将边界框另存为图像

Question

I have some python code that takes in an image of an A4 letter, then draws bounding boxes around each character.

I want to know how to save each bounding box as an image, so essentially it's taking every character it detects and saving it. Preferable as a .png resized to 20x20

(A similar question was asked here but the answer is quite vague and don't know how to implement it in my code)

Here is my code:

import numpy as np
import matplotlib.pyplot as plt
import matplotlib.patches as mpatches
from scipy.misc import imread,imresize
from skimage.segmentation import clear_border
from skimage.morphology import label
from skimage.measure import regionprops


image = imread('./adobe.png',1)

#apply threshold in order to make the image binary
bw = image < 120

# remove artifacts connected to image border
cleared = bw.copy()
clear_border(cleared)

# label image regions
label_image = label(cleared,neighbors=8)
borders = np.logical_xor(bw, cleared)
label_image[borders] = -1

print label_image.max()

fig, ax = plt.subplots(ncols=1, nrows=1, figsize=(6, 6))
ax.imshow(bw, cmap='jet')



for region in regionprops(label_image, ['Area', 'BoundingBox']):
    # skip small images
    if region['Area'] > 50:

        # draw rectangle around segmented coins
        minr, minc, maxr, maxc = region['BoundingBox']
        rect = mpatches.Rectangle((minc, minr), maxc - minc, maxr - minr,
                              fill=False, edgecolor='red', linewidth=2)
        ax.add_patch(rect)

plt.show()

If I'm not clear enough, please comment and I'll try elaborate my best,

Thank you

Answer 1

The question you reference uses findContours from OpenCV, a common library for image manipulation. If you already have the bounding box (in x, y and width, height) then you can simply export using matplotlib or, alternatively opencv:

image_patch = img[minr:maxr, minc:maxc]  # get region of interest (slice)
# .. maybe do some scaling
plt.imsave("filename.png", image_patch)

Alternatively with fig.savefig(path) after rendering it to a figure. Or with opencv:

import cv2
cv2.imsave("path.png", img_patch)

You may want to add suffixes to your file names (and/o checking if the file already exists?) to avoid overwriting.