当前位置：首页 > news >正文

【python】OpenCV—Extract Horizontal and Vertical Lines—Morphology

news 2025/6/24 20:50:01

在这里插入图片描述

文章目录

1、功能描述
2、代码实现
3、效果展示
4、完整代码
5、参考

更多有趣的代码示例，可参考【Programming】

1、功能描述

基于 opencv-python 库，利用形态学的腐蚀和膨胀，提取图片中的水平或者竖直线条

2、代码实现

导入基本的库函数

import numpy as np
import cv2 as cv

读入图片（https://raw.githubusercontent.com/opencv/opencv/5.x/doc/tutorials/imgproc/morph_lines_detection/images/src.png），增加读错图片的判断机制

1.jpg

在这里插入图片描述

def main(save=False):# Load the imagesrc = cv.imread("./1.jpg", cv.IMREAD_COLOR)# Check if image is loaded fineif src is None:print('Error opening image')return -1

可视化图片，并将其转化为灰度图

    # Show source imagecv.imshow("src", src)# [load_image]# [gray]# Transform source image to gray if it is not alreadyif len(src.shape) != 2:gray = cv.cvtColor(src, cv.COLOR_BGR2GRAY)else:gray = srcif save:cv.imwrite("gray.jpg", gray)# Show gray imageshow_wait_destroy("gray", gray)# [gray]

gray.jpg
在这里插入图片描述

show_wait_destroy 实现如下，关闭图片后才运行后续代码

def show_wait_destroy(winname, img):cv.imshow(winname, img)cv.moveWindow(winname, 500, 0)cv.waitKey(0)cv.destroyWindow(winname)

二进制求反灰度图，并自适应阈值二值化

    # [bin]# Apply adaptiveThreshold at the bitwise_not of gray, notice the ~ symbolgray = cv.bitwise_not(gray)if save:cv.imwrite("bitwise_not_gray.jpg", gray)bw = cv.adaptiveThreshold(gray, 255, cv.ADAPTIVE_THRESH_MEAN_C, \cv.THRESH_BINARY, 15, -2)if save:cv.imwrite("adaptiveThreshold.jpg", bw)# Show binary imageshow_wait_destroy("binary", bw)# [bin]

bitwise_not_gray.jpg
在这里插入图片描述
adaptiveThreshold.jpg

在这里插入图片描述

复制图片 adaptiveThreshold.jpg ，准备提取水平线和竖直线

    # [init]# Create the images that will use to extract the horizontal and vertical lineshorizontal = np.copy(bw)vertical = np.copy(bw)# [init]

提取水平线

    # [horiz]# Specify size on horizontal axiscols = horizontal.shape[1]  # 1024 colshorizontal_size = cols // 30  # 34# Create structure element for extracting horizontal lines through morphology operationshorizontalStructure = cv.getStructuringElement(cv.MORPH_RECT, (horizontal_size, 1))# Apply morphology operationshorizontal = cv.erode(horizontal, horizontalStructure)if save:cv.imwrite("erode-horizontal.jpg", horizontal)horizontal = cv.dilate(horizontal, horizontalStructure)if save:cv.imwrite("dilate-horizontal.jpg", horizontal)# Show extracted horizontal linesshow_wait_destroy("horizontal", horizontal)# [horiz]

首先会构建结构元素 horizontalStructure（定义了形态学操作的邻域形状和大小）

图片列数 // 30 得到全为 1 的数组

array([[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]], dtype=uint8)

接着腐蚀操作 erode-horizontal.jpg

在这里插入图片描述

最后膨胀操作 dilate-horizontal.jpg

在这里插入图片描述

至此我们就提取到了图片中的水平方向的线条

接下来我们提取竖直方向的线条

 	# [vert]# Specify size on vertical axisrows = vertical.shape[0]  # 134verticalsize = rows // 30  # 4# Create structure element for extracting vertical lines through morphology operationsverticalStructure = cv.getStructuringElement(cv.MORPH_RECT, (1, verticalsize))# Apply morphology operationsvertical = cv.erode(vertical, verticalStructure)if save:cv.imwrite("erode-vertical.jpg", vertical)vertical = cv.dilate(vertical, verticalStructure)if save:cv.imwrite("dilate-vertical.jpg", vertical)# Show extracted vertical linesshow_wait_destroy("vertical", vertical)# [vert]

