• 轮廓发现(16)


    一 函数介绍

    findContours 寻找轮廓

    cv2.findContours(image, mode, method[, contours[, hierarchy[, offset ]]])
    • 参数

    第一个参数是寻找轮廓的图像;

    第二个参数表示轮廓的检索模式,有四种(本文介绍的都是新的cv2接口):
        cv2.RETR_EXTERNAL      表示只检测外轮廓
        cv2.RETR_LIST                 检测的轮廓不建立等级关系
        cv2.RETR_CCOMP           建立两个等级的轮廓,上面的一层为外边界,里面的一层为内孔的边界信息。如果内孔内还有一个连通物体,这个物体的边界也在顶层。
        cv2.RETR_TREE              建立一个等级树结构的轮廓。

    第三个参数method为轮廓的近似办法
        cv2.CHAIN_APPROX_NONE          存储所有的轮廓点,相邻的两个点的像素位置差不超过1,即max(abs(x1-x2),abs(y2-y1))==1
        cv2.CHAIN_APPROX_SIMPLE       压缩水平方向,垂直方向,对角线方向的元素,只保留该方向的终点坐标,例如一个矩形轮廓只需4个点来保存轮廓信息
        cv2.CHAIN_APPROX_TC89_L1,CV_CHAIN_APPROX_TC89_KCOS           使用teh-Chinl chain 近似算法

    • 返回值

    contour  :轮廓要素,列表

    hierarchy:轮廓属性

    cv2.drawContours 绘制轮廓

    drawContours(   image, 
                    contours, 
                    contourIdx, 
                    color, 
                    thickness=None, 
                    lineType=None, 
                    hierarchy=None, 
                    maxLevel=None, 
                    offset=None
                    )

    参数解释

    .   @param image Destination image. 
              绘制到那张图
    .   @param contours All the input contours. Each contour is stored as a point vector.
                有输入轮廓。每个轮廓都存储为点矢量。
    . @param contourIdx Parameter indicating a contour to draw. If it is negative, all the contours are drawn.
              指示要绘制的轮廓的参数。如果是
    negative,则绘制所有轮廓。
    .   @param color Color of the contours.
              绘制线条的颜色
    . @param thickness Thickness of lines the contours are drawn with. If it is negative (for example,
    . thickness=#FILLED ), the contour interiors are drawn.
            绘制的线的宽度,如果为<=0,则表示填充
    . @param lineType Line connectivity. See #LineTypes
    . @param hierarchy Optional information about hierarchy. It is only needed if you want to draw only
    . some of the contours (see maxLevel ).
    . @param maxLevel Maximal level for drawn contours. If it is 0, only the specified contour is drawn.
    . If it is 1, the function draws the contour(s) and all the nested contours. If it is 2, the function
    . draws the contours, all the nested contours, all the nested-to-nested contours, and so on. This
    . parameter is only taken into account when there is hierarchy available.
    . @param offset Optional contour shift parameter. Shift all the drawn contours by the specified
    . f$ exttt{offset}=(dx,dy)f$ .

    三 简单边缘发现代码实现

    代码

    import cv2 as cv
    import numpy as np
    
    
    # 轮廓发现
    def contous_image(image):
        #高斯模糊去除噪点
        dst = cv.GaussianBlur(image, (3, 3), 0)
        gray = cv.cvtColor(dst, cv.COLOR_BGR2GRAY)
        #图像反转
        rev=cv.bitwise_not(gray)
        ret, binary = cv.threshold(rev, 30, 255, cv.THRESH_BINARY | cv.THRESH_OTSU)
        cv.imshow("binary", binary)
        contous, heriachy = cv.findContours(binary, cv.RETR_EXTERNAL, cv.CHAIN_APPROX_SIMPLE)
        for i, contou in enumerate(contous):
            cv.drawContours(image, contous, i, (0, 0, 255), 2,)
        cv.imshow("lunkuo", image)
        for i, contou in enumerate(contous):
            #-1 表示轮廓填充
            cv.drawContours(image, contous, i, (0, 0, 255), -1)
        cv.imshow("lunkuofill", image)
    
    
    src = cv.imread("yingbi.jpg")
    cv.imshow("before", src)
    contous_image(src)
    cv.waitKey(0)
    cv.destroyAllWindows()

    效果展示

    四 基于canny边缘提取的轮廓发现

    代码

    # -*- coding=GBK -*-
    import cv2 as cv
    import numpy as np
    
    
    def edge_demo(image):
        '边缘提取函数'
        blurred=cv.GaussianBlur(image,(3,3),0)
        gray=cv.cvtColor(blurred,cv.COLOR_BGR2GRAY)
        #x Grad
        xgrad=cv.Sobel(gray,cv.CV_16SC1,1,0)
        ygrad=cv.Sobel(gray,cv.CV_16SC1,0,1)
        #边缘提取
        # edge_output=cv.Canny(xgrad,ygrad,50,150)
        edge_output=cv.Canny(gray,30,150)
        cv.imshow('Canny',edge_output)
        return  edge_output
    
    
    # 轮廓发现
    def contous_image(image):
        binary=edge_demo(image)
        contous, heriachy = cv.findContours(binary, cv.RETR_EXTERNAL, cv.CHAIN_APPROX_SIMPLE)
        for i, contou in enumerate(contous):
            cv.drawContours(image, contous, i, (0, 0, 255), 2,)
        cv.imshow("lunkuo", image)
        for i, contou in enumerate(contous):
            #-1 表示轮廓填充
            cv.drawContours(image, contous, i, (0, 0, 255), -1)
        cv.imshow("lunkuofill", image)
    
    
    src = cv.imread("yingbi.jpg")
    cv.imshow("before", src)
    contous_image(src)
    cv.waitKey(0)
    cv.destroyAllWindows()

     效果展示

     

  • 相关阅读:
    去除文件中的空行
    数据分析 numpy matplotlib
    程序员
    c#
    java
    微信小游戏
    小游戏开发手册
    模板
    微信小程序小程序代码构成(.json .js .wxss .wxml)
    微信程序
  • 原文地址:https://www.cnblogs.com/angle6-liu/p/10701918.html
Copyright © 2020-2023  润新知