使用 python 和 OpenCV 從圖像中提取數字

Question

我正在尋找一些編碼解決方案/幫助來從 LCD 顯示器中提取數字，然后從圖像中提取 output 值。

下面是代碼和示例圖像，以及到目前為止我是如何做到的，但我需要一些進一步的幫助才能從圖像中實際提取“數字”和 output 值。

我從前面的例子中制作了數字查找表，

# 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, 0.05 * 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("Threshed", thresh)
cv2.imwrite("Threshed.jpg",thresh)
cv2.waitKey(0)
cv2.destroyAllWindows()

可以非常精通 python 的人，尤其是在 Open CV 方面可以幫助我解決這個問題。 這是關於圖像處理部分的學校作業，我決定使用 Python 和 OpenCV，因此它不是編程作業，代碼將僅用於執行和解釋實際的圖像處理。 我只需要幫助才能從經過篩選的圖像中實際提取數字。 我還提供了 LCD 顯示器的原始圖像，以防有更好的方法來實現我正在尋找的東西。

Answer 1

這是一種使用您提供的閾值輸入圖像的方法

• 將圖像轉換為灰度和 Otsu 的閾值
• 使用水平 kernel 執行變形關閉以將數字合並到單個輪廓中
• 查找輪廓並使用最小閾值區域過濾以過濾掉較大的外輪廓
• 按最大輪廓區域排序，該區域應該是所需的文本輪廓
• 使用 Numpy 切片遍歷輪廓並提取 ROI

---

從您的輸入圖像開始

我們使用水平 kernel 變形關閉，將數字合並到一個輪廓中

從這里我們找到輪廓並過濾以僅保留低於閾值區域的輪廓。 具體來說，我們使用0.75 * w * h來過濾掉外部輪廓。 一旦我們這樣做了，所需的文本輪廓應該是最大的輪廓

最后我們使用cv2.boundingRect()和 Numpy 切片提取 ROI

import cv2

image = cv2.imread('1.jpg')
original = image.copy()
h, w, _ = image.shape

gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)[1]
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (15,1))
close = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel, iterations=2)

cnts = cv2.findContours(close, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
minimum_area = .75 * h * w
cnts = [c for c in cnts if cv2.contourArea(c) < minimum_area]
cnts = sorted(cnts, key=cv2.contourArea, reverse=True)
for c in cnts:
    x,y,w,h = cv2.boundingRect(c)
    ROI = 255 - original[y:y+h, x:x+w]
    cv2.rectangle(image, (x, y), (x + w, y + h), (36,255,12), 2)
    break

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