同理，也是先构建一个结构元素 verticalStructure

array([[1],[1],[1],[1]], dtype=uint8)

腐蚀 erode-vertical.jpg

在这里插入图片描述

膨胀 dilate-vertical.jpg

在这里插入图片描述
至此我们提取出了竖直方向的线条

可以拓展一下，

As you can see we are almost there. However, at that point you will notice that the edges of the notes are a bit rough. For that reason we need to refine the edges in order to obtain a smoother result

    '''Extract edges and smooth image according to the logic1. extract edges2. dilate(edges)3. src.copyTo(smooth)4. blur smooth img5. smooth.copyTo(src, edges)'''

dilate-vertical.jpg 二进制求反，

    # [smooth]# Inverse vertical imagevertical = cv.bitwise_not(vertical)if save:cv.imwrite("bitwise_not_vertical.jpg", vertical)show_wait_destroy("vertical_bit", vertical)

bitwise_not_vertical.jpg
在这里插入图片描述
cv2.adaptiveThreshold 适应性阈值二值化

    # Step 1edges = cv.adaptiveThreshold(vertical, 255, cv.ADAPTIVE_THRESH_MEAN_C, \cv.THRESH_BINARY, 3, -2)if save:cv.imwrite("step1_edges.jpg", edges)show_wait_destroy("edges", edges)

得到 step1_edges.jpg，实现了边缘检测

在这里插入图片描述

看看 cv2.adaptiveThreshold 的介绍仔细分析下实现过程

dst = cv2.adaptiveThreshold(src, maxValue, adaptiveMethod, thresholdType, blockSize, C)

在这里插入图片描述

形参 C 从邻域像素的平均值或加权平均值中减去的常数，配置的为负数，附近颜色相近的变黑（eg 纯白区域，像素 255，阈值 255-（-2）=257，都变黑，再 eg，纯黑区域，像素 0，阈值 0-（-2）=2，也是黑），附近颜色变动的变白（黑白交替，白色的部分保留，黑色的部分变黑），可以实现边缘提取，妙

膨胀强化边缘

    # Step 2kernel = np.ones((2, 2), np.uint8)edges = cv.dilate(edges, kernel)if save:cv.imwrite("step2_edges.jpg", edges)show_wait_destroy("dilate", edges)

kernel 为

array([[1, 1],[1, 1]], dtype=uint8)

step2_edges.jpg

在这里插入图片描述

复制 bitwise_not_vertical.jpg

    # Step 3smooth = np.copy(vertical)

模糊处理 step4_smooth.jpg

    # Step 4smooth = cv.blur(smooth, (2, 2))if save:cv.imwrite("step4_smooth.jpg", smooth)

在这里插入图片描述

记录下 step2_edges.jpg 中像素不为零的部分的坐标，也即边缘部分坐标

边缘部分用平滑后的像素替换原来的像素

    # Step 5(rows, cols) = np.where(edges != 0)vertical[rows, cols] = smooth[rows, cols]# Show final resultshow_wait_destroy("smooth - final", vertical)if save:cv.imwrite("smooth_final.jpg", vertical)# [smooth]

