Python - cv2 查找轮廓
Python - cv2 find Contours
想把文档中所有的大元素都找出来,但是不知道怎么控制大小(文档是从网上下载的:))
我有一个文件
然后我写了一个简单的代码
import cv2
import pytesseract
image = cv2.imread('2.png')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (7, 7), 0)
thresh = cv2.threshold(
blur, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
kernal = cv2.getStructuringElement(cv2.MORPH_RECT, (3, 50))
dilate = cv2.dilate(thresh, kernal, iterations=1)
cv2.imwrite('1_dilated.png', dilate)
cnts = cv2.findContours(dilate, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
cnts = sorted(cnts, key=lambda x: cv2.boundingRect(x)[1])
for c in cnts:
x, y, w, h = cv2.boundingRect(c)
if h > 100 and w > 100:
roi = image[y:y+h, x:x+w]
cv2.rectangle(image, (x, y), (x+w, y+h), (36, 255, 12), 2)
# ocr = pytesseract.image_to_string(roi)
# print(ocr)
cv2.imwrite('1_boxes4.png', image)
但只检测到它
我想要这个
如何控制检测区域的大小?
非常感谢您的所有评论
你很接近,但你需要增加dilate
操作的迭代次数。此外,矩形 structuring element
可能有助于更好地形成文本块。让我们检查一下您的代码的一些可能的改进:
# imports:
import cv2
import numpy as np
# Set image path
imagePath = "D://opencvImages//"
imageName = "F74Yq.png"
# Read image:
inputImage = cv2.imread(imagePath + imageName)
# Store a deeep copy for results:
inputCopy = inputImage.copy()
# Convert BGR to grayscale:
grayInput = cv2.cvtColor(inputImage, cv2.COLOR_BGR2GRAY)
# Threshold via Otsu
_, binaryImage = cv2.threshold(grayInput, 0, 255, cv2.THRESH_BINARY_INV+cv2.THRESH_OTSU)
第一部分生成输入图像的二值图像,这里没有什么特别的 - 只是通过 Otsu
的方法直接进行阈值处理。这是得到的二值图像:
现在,让我们应用 dilate
操作。让我们使用 9 x 9
矩形内核并将迭代次数设置为 5
。一定要小心,不要 dilate
太多,因为来自文档不同部分的文本块最终可能会连接在一起:
# Set kernel (structuring element) size:
kernelSize = (9, 9)
# Set operation iterations:
opIterations = 5
# Get the structuring element:
morphKernel = cv2.getStructuringElement(cv2.MORPH_RECT, kernelSize)
# Perform Dilate:
dilateImage = cv2.morphologyEx(binaryImage, cv2.MORPH_DILATE, morphKernel, None, None, opIterations, cv2.BORDER_REFLECT101)
这是结果:
好的,现在让我们检测外部轮廓并得到它们的bounding boxes
,这样我们就可以在目标区域周围绘制矩形。请注意,我在输入的深层副本上绘制矩形:
# Find the contours on the binary image:
contours, hierarchy = cv2.findContours(dilateImage, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
# Look for the outer bounding boxes (no children):
for _, c in enumerate(contours):
# Get the contours bounding rectangle:
boundRect = cv2.boundingRect(c)
# Get the dimensions of the bounding rectangle:
rectX = boundRect[0]
rectY = boundRect[1]
rectWidth = boundRect[2]
rectHeight = boundRect[3]
# Set bounding rectangle:
color = (0, 0, 255)
cv2.rectangle( inputCopy, (int(rectX), int(rectY)),
(int(rectX + rectWidth), int(rectY + rectHeight)), color, 5 )
cv2.imshow("Bounding Rectangles", inputCopy)
cv2.waitKey()
这是最终结果:
想把文档中所有的大元素都找出来,但是不知道怎么控制大小(文档是从网上下载的:))
我有一个文件
然后我写了一个简单的代码
import cv2
import pytesseract
image = cv2.imread('2.png')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (7, 7), 0)
thresh = cv2.threshold(
blur, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
kernal = cv2.getStructuringElement(cv2.MORPH_RECT, (3, 50))
dilate = cv2.dilate(thresh, kernal, iterations=1)
cv2.imwrite('1_dilated.png', dilate)
cnts = cv2.findContours(dilate, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
cnts = sorted(cnts, key=lambda x: cv2.boundingRect(x)[1])
for c in cnts:
x, y, w, h = cv2.boundingRect(c)
if h > 100 and w > 100:
roi = image[y:y+h, x:x+w]
cv2.rectangle(image, (x, y), (x+w, y+h), (36, 255, 12), 2)
# ocr = pytesseract.image_to_string(roi)
# print(ocr)
cv2.imwrite('1_boxes4.png', image)
但只检测到它
我想要这个
如何控制检测区域的大小?
非常感谢您的所有评论
你很接近,但你需要增加dilate
操作的迭代次数。此外,矩形 structuring element
可能有助于更好地形成文本块。让我们检查一下您的代码的一些可能的改进:
# imports:
import cv2
import numpy as np
# Set image path
imagePath = "D://opencvImages//"
imageName = "F74Yq.png"
# Read image:
inputImage = cv2.imread(imagePath + imageName)
# Store a deeep copy for results:
inputCopy = inputImage.copy()
# Convert BGR to grayscale:
grayInput = cv2.cvtColor(inputImage, cv2.COLOR_BGR2GRAY)
# Threshold via Otsu
_, binaryImage = cv2.threshold(grayInput, 0, 255, cv2.THRESH_BINARY_INV+cv2.THRESH_OTSU)
第一部分生成输入图像的二值图像,这里没有什么特别的 - 只是通过 Otsu
的方法直接进行阈值处理。这是得到的二值图像:
现在,让我们应用 dilate
操作。让我们使用 9 x 9
矩形内核并将迭代次数设置为 5
。一定要小心,不要 dilate
太多,因为来自文档不同部分的文本块最终可能会连接在一起:
# Set kernel (structuring element) size:
kernelSize = (9, 9)
# Set operation iterations:
opIterations = 5
# Get the structuring element:
morphKernel = cv2.getStructuringElement(cv2.MORPH_RECT, kernelSize)
# Perform Dilate:
dilateImage = cv2.morphologyEx(binaryImage, cv2.MORPH_DILATE, morphKernel, None, None, opIterations, cv2.BORDER_REFLECT101)
这是结果:
好的,现在让我们检测外部轮廓并得到它们的bounding boxes
,这样我们就可以在目标区域周围绘制矩形。请注意,我在输入的深层副本上绘制矩形:
# Find the contours on the binary image:
contours, hierarchy = cv2.findContours(dilateImage, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
# Look for the outer bounding boxes (no children):
for _, c in enumerate(contours):
# Get the contours bounding rectangle:
boundRect = cv2.boundingRect(c)
# Get the dimensions of the bounding rectangle:
rectX = boundRect[0]
rectY = boundRect[1]
rectWidth = boundRect[2]
rectHeight = boundRect[3]
# Set bounding rectangle:
color = (0, 0, 255)
cv2.rectangle( inputCopy, (int(rectX), int(rectY)),
(int(rectX + rectWidth), int(rectY + rectHeight)), color, 5 )
cv2.imshow("Bounding Rectangles", inputCopy)
cv2.waitKey()
这是最终结果: