How to shape-mark images using Python

How to use Python to mark images with shapes

Introduction:

In the fields of image processing and computer vision, objects in images are marked and Identification is an important task. The shape of the marked object can be used for applications such as object detection, edge detection, and contour extraction. This article will introduce how to use Python and the OpenCV library to label images with shapes.

Step 1: Install the required libraries

Before we begin, we need to install the Python and OpenCV libraries. You can install the OpenCV library through the pip command. The specific command is as follows:

pip install opencv-python

Step 2: Import the required libraries

In the code, we need to import the OpenCV library and some other auxiliary libraries. The specific code is as follows:

import cv2
import numpy as np

Step 3: Read the image file

Use the imread() function of the OpenCV library to read the image file. The specific code is as follows:

img = cv2.imread('image.jpg')

Step 4: Convert the image to grayscale image

Before doing shape labeling, we need to convert the image to grayscale image. This can be achieved using the cvtColor() function of the OpenCV library. The specific code is as follows:

gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

Step 5: Threshold segmentation

Threshold segmentation of the grayscale image can obtain a binary image, which facilitates subsequent shape marking operations. This can be achieved using the threshold() function of the OpenCV library. The specific code is as follows:

_, thresh = cv2.threshold(gray, 127, 255, cv2.THRESH_BINARY)

Step 6: Find contours

Use the findContours() function of the OpenCV library to find contours in the image. The specific code is as follows:

contours, _ = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

Step 7: Draw the contour

Use the drawContours() function of the OpenCV library to draw the contour on the image. The specific code is as follows:

cv2.drawContours(img, contours, -1, (0, 255, 0), 3)

Step 8: Display the results

Use the imshow() function of the OpenCV library to display the processed image. The specific code is as follows:

cv2.imshow('Contours', img)
cv2.waitKey(0)
cv2.destroyAllWindows()

Full code example:

import cv2
import numpy as np

# 读取图像文件
img = cv2.imread('image.jpg')

# 将图像转换为灰度图像
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

# 进行阈值分割
_, thresh = cv2.threshold(gray, 127, 255, cv2.THRESH_BINARY)

# 查找轮廓
contours, _ = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

# 绘制轮廓
cv2.drawContours(img, contours, -1, (0, 255, 0), 3)

# 显示结果
cv2.imshow('Contours', img)
cv2.waitKey(0)
cv2.destroyAllWindows()

Conclusion:

This article introduces how to use Python and the OpenCV library to mark images with shapes. By implementing the code example, the contours of objects in the image can be extracted and marked to facilitate subsequent image processing and computer vision applications. Readers can make corresponding adjustments and expansions according to their own needs and actual conditions. Hope this article is helpful to readers!

The above is the detailed content of How to shape-mark images using Python. For more information, please follow other related articles on the PHP Chinese website!