使用 Python/OpenCV 对非浅色/彩色数字进行数字识别

Question

我正在使用 OpenCV 4 和最新的 Python 版本。也拿到了所有的包裹。

我知道如何调整大小、灰度、模糊、边缘等，但我得到了很多错误，好像我无法检测到。

这是裁剪后的万用表显示图像，我试图从中检测和提取数字。

我需要一个简单的代码或帮助来编码和检索数字，尝试了多个指南但没有成功。 OpenCV 对我来说是新手，但我花了 2-3 天的时间来学习基本的图像处理能力。

数字万用表非彩色

好的，现在我已经更新了代码。我想从扭曲和转换的二进制图像中提取数字。但是我得到了错误或者我需要删除部分代码才能至少向我显示这两个图像。 到目前为止的代码如下：

# import the necessary packages
from imutils.perspective import four_point_transform
from imutils import contours
import imutils
import cv2

# define the dictionary of digit segments so we can identify
# each digit on the thermostat
DIGITS_LOOKUP = {
(1, 1, 1, 0, 1, 1, 1): 0,
(0, 0, 1, 0, 0, 1, 0): 1,
(1, 0, 1, 1, 1, 1, 0): 2,
(1, 0, 1, 1, 0, 1, 1): 3,
(0, 1, 1, 1, 0, 1, 0): 4,
(1, 1, 0, 1, 0, 1, 1): 5,
(1, 1, 0, 1, 1, 1, 1): 6,
(1, 0, 1, 0, 0, 1, 0): 7,
(1, 1, 1, 1, 1, 1, 1): 8,
(1, 1, 1, 1, 0, 1, 1): 9}

# load the example image
image = cv2.imread("Multimeter_1.jpg")

# pre-process the image by converting it to
# graycale, blurring it, and computing an edge map
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (7,7), 0)
thresh = cv2.adaptiveThreshold(blur,255,cv2.ADAPTIVE_THRESH_GAUSSIAN_C, 
cv2.THRESH_BINARY_INV,87,9)


# find contours in the edge map,
cnts = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
cnts = sorted(cnts, key=cv2.contourArea, reverse=True)

rect = None
# loop over the contours
for c in cnts:
# approximate the contour
x,y,w,h = cv2.boundingRect(c)
#cv2.rectangle(image, (x, y), (x+w, y+h), (36, 255, 12), 1)
cv2.drawContours(image, [c], -1, (36,255,12),3)
rect = c

peri = cv2.arcLength(c, True)
approx = cv2.approxPolyDP(c, 0.02 * peri, True)

if len(approx) == 4:
    rect = approx
    break


# extract the display, apply a perspective transform

warped = four_point_transform(thresh, rect.reshape(4, 2))
output = four_point_transform(image, rect.reshape(4, 2))

# Warp the image and perform morphology to clean it

thresh = cv2.threshold(warped, 0, 255,cv2.THRESH_BINARY | cv2.THRESH_OTSU) 
[1]
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (5, 5))
thresh = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel)


# pre-process the image by converting it to
# graycale, blurring it, and computing an edge map
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (7,7), 0)
thresh = cv2.adaptiveThreshold(blur,255,cv2.ADAPTIVE_THRESH_GAUSSIAN_C, 
cv2.THRESH_BINARY_INV,87,9)


# find contours in the edge map,
cnts = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
cnts = sorted(cnts, key=cv2.contourArea, reverse=True)

rect = None
# loop over the contours
for c in cnts:
# approximate the contour
x,y,w,h = cv2.boundingRect(c)
#cv2.rectangle(image, (x, y), (x+w, y+h), (36, 255, 12), 1)
cv2.drawContours(image, [c], -1, (36,255,12),3)
rect = c

peri = cv2.arcLength(c, True)
approx = cv2.approxPolyDP(c, 0.02 * peri, True)

if len(approx) == 4:
    rect = approx
    break


# extract the display, apply a perspective transform

warped = four_point_transform(thresh, rect.reshape(4, 2))
output = four_point_transform(image, rect.reshape(4, 2))
# Warp the image and perform morphology to clean it

thresh = cv2.threshold(warped, 0, 255,cv2.THRESH_BINARY | cv2.THRESH_OTSU) 
[1]
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (1, 5))
thresh = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel)

cnts = 
cv2.findContours(thresh.copy(),cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)
cnts = imutils.grab_contours(cnts)
digitCnts = []

# loop over the digit area candidates
for c in cnts:
(x,y,w,h) = cv2.boundingRect(c)

# if the contour is sufficiently large, it must be a digit
if w >= 25 and (h >= 50 and h <= 60):
digitCnts.append(c)


cv2.imshow("Multimeter", image)
cv2.imshow("Multimeter2", thresh)


cv2.waitKey(0)
cv2.destroyAllWindows()

Warped,Transformed, tresholded

Answer 1

我很难为此编写正确的代码，仍在学习过程中......

我拍摄了那个变形的图像并制作了另一个 Python 脚本来简化事情。现在让我们说图像已经是二进制、转换和扭曲的。提取后如何检测数字并在图像或控制台上显示信息？我还没有学会这样做。我很难找到数字的坐标，我只是找到了图像的矩形边界，但不是我要找的。

换句话说：我需要帮助找到第一个数字的边界框，检测并提取它们。

Image example

到目前为止，这里是简化的示例代码：

# import the necessary packages
from imutils.perspective import four_point_transform
from imutils import contours
import imutils
import cv2
import numpy

image = cv2.imread("Morph.jpg")
copy = image.copy()
image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

cnts = cv2.findContours(image, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]

ROI_number = 0
for c in cnts:
x,y,w,h = cv2.boundingRect(c)
ROI = image[y:y+h, x:x+w]
cv2.imwrite('ROI_{}.png'.format(ROI_number), ROI)
cv2.rectangle(copy,(x,y),(x+w,y+h),(36,255,12),2)
ROI_number += 1



cv2.imshow('thresh', image)
cv2.imshow('copy', copy)
cv2.imwrite("Morphed_rectangle.jpg",copy)

cv2.waitKey(0)
cv2.destroyAllWindows()

Answer 2

您可以使用cv2.adaptiveThreshold() 获取二值图像，然后通过对最大轮廓进行排序来提取显示。一旦你检测到这个轮廓，你就可以应用你的透视变换

import cv2

image = cv2.imread('1.jpg')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (7,7), 0)
thresh = cv2.adaptiveThreshold(blur,255,cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY_INV,87,9)

cnts = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
cnts = sorted(cnts, key=cv2.contourArea, reverse=True)

rect = None
for c in cnts:
    x,y,w,h = cv2.boundingRect(c)
    cv2.drawContours(image, [c], -1, (36,255,12), 3)
    # cv2.rectangle(image, (x, y), (x+w, y+h), (36, 255, 12), 1)
    rect = c
    break

cv2.imshow('image', image)
cv2.waitKey()