我正在使用 python 3 和最新版本的 openCV。我正在尝试使用提供的调整大小功能调整图像大小,但调整大小后图像非常扭曲。代码:
import cv2
file = "/home/tanmay/Desktop/test_image.png"
img = cv2.imread(file , 0)
print(img.shape)
cv2.imshow('img' , img)
k = cv2.waitKey(0)
if k == 27:
cv2.destroyWindow('img')
resize_img = cv2.resize(img , (28 , 28))
cv2.imshow('img' , resize_img)
x = cv2.waitKey(0)
if x == 27:
cv2.destroyWindow('img')
原始图像是 480 x 640(RGB 因此我传递了 0 将其转换为灰度)
有什么方法可以调整它的大小并避免使用 OpenCV 或任何其他库的扭曲吗?我打算制作一个手写数字识别器,并且我已经使用 MNIST 数据训练了我的神经网络,因此我需要图像为 28x28。
您可以尝试以下。该功能将保持原始图像的纵横比。
def image_resize(image, width = None, height = None, inter = cv2.INTER_AREA):
# initialize the dimensions of the image to be resized and
# grab the image size
dim = None
(h, w) = image.shape[:2]
# if both the width and height are None, then return the
# original image
if width is None and height is None:
return image
# check to see if the width is None
if width is None:
# calculate the ratio of the height and construct the
# dimensions
r = height / float(h)
dim = (int(w * r), height)
# otherwise, the height is None
else:
# calculate the ratio of the width and construct the
# dimensions
r = width / float(w)
dim = (width, int(h * r))
# resize the image
resized = cv2.resize(image, dim, interpolation = inter)
# return the resized image
return resized
这是一个示例用法。
image = image_resize(image, height = 800)
如果您需要修改图像分辨率并保持纵横比,请使用功能imutils(查看文档)。像这样的东西:
img = cv2.imread(file , 0)
img = imutils.resize(img, width=1280)
cv2.imshow('image' , img)
希望有帮助,祝你好运!
在使用 OpenCV 的 python 中尝试这个简单的函数。只需传递图像并提及您想要的正方形的大小即可。
def resize_image(img, size=(28,28)):
h, w = img.shape[:2]
c = img.shape[2] if len(img.shape)>2 else 1
if h == w:
return cv2.resize(img, size, cv2.INTER_AREA)
dif = h if h > w else w
interpolation = cv2.INTER_AREA if dif > (size[0]+size[1])//2 else
cv2.INTER_CUBIC
x_pos = (dif - w)//2
y_pos = (dif - h)//2
if len(img.shape) == 2:
mask = np.zeros((dif, dif), dtype=img.dtype)
mask[y_pos:y_pos+h, x_pos:x_pos+w] = img[:h, :w]
else:
mask = np.zeros((dif, dif, c), dtype=img.dtype)
mask[y_pos:y_pos+h, x_pos:x_pos+w, :] = img[:h, :w, :]
return cv2.resize(mask, size, interpolation)
用途: squared_image=get_square(图像, 大小=(28,28))
说明: 函数接受任何尺寸的输入,并创建一个方形空白图像,其尺寸为图像的高度或宽度,以较大者为准。 然后它将原始图像放置在空白图像的中心。然后它将这个方形图像调整为所需的大小,以便保留原始图像内容的形状。
希望这对你有帮助
所有其他答案都使用 pad 来校正纵横比,当您尝试为神经网络创建标准化数据集时,这通常非常糟糕。下面是裁剪和调整大小的简单实现,它保持纵横比并且不创建焊盘。
def crop_square(img, size, interpolation=cv2.INTER_AREA):
h, w = img.shape[:2]
min_size = np.amin([h,w])
# Centralize and crop
crop_img = img[int(h/2-min_size/2):int(h/2+min_size/2), int(w/2-min_size/2):int(w/2+min_size/2)]
resized = cv2.resize(crop_img, (size, size), interpolation=interpolation)
return resized
示例:
img2 = crop_square(img, 300)
原文:
调整大小:
@vijay jha 提供的答案过于具体。还包括额外的不必要的填充。我建议下面的固定代码:
def resize2SquareKeepingAspectRation(img, size, interpolation):
h, w = img.shape[:2]
c = None if len(img.shape) < 3 else img.shape[2]
if h == w: return cv2.resize(img, (size, size), interpolation)
if h > w: dif = h
else: dif = w
x_pos = int((dif - w)/2.)
y_pos = int((dif - h)/2.)
if c is None:
mask = np.zeros((dif, dif), dtype=img.dtype)
mask[y_pos:y_pos+h, x_pos:x_pos+w] = img[:h, :w]
else:
mask = np.zeros((dif, dif, c), dtype=img.dtype)
mask[y_pos:y_pos+h, x_pos:x_pos+w, :] = img[:h, :w, :]
return cv2.resize(mask, (size, size), interpolation)
该代码调整图像大小,使其成为正方形并同时保持纵横比。该代码也适用于 3 通道(彩色)图像。 使用示例:
resized = resize2SquareKeepingAspectRation(img, size, cv2.INTER_AREA)
import cv2
def resize_and_letter_box(image, rows, cols):
"""
Letter box (black bars) a color image (think pan & scan movie shown
on widescreen) if not same aspect ratio as specified rows and cols.
