
crop_img = img[y:y+h, x:x+w]
cv2.imshow("cropped", crop_img)
cv2.waitKey(0)

我有这个问题,在这里找到了另一个答案:感兴趣的复制区域

如果我们将(0,0)视为图像im的左上角,从左到右为x方向,从上到下为y方向。我们有(x1,y1)作为图像中一个矩形区域的左上角顶点(x2,y2)作为右下角顶点,那么:

roi = im[y1:y2, x1:x2]

这里有一个关于Numpy数组索引和切片的综合资源,它可以告诉你更多关于裁剪图像部分的事情。图像将在opencv2中存储为numpy数组。

:)

下面是一些更健壮的收割代码(有点像matlab)

def imcrop(img, bbox):
x1,y1,x2,y2 = bbox
if x1 < 0 or y1 < 0 or x2 > img.shape[1] or y2 > img.shape[0]:
img, x1, x2, y1, y2 = pad_img_to_fit_bbox(img, x1, x2, y1, y2)
return img[y1:y2, x1:x2, :]


def pad_img_to_fit_bbox(img, x1, x2, y1, y2):
img = np.pad(img, ((np.abs(np.minimum(0, y1)), np.maximum(y2 - img.shape[0], 0)),
(np.abs(np.minimum(0, x1)), np.maximum(x2 - img.shape[1], 0)), (0,0)), mode="constant")
y1 += np.abs(np.minimum(0, y1))
y2 += np.abs(np.minimum(0, y1))
x1 += np.abs(np.minimum(0, x1))
x2 += np.abs(np.minimum(0, x1))
return img, x1, x2, y1, y2

健壮的农作物与opencv复制边界功能:

def imcrop(img, bbox):
x1, y1, x2, y2 = bbox
if x1 < 0 or y1 < 0 or x2 > img.shape[1] or y2 > img.shape[0]:
img, x1, x2, y1, y2 = pad_img_to_fit_bbox(img, x1, x2, y1, y2)
return img[y1:y2, x1:x2, :]


def pad_img_to_fit_bbox(img, x1, x2, y1, y2):
img = cv2.copyMakeBorder(img, - min(0, y1), max(y2 - img.shape[0], 0),
-min(0, x1), max(x2 - img.shape[1], 0),cv2.BORDER_REPLICATE)
y2 += -min(0, y1)
y1 += -min(0, y1)
x2 += -min(0, x1)
x1 += -min(0, x1)
return img, x1, x2, y1, y2

注意,图像切片不是创建cropped image的副本,而是创建roipointer。如果加载这么多图像,用切片裁剪图像的相关部分,然后追加到一个列表中,这可能是巨大的内存浪费。

假设你加载N张图片,每张图片都是>1MP,你只需要左上角的100x100区域。

Slicing:

X = []
for i in range(N):
im = imread('image_i')
X.append(im[0:100,0:100]) # This will keep all N images in the memory.
# Because they are still used.

或者,你可以通过.copy()复制相关部分,这样垃圾收集器就会删除im

X = []
for i in range(N):
im = imread('image_i')
X.append(im[0:100,0:100].copy()) # This will keep only the crops in the memory.
# im's will be deleted by gc.

在发现这一点之后,我意识到其中一个评论是通过user1270710提到了这一点,但它花了我相当长的时间才找到(即调试等)。所以,我认为值得一提。

这段代码将图像从x=0,y=0裁剪到h=100,w=200。

import numpy as np
import cv2


image = cv2.imread('download.jpg')
y=0
x=0
h=100
w=200
crop = image[y:y+h, x:x+w]
cv2.imshow('Image', crop)
cv2.waitKey(0)

下面是裁剪图像的方法。

image_path:要编辑图像的路径

坐标: x/y坐标(x1, y1, x2, y2)的元组[打开图像在 Mspaint和检查“标尺”在视图标签中查看坐标]

saved_location:保存裁剪图像的路径

from PIL import Image
def crop(image_path, coords, saved_location:
image_obj = Image.open("Path of the image to be cropped")
cropped_image = image_obj.crop(coords)
cropped_image.save(saved_location)
cropped_image.show()




if __name__ == '__main__':
image = "image.jpg"
crop(image, (100, 210, 710,380 ), 'cropped.jpg')

或者,你可以使用tensorflow进行裁剪,使用openCV从图像中生成数组。

import cv2
img = cv2.imread('YOURIMAGE.png')

现在img是一个(imageheight, imagewidth, 3)形状数组。用tensorflow裁剪数组:

import tensorflow as tf
offset_height=0
offset_width=0
target_height=500
target_width=500
x = tf.image.crop_to_bounding_box(
img, offset_height, offset_width, target_height, target_width
)

用tf重新组装图像。Keras,所以我们可以看看它是否有效:

tf.keras.preprocessing.image.array_to_img(
x, data_format=None, scale=True, dtype=None
)

这将在笔记本中打印出图片(在谷歌Colab中测试)。


整个代码放在一起:

import cv2
img = cv2.imread('YOURIMAGE.png')


import tensorflow as tf
offset_height=0
offset_width=0
target_height=500
target_width=500
x = tf.image.crop_to_bounding_box(
img, offset_height, offset_width, target_height, target_width
)


tf.keras.preprocessing.image.array_to_img(
x, data_format=None, scale=True, dtype=None
)

为了让你更容易,这里是我使用的代码:

    top=514
right=430
height= 40
width=100
croped_image = image[top : (top + height) , right: (right + width)]
plt.imshow(croped_image, cmap="gray")
plt.show()

通过使用这个函数,你可以很容易地裁剪图像

def cropImage(Image, XY: tuple, WH: tuple, returnGrayscale=False):
# Extract the x,y and w,h values
(x, y) = XY
(w, h) = WH
# Crop Image with numpy splitting
crop = Image[y:y + h, x:x + w]
# Check if returnGrayscale Var is true if is then convert image to grayscale
if returnGrayscale:
crop = cv2.cvtColor(crop, cv2.COLOR_BGR2GRAY)
# Return cropped image
return crop

希望这能有所帮助

以裁剪或感兴趣的区域(ROI)用于下面的代码

import cv2
face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
image=cv2.imread("ronaldo.jpg")
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
faces = face_cascade.detectMultiScale(gray, 1.3, 5)
for (x,y,w,h) in faces:
cv2.rectangle(img,(x,y),(x+w,y+h),(255,255,0),2)
roi_image = gray[y:y+h, x:x+w]
cv2.imshow("crop/region of interset image",roi_image)
cv2.waitKey(0)
cv2.destroyAllWindows()

check for reference

# Import packages
import cv2


import numpy as np
img = cv2.imread('skewness.png')
print(img.shape) # Print image shape


cv2.imshow("original", img)


# Cropping an image
cropped_image = img[80:280, 150:330]
 

# Display cropped image
cv2.imshow("cropped", cropped_image)


# Save the cropped image
cv2.imwrite("Cropped Image.jpg", cropped_image)


#The function waitKey waits for a key event infinitely (when \f$\texttt{delay}\leq 0\f$ ) or for delay milliseconds, when it is positive
cv2.waitKey(0)


#The function destroyAllWindows destroys all of the opened HighGUI windows.
cv2.destroyAllWindows()