Python 无法使用排序控制器生成七段OCR
我正试图建立一个OCR来识别七段显示,如下所述 使用OpenCV的预处理工具,我在这里得到了它 现在我试着学习本教程- 但在这方面Python 无法使用排序控制器生成七段OCR,python,opencv,image-processing,ocr,Python,Opencv,Image Processing,Ocr,我正试图建立一个OCR来识别七段显示,如下所述 使用OpenCV的预处理工具,我在这里得到了它 现在我试着学习本教程- 但在这方面 digitCnts = contours.sort_contours(digitCnts, method="left-to-right")[0] digits = [] 我得到的错误是- 使用THRESH\u BINARY\u INV解决了该错误,但OCR仍然无法工作。任何修复都很好 文件“/Users/ms/anaconda3/lib/python3
digitCnts = contours.sort_contours(digitCnts,
method="left-to-right")[0]
digits = []
我得到的错误是-
使用THRESH\u BINARY\u INV解决了该错误,但OCR仍然无法工作。任何修复都很好
文件“/Users/ms/anaconda3/lib/python3.6/site packages/imutils/courtous.py”,第25行,在sort\u等高线中
键=λb:b[i],反向=反向)
ValueError:没有足够的值来解包(应为2,得到0)
你知道如何解决这个问题并使我的OCR成为一个工作模型吗
我的全部代码是:
import numpy as np
import cv2
import imutils
# 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 image
image = cv2.imread('d4.jpg')
# create hsv
hsv = cv2.cvtColor(image, cv2.COLOR_BGR2HSV)
# set lower and upper color limits
low_val = (60,180,160)
high_val = (179,255,255)
# Threshold the HSV image
mask = cv2.inRange(hsv, low_val,high_val)
# find contours in mask
ret, cont, hierarchy = cv2.findContours(mask,cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
# select the largest contour
largest_area = 0
for cnt in cont:
if cv2.contourArea(cnt) > largest_area:
cont = cnt
largest_area = cv2.contourArea(cnt)
# get the parameters of the boundingbox
x,y,w,h = cv2.boundingRect(cont)
# create and show subimage
roi = image[y:y+h, x:x+w]
cv2.imshow("Result", roi)
# draw box on original image and show image
cv2.rectangle(image, (x,y),(x+w,y+h), (0,0,255),2)
cv2.imshow("Image", image)
grayscaled = cv2.cvtColor(roi,cv2.COLOR_BGR2GRAY)
retval, threshold = cv2.threshold(grayscaled, 10, 255, cv2.THRESH_BINARY)
retval2,threshold2 = cv2.threshold(grayscaled,125,255,cv2.THRESH_BINARY+cv2.THRESH_OTSU)
cv2.imshow('threshold',threshold2)
cv2.waitKey(0)
cv2.destroyAllWindows()
# find contours in the thresholded image, then initialize the
# digit contours lists
cnts = cv2.findContours(threshold2.copy(), cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE)
cnts = imutils.grab_contours(cnts)
digitCnts = []
# loop over the digit area candidates
for c in cnts:
# compute the bounding box of the contour
(x, y, w, h) = cv2.boundingRect(c)
# if the contour is sufficiently large, it must be a digit
if w >= 15 and (h >= 30 and h <= 40):
digitCnts.append(c)
# sort the contours from left-to-right, then initialize the
# actual digits themselves
digitCnts = contours.sort_contours(digitCnts,
method="left-to-right")[0]
digits = []
# loop over each of the digits
for c in digitCnts:
# extract the digit ROI
(x, y, w, h) = cv2.boundingRect(c)
roi = thresh[y:y + h, x:x + w]
# compute the width and height of each of the 7 segments
# we are going to examine
(roiH, roiW) = roi.shape
(dW, dH) = (int(roiW * 0.25), int(roiH * 0.15))
dHC = int(roiH * 0.05)
# define the set of 7 segments
segments = [
((0, 0), (w, dH)), # top
((0, 0), (dW, h // 2)), # top-left
((w - dW, 0), (w, h // 2)), # top-right
((0, (h // 2) - dHC) , (w, (h // 2) + dHC)), # center
((0, h // 2), (dW, h)), # bottom-left
((w - dW, h // 2), (w, h)), # bottom-right
((0, h - dH), (w, h)) # bottom
]
on = [0] * len(segments)
# loop over the segments
for (i, ((xA, yA), (