如何从图像中删除方括号？答案

【问题标题】：How to remove square brackets from an image?如何从图像中删除方括号？
【发布时间】：2020-10-25 13:32:33
【问题描述】：

我有这张图片：raw

我想从这张图片中删除方括号。我已经来了这么远：

# Import packages 
import cv2
import numpy as np

#Create MSER object
mser = cv2.MSER_create()

#Your image path i-e receipt path
img = cv2.imread('uky.JPG')

#Convert to gray scale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

vis = img.copy()

#detect regions in gray scale image
regions, _ = mser.detectRegions(gray)

hulls = [cv2.convexHull(p.reshape(-1, 1, 2)) for p in regions]

cv2.polylines(vis, hulls, 1, (0, 255, 0))

cv2_imshow(vis)

mask = np.zeros((img.shape[0], img.shape[1], 1), dtype=np.uint8)

for contour in hulls:

    cv2.drawContours(mask, [contour], -1, (255, 255, 255), -1)

#this is used to find only text regions, remaining are ignored
text_only = cv2.bitwise_and(img, img, mask=mask)

cv2_imshow(text_only)

此代码的结果：detected

预期输出：expected

但我不知道如何删除方括号。我确信这是一个如此简单的问题，但由于我对 OpenCV 不熟悉，所以我几个小时都无法解决这个问题。

如果有人可以向我解释这一点，我会非常高兴。非常感谢您。

【问题讨论】：

我认为你需要使用shape detection（虽然我对openCV不太熟悉:)）

标签： python numpy opencv image-processing computer-vision

【解决方案1】：

这是 Python/OpenCV 中的一种方法。获取轮廓并过滤纵横比和面积。在白色背景上将剩余的轮廓绘制为黑色。

输入：

import cv2
import numpy as np

#Read input image
img = cv2.imread('brackets.jpg')

# threshold on black
lower =(0,0,0) 
upper = (50,50,50) 
thresh = cv2.inRange(img, lower, upper)

# find contours and get one with area about 180*35
contours = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]

# filter contours on aspect ratio and area
max_aspect = 3.7
min_aspect = 0.7
min_area = 15
result = np.full_like(img, (255,255,255))
for cntr in contours:
    area = cv2.contourArea(cntr)
    x,y,w,h = cv2.boundingRect(cntr)
    aspect = h/w
    if aspect > min_aspect and aspect < max_aspect and area > min_area:
            cv2.drawContours(result, [cntr], -1, (0, 0, 0), 2)

# save result
cv2.imwrite("brackets_thresh.jpg", thresh)
cv2.imwrite("brackets_removed.jpg", result)

# show images
cv2.imshow("THRESH", thresh)
cv2.imshow("RESULT", result)
cv2.waitKey(0)

阈值图像：

结果：

【讨论】：