裁剪图像中的所有字符

Question

我整理了一些代码来从图像中提取所有字符。我从左到右对字符进行排序，并尝试将每个字符裁剪到单独的图像中。并非所有字符都被正确裁剪，其中一些最终大小为零。

import cv2
import numpy as np

def crop_minAreaRect(img, rect):
# https://stackoverflow.com/questions/37177811/crop-rectangle-returned-by-minarearect-opencv-python
    # rotate img
    center = rect[0]
    size = rect[1]
    print("size[0]: " + str(int(size[0])) + ", size[1]: " + str(int(size[1])))
    angle = rect[2]
    print("angle: " + str(angle))
    rows,cols = img.shape[0], img.shape[1]
    M = cv2.getRotationMatrix2D((cols/2,rows/2),angle,1)
    img_rot = cv2.warpAffine(img,M,(cols,rows))

    # rotate bounding box
    rect0 = (rect[0], rect[1], angle) 
    box = cv2.boxPoints(rect0)
    pts = np.int0(cv2.transform(np.array([box]), M))[0]    
    pts[pts < 0] = 0

    # crop
    img_crop = img_rot[pts[1][1]:pts[0][1], pts[1][0]:pts[2][0]]

    w, h = img_crop.shape[0], img_crop.shape[1]
    print("w_cropped: " + str(w) + ", h_cropped: " + str(h))
    return img_crop

def sort_contours(cnts, method="left-to-right"):
# from https://pyimagesearch.com/2015/04/20/sorting-contours-using-python-and-opencv/    
    reverse = False
    i = 0
    if method == "right-to-left" or method == "bottom-to-top":
        reverse = True
    if method == "top-to-bottom" or method == "bottom-to-top":
        i = 1
    boundingBoxes = [cv2.boundingRect(c) for c in cnts]
    (cnts, boundingBoxes) = zip(*sorted(zip(cnts, boundingBoxes),   key=lambda b:b[1][i], reverse=reverse))
    return (cnts, boundingBoxes)    
    
im_name = 'letters.png'
im = cv2.imread(im_name)
im_copy = im.copy()

imgray = cv2.cvtColor(im, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(imgray, 127, 255, 0)
contours, hierarchy = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

#cv2.drawContours(im_copy, contours, -1, (0,255,0), 2)
#cv2.imshow("contours", im_copy)

print("num contours: " + str(len(contours)))
i = 0

sorted_cnts, bounding_boxes = sort_contours(contours, method="left-to-right")

for cnt in sorted_cnts:
  size = cv2.contourArea(cnt)
  x,y,w,h = cv2.boundingRect(cnt)
  rect = cv2.minAreaRect(cnt)
#  print(str(rect))
#  if rect[1][0] > 0 and rect[1][1]>0:
  im_cropped = crop_minAreaRect(im, rect)
    
  h,w = im_cropped.shape[0], im_cropped.shape[1]
  if w > h:
    im_cropped = cv2.rotate(im_cropped, cv2.ROTATE_90_CLOCKWISE)  
    
  print("w: " + str(w) + ", h: " + str(h))
  if w>0 and h>0:
    cv2.imshow("cropped" + str(i), im_cropped)
  i += 1
#    cv2.waitKey(0)

cv2.waitKey(0)

Answer 1

您的crop_minAreaRect函数中似乎存在错误。除了返回crop_minAreaRect之外，我没有进一步调试您的代码，因此根据您的方法可能会或可能不会正确旋转字母，但此更改修复了根本问题。
建议的功能取自以下问题并进行了修改：如何在Python中使用OpenCV拉直图像的旋转矩形区域？

import cv2
import numpy as np


def subimage(image, center, theta, width, height):
    '''
   Rotates OpenCV image around center with angle theta (in deg)
   then crops the image according to width and height.
   '''
    width = int(width)
    height = int(height)
    # Uncomment for theta in radians
    # theta *= 180/np.pi

    shape = (image.shape[1], image.shape[0])  # cv2.warpAffine expects shape in (length, height)

    matrix = cv2.getRotationMatrix2D(center=center, angle=theta, scale=1)
    image = cv2.warpAffine(src=image, M=matrix, dsize=shape)

    x = int(center[0] - width / 2)
    y = int(center[1] - height / 2)

    image = image[y:y + height, x:x + width]

    return image


def sort_contours(cnts, method="left-to-right"):
    # from https://pyimagesearch.com/2015/04/20/sorting-contours-using-python-and-opencv/
    reverse = False
    i = 0
    if method == "right-to-left" or method == "bottom-to-top":
        reverse = True
    if method == "top-to-bottom" or method == "bottom-to-top":
        i = 1
    boundingBoxes = [cv2.boundingRect(c) for c in cnts]
    (cnts, boundingBoxes) = zip(*sorted(zip(cnts, boundingBoxes), key=lambda b: b[1][i], reverse=reverse))
    return (cnts, boundingBoxes)


im_name = 'letters.png'
im = cv2.imread(im_name)
im_copy = im.copy()

imgray = cv2.cvtColor(im, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(imgray, 127, 255, 0)
contours, hierarchy = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

cv2.drawContours(im_copy, contours, -1, (0, 255, 0), 2)
cv2.imshow("contours", im_copy)

# print("num contours: " + str(len(contours)))
i = 0

sorted_cnts, bounding_boxes = sort_contours(contours, method="left-to-right")

for cnt in sorted_cnts:
    size = cv2.contourArea(cnt)
    x, y, w, h = cv2.boundingRect(cnt)
    rect = cv2.minAreaRect(cnt)


    im_cropped = subimage(im, center=rect[0], theta=rect[2], width=rect[1][0], height=rect[1][1])

    h, w = im_cropped.shape[0], im_cropped.shape[1]
    if w > h:
        im_cropped = cv2.rotate(im_cropped, cv2.ROTATE_90_CLOCKWISE)

    # print("w: " + str(w) + ", h: " + str(h))
    if w > 0 and h > 0:
        cv2.imshow("cropped" + str(i), im_cropped)
    i += 1
#    cv2.waitKey(0)

cv2.waitKey(0)