如何将 roi 提取为单个 roi 图像 [关闭]

Question

我的图像在透明图像中包含多个 rois //非矩形//。请帮助我如何将这些 rois 提取为单个 roi 图像

Answer 1

1. 找到图片的contours。

---

import cv2

img = cv2.imread("gzgSI.jpg")
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(gray, 127, 255, 0)
contours, hierarchy = cv2.findContours(thresh,
                                       cv2.RETR_TREE,
                                       cv2.CHAIN_APPROX_SIMPLE)

for cnt in contours:
    cv2.drawContours(img, [cnt], 0, (0, 255, 0), 3)

结果：

1. 现在我们确定，我们已经检测到图像中的所有轮廓，我们可以单独保存它们。

   • 获取每个contour的坐标

     for i, cnt in enumerate(contours):
         x, y, width, height = cv2.boundingRect(cnt)
     

   • 设置图片中的坐标

     roi = img[y:y+height, x:x+width]
     

   • 一些示例结果：

• 确保在运行代码之前已创建rois 文件夹。

代码：

import cv2

img = cv2.imread("gzgSI.jpg")
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(gray, 127, 255, 0)
contours, hierarchy = cv2.findContours(thresh,
                                       cv2.RETR_TREE,
                                       cv2.CHAIN_APPROX_SIMPLE)

for i, cnt in enumerate(contours):
    x, y, width, height = cv2.boundingRect(cnt)
    roi = img[y:y+height, x:x+width]
    cv2.imwrite("rois/roi{}.png".format(i), roi)

Answer 2

import numpy as np
import matplotlib.pyplot as plt

!mkdir /content/test
!rm -r /content/test/*
image = cv2.imread('/content/test.png')
original = image.copy()
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
blurred = cv2.GaussianBlur(gray, (3, 3), 0)
canny = cv2.Canny(blurred, 120, 255, 1)
kernel = np.ones((5,5),np.uint8)
dilate = cv2.dilate(canny, kernel, iterations=1)

# Find contours
cnts = cv2.findContours(dilate, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]

# Iterate thorugh contours and filter for ROI
image_number = 0
for c in cnts:
    x,y,w,h = cv2.boundingRect(c)
    #cv2.rectangle(image, (x, y), (x + w, y + h), (36,255,12), 2)
    ROI = original[y:y+h, x:x+w]
    #cv2.imwrite("/content/test/ROI_{}.png".format(image_number), ROI)
    image_number += 1

## (4) Create mask and do bitwise-op
mask = np.zeros(image.shape[:2],np.uint8)
cv2.drawContours(mask, [c],-1, 255, -1)
dst = cv2.bitwise_and(image, image, mask=mask)

## Save it
#cv2.imwrite("dst.png", dst)
cv2.imwrite("/content/test/ROI_{}.png".format(image_number), dst)
image_number += 1



# cv2.imshow('canny', canny)
# cv2.imshow('image', image)
# cv2.waitKey(0)

plt.imshow(canny)
plt.imshow(image)here