在这里插入图片描述

3、效果展示

输入
在这里插入图片描述

水平线条

在这里插入图片描述

竖直线条

在这里插入图片描述

平滑竖直线条后的结果

在这里插入图片描述

输入图片

在这里插入图片描述

水平线

在这里插入图片描述

竖直线

在这里插入图片描述

平滑竖直线条后的结果

在这里插入图片描述

4、完整代码

"""
@brief Use morphology transformations for extracting horizontal and vertical lines sample code
"""
import numpy as np
import cv2 as cvdef show_wait_destroy(winname, img):cv.imshow(winname, img)cv.moveWindow(winname, 500, 0)cv.waitKey(0)cv.destroyWindow(winname)def main(save=False):# Load the imagesrc = cv.imread("./1.jpg", cv.IMREAD_COLOR)# Check if image is loaded fineif src is None:print('Error opening image')return -1# Show source imagecv.imshow("src", src)# [load_image]# [gray]# Transform source image to gray if it is not alreadyif len(src.shape) != 2:gray = cv.cvtColor(src, cv.COLOR_BGR2GRAY)else:gray = srcif save:cv.imwrite("gray.jpg", gray)# Show gray imageshow_wait_destroy("gray", gray)# [gray]# [bin]# Apply adaptiveThreshold at the bitwise_not of gray, notice the ~ symbolgray = cv.bitwise_not(gray)  # (134, 1024)if save:cv.imwrite("bitwise_not_gray.jpg", gray)bw = cv.adaptiveThreshold(gray, 255, cv.ADAPTIVE_THRESH_MEAN_C, \cv.THRESH_BINARY, 15, -2)if save:cv.imwrite("adaptiveThreshold.jpg", bw)# Show binary imageshow_wait_destroy("binary", bw)# [bin]# [init]# Create the images that will use to extract the horizontal and vertical lineshorizontal = np.copy(bw)vertical = np.copy(bw)# [init]# [horiz]# Specify size on horizontal axiscols = horizontal.shape[1]  # 1024 colshorizontal_size = cols // 30  # 34# Create structure element for extracting horizontal lines through morphology operationshorizontalStructure = cv.getStructuringElement(cv.MORPH_RECT, (horizontal_size, 1))# Apply morphology operationshorizontal = cv.erode(horizontal, horizontalStructure)if save:cv.imwrite("erode-horizontal.jpg", horizontal)horizontal = cv.dilate(horizontal, horizontalStructure)if save:cv.imwrite("dilate-horizontal.jpg", horizontal)# Show extracted horizontal linesshow_wait_destroy("horizontal", horizontal)# [horiz]# [vert]# Specify size on vertical axisrows = vertical.shape[0]  # 134verticalsize = rows // 30  # 4# Create structure element for extracting vertical lines through morphology operationsverticalStructure = cv.getStructuringElement(cv.MORPH_RECT, (1, verticalsize))# Apply morphology operationsvertical = cv.erode(vertical, verticalStructure)if save:cv.imwrite("erode-vertical.jpg", vertical)vertical = cv.dilate(vertical, verticalStructure)if save:cv.imwrite("dilate-vertical.jpg", vertical)# Show extracted vertical linesshow_wait_destroy("vertical", vertical)# [vert]# [smooth]# Inverse vertical imagevertical = cv.bitwise_not(vertical)if save:cv.imwrite("bitwise_not_vertical.jpg", vertical)show_wait_destroy("vertical_bit", vertical)'''Extract edges and smooth image according to the logic1. extract edges2. dilate(edges)3. src.copyTo(smooth)4. blur smooth img5. smooth.copyTo(src, edges)'''# Step 1edges = cv.adaptiveThreshold(vertical, 255, cv.ADAPTIVE_THRESH_MEAN_C, \cv.THRESH_BINARY, 3, -2)if save:cv.imwrite("step1_edges.jpg", edges)show_wait_destroy("edges", edges)# Step 2kernel = np.ones((2, 2), np.uint8)edges = cv.dilate(edges, kernel)if save:cv.imwrite("step2_edges.jpg", edges)show_wait_destroy("dilate", edges)# Step 3smooth = np.copy(vertical)# Step 4smooth = cv.blur(smooth, (2, 2))if save:cv.imwrite("step4_smooth.jpg", smooth)# Step 5(rows, cols) = np.where(edges != 0)vertical[rows, cols] = smooth[rows, cols]# Show final resultshow_wait_destroy("smooth - final", vertical)if save:cv.imwrite("smooth_final.jpg", vertical)# [smooth]return 0if __name__ == "__main__":main(save=True)