用opencv感兴趣区域提取（圆形区域）

最新推荐文章于 2023-11-24 09:29:36 发布

猫宁大人

最新推荐文章于 2023-11-24 09:29:36 发布

阅读量1.8k

点赞数

文章标签： opencv python 计算机视觉

原文链接：https://blog.csdn.net/linmuquan1989/article/details/126315114?spm=1001.2014.3001.5502

版权

该博客主要介绍了如何利用OpenCV库在Python中处理图像，通过读取图像、灰度转换、二值化、寻找轮廓，最终对直径大于200像素的圆形区域进行提取并保存。具体步骤包括阈值处理、最小外接圆检测以及使用掩模技术进行图像分离。

摘要由CSDN通过智能技术生成

import cv2
import numpy as np
from glob import glob
import os

img_path = glob(r"F:/YjnJiaNing/val/l1/*.jpg")
path_save = r"F:/YjnJiaNing/val/region_of_interest/L1_ROI"

for i, file in enumerate(img_path):
    name = os.path.join(path_save, "%d.png" % i)
    image = cv2.imread(file)
    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
    _, binary = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)
    contours, _ = cv2.findContours(binary, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
    for cont in contours:
        (x, y), radius = cv2.minEnclosingCircle(cont)
        if radius > 200:
            ming = cv2.circle(image, (int(x), int(y)), int(radius), (0, 0, 255), 2)
            print("radius is ")
            print(radius)
            print((x, y))
            roi = np.zeros(image.shape[:2], np.uint8)
            roi = cv2.circle(roi, (int(x), int(y)), int(radius), 255, cv2.FILLED)
            mask = np.ones_like(image) * 255
            mask = cv2.bitwise_and(mask, image, mask=roi) + cv2.bitwise_and(mask, mask, mask=~roi)
            cv2.imwrite(name, mask)
            print(i, name)