英文:
How to crop an image with upto 6 tissue samples using OpenCV?
问题
我有一个来自公共数据集的图像（示例如下）。我想使用工具将两个组织样本分开，以增加数据集中的实例数量。数据集中的其他图像最多有6个组织。是否可以使用OpenCV来实现这一点？也欢迎其他工具。
我尝试过从一篇博客中找到的方法，但它只是在整个图像周围创建了一个边界框。也许阈值方案效果不好。
import cv2# 读取输入图像img = cv2.imread('pic.png')# 将图像转换为灰度gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)# 在灰度图像上应用阈值处理以创建二进制图像ret, thresh = cv2.threshold(gray, 127, 255, 0)# 查找轮廓contours, _ = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)# 获取第一个轮廓cnt = contours[0]# 计算轮廓的边界矩形x, y, w, h = cv2.boundingRect(cnt)# 绘制轮廓gray = cv2.drawContours(gray, [cnt], 0, (0, 255, 255), 2)# 绘制边界矩形gray = cv2.rectangle(gray, (x, y), (x+w, y+h), (0, 255, 0), 2)# 显示带有绘制边界矩形的图像cv2.imshow("Bounding Rectangle", gray)cv2.waitKey(0)cv2.destroyAllWindows()
英文:
I have an image from a public dataset (sample show below). I want to separate the two tissue samples using a tool to increase the number of instances in the dataset. Other images in the dataset have upto 6 tissues. Is there I can do that using OpenCV? Other tools are also welcomed.
I tried this from one of the blogs I came across but it just creates a bounding box around the entire image. Maybe the thresholding scheme doesn't work well
import cv2# read the input imageimg = cv2.imread('pic.png')# convert the image to grayscalegray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)# apply thresholding on the gray image to create a binary imageret,thresh = cv2.threshold(gray,127,255,0)# find the contourscontours, _ = cv2.findContours(gray,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)# take the first contourcnt = contours[0]# compute the bounding rectangle of the contourx,y,w,h = cv2.boundingRect(cnt)# draw contourgray = cv2.drawContours(gray,[cnt],0,(0,255,255),2)# draw the bounding rectanglegray = cv2.rectangle(gray,(x,y),(x+w,y+h),(0,255,0),2)# display the image with bounding rectangle drawn on itcv2.imshow("Bounding Rectangle", gray)cv2.waitKey(0)cv2.destroyAllWindows()
答案1
得分: 1
以下是翻译好的代码部分：
# 导入OpenCV库import cv2# 读取输入图像img = cv2.imread('pic.png')# 将图像转换为灰度图gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)# 在灰度图上应用阈值处理以创建二值图像# ret, thresh = cv2.threshold(gray, 127, 255, 0)# ret, thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_OTSU + cv2.THRESH_BINARY_INV) # 反转极性 - findContours需要白色轮廓ret, thresh = cv2.threshold(gray, 230, 255, cv2.THRESH_BINARY_INV) # 反转极性 - findContours需要白色轮廓# 在cv2.findContours之前考虑添加形态学闭运算。# 查找轮廓# contours, _ = cv2.findContours(gray, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE) # 为什么使用灰度图？contours, _ = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE) # 使用RETR_EXTERNAL而不是RETR_TREE - 我们不想找到嵌套的轮廓，只需外部轮廓# 取第一个轮廓# cnt = contours[0] # 为什么是第一个？第一个可能是微小的轮廓gray_as_bgr = cv2.cvtColor(gray, cv2.COLOR_GRAY2BGR) # 在绘制之前准备BGR图像# 迭代所有轮廓for cnt in contours:area = cv2.contourArea(cnt) # 计算面积if area > 1000: # 忽略像素少于1000的轮廓 - 被视为噪声。# 计算轮廓的边界矩形x, y, w, h = cv2.boundingRect(cnt)# 绘制轮廓gray_as_bgr = cv2.drawContours(gray_as_bgr, [cnt], 0, (0, 255, 255), 2)# 绘制边界矩形gray_as_bgr = cv2.rectangle(gray_as_bgr, (x, y), (x+w, y+h), (0, 255, 0), 2) # 绘制绿色矩形# 显示带有绘制的边界矩形的图像cv2.imshow("thresh", thresh)cv2.imshow("Bounding Rectangle", gray_as_bgr)cv2.waitKey(0)cv2.destroyAllWindows()
这是您提供的代码的翻译部分。
英文:
There are multiple issues:
-
findContoursexpects white contours on black background - we have to invert polarity (and also select higher threshold):ret, thresh = cv2.threshold(gray, 230, 255, cv2.THRESH_BINARY_INV)
-
contours, _ = cv2.findContours(grayis a bug - it should becontours, _ = cv2.findContours(thresh(find contours inthresh). -
Use
cv2.RETR_EXTERNALinstead ofcv2.RETR_TREE- we don't want to find nested contours, only the outer contour:contours, _ = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
-
cnt = contours[0]return the first contour that may be tiny, we have to iterate all contours. -
We better filter contours by area - ignore small contours that are considered to be noise.
Code sample:
import cv2# read the input imageimg = cv2.imread('pic.png')# convert the image to grayscalegray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)# apply thresholding on the gray image to create a binary image#ret, thresh = cv2.threshold(gray, 127, 255, 0)#ret, thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_OTSU + cv2.THRESH_BINARY_INV) # Invert polarity - findContours expects white contoursret, thresh = cv2.threshold(gray, 230, 255, cv2.THRESH_BINARY_INV) # Invert polarity - findContours expects white contours# Consider adding morphological closing before cv2.findContours.# find the contours#contours, _ = cv2.findContours(gray, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE) # Why gray?contours, _ = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE) # Use RETR_EXTERNAL instead of RETR_TREE - we don't want to find nested contours, only the outer contour# take the first contour#cnt = contours[0] # Why the first? The fist may be a tiny contourgray_as_bgr = cv2.cvtColor(gray, cv2.COLOR_GRAY2BGR) # Prepare BGR image before drawing# Iterate all contoursfor cnt in contours:area = cv2.contourArea(cnt) # Compute the areaif area > 1000: # Ignore contours with less than 1000 pixels - considered to be noise.# compute the bounding rectangle of the contourx, y, w, h = cv2.boundingRect(cnt)# draw contourgray_as_bgr = cv2.drawContours(gray_as_bgr, [cnt], 0, (0, 255, 255), 2)# draw the bounding rectanglegray_as_bgr = cv2.rectangle(gray_as_bgr, (x, y), (x+w, y+h), (0, 255, 0), 2) # Draw green rectangles# display the image with bounding rectangle drawn on itcv2.imshow("thresh", thresh)cv2.imshow("Bounding Rectangle", gray_as_bgr)cv2.waitKey(0)cv2.destroyAllWindows()
Output gray_as_bgr:
通过集体智慧和协作来改善编程学习和解决问题的方式。致力于成为全球开发者共同参与的知识库，让每个人都能够通过互相帮助和分享经验来进步。
评论