:param image: numpy.ndarray((image_rows, image_cols, channels), dtype=numpy.uint8)
:param rows: int rows of letter boxed image returned
:param cols: int cols of letter boxed image returned
:return: numpy.ndarray((rows, cols, channels), dtype=numpy.uint8)
"""
image_rows, image_cols = image.shape[:2]
row_ratio = rows / float(image_rows)
col_ratio = cols / float(image_cols)
ratio = min(row_ratio, col_ratio)
image_resized = cv2.resize(image, dsize=(0, 0), fx=ratio, fy=ratio)
letter_box = np.zeros((int(rows), int(cols), 3))
row_start = int((letter_box.shape[0] - image_resized.shape[0]) / 2)
col_start = int((letter_box.shape[1] - image_resized.shape[1]) / 2)
letter_box[row_start:row_start + image_resized.shape[0], col_start:col_start + image_resized.shape[1]] = image_resized
return letter_box
img = cv2.resize(img, (int(img.shape[1]/2), int(img.shape[0]/2)))
会将图像大小调整为原始大小的一半。您可以将其修改为任何其他比率。 请注意,传递给 resize() 的第一个参数是 img.shape[1],而不是 img.shape[0]。这可能是违反直觉的。人们很容易忽视这种逆转并得到非常扭曲的画面。
def crop_and_resize(img, w, h):
im_h, im_w, channels = img.shape
res_aspect_ratio = w/h
input_aspect_ratio = im_w/im_h
if input_aspect_ratio > res_aspect_ratio:
im_w_r = int(input_aspect_ratio*h)
im_h_r = h
img = cv2.resize(img, (im_w_r , im_h_r))
x1 = int((im_w_r - w)/2)
x2 = x1 + w
img = img[:, x1:x2, :]
if input_aspect_ratio < res_aspect_ratio:
im_w_r = w
im_h_r = int(w/input_aspect_ratio)
img = cv2.resize(img, (im_w_r , im_h_r))
y1 = int((im_h_r - h)/2)
y2 = y1 + h
img = img[y1:y2, :, :]
if input_aspect_ratio == res_aspect_ratio:
img = cv2.resize(img, (w, h))
return img
感谢
@vijay jha,我创建了方形图像,同时保持了原始图像的纵横比。但有一个问题是,规模缩小得越多,丢失的信息就越多。
512x256 到 64x64 看起来像这样:
我修改了一些原始代码以平滑地缩小图像。
from skimage.transform import resize, pyramid_reduce
def get_square(image, square_size):
height, width = image.shape
if(height > width):
differ = height
else:
differ = width
differ += 4
# square filler
mask = np.zeros((differ, differ), dtype = "uint8")
x_pos = int((differ - width) / 2)
y_pos = int((differ - height) / 2)
# center image inside the square
mask[y_pos: y_pos + height, x_pos: x_pos + width] = image[0: height, 0: width]
# downscale if needed
if differ / square_size > 1:
mask = pyramid_reduce(mask, differ / square_size)
else:
mask = cv2.resize(mask, (square_size, square_size), interpolation = cv2.INTER_AREA)
return mask
512x256 -> 64x64
512x256 -> 28x28
window_height
,通过它计算
window_width
变量,同时保持图像的长宽比。以免变形。
import cv2
def resize(self,image,window_height = 500):
aspect_ratio = float(image.shape[1])/float(image.shape[0])
window_width = window_height/aspect_ratio
image = cv2.resize(image, (int(window_height),int(window_width)))
return image
img = cv2.imread(img_source) #image location
img_resized = resize(img,window_height = 800)
cv2.imshow("Resized",img_resized)
cv2.waitKey(0)
cv2.destroyAllWindows()
Pillow
lib的简单且最有效的方法 这里
width
或
height
将是
400
from PIL import Image
imgPath = './forest.jpg'
img = Image.open(imgPath)
print('The size of img is: ', img.size)
print('After applying thumbnail() function')
img.thumbnail((400, 400))
img.save('image_thumbnail.jpg')
import cv2
import imutils
import numpy as np
def resize(image, to_height, to_width):
result = np.ones((to_height, to_width, 3), dtype = np.uint8)
result = 255 * result
if image.shape[0] > image.shape[1]:
new_img = imutils.resize(image, width=to_width)
dy = int((to_height - new_img.shape[0]) / 2)
result[dy:dy + new_img.shape[0], 0 : new_img.shape[1]] = new_img
else:
new_img = imutils.resize(image, height=to_height)
dx = int((to_width - new_img.shape[1]) / 2)
result[0:new_img.shape[0], dx : dx + new_img.shape[1]] = new_img
return result
image = cv2.imread('./sample.jpg')
image = resize(image, to_height=300, to_width=400)
print(image.shape)
cv2.imshow('Sample', image)
cv2.waitKey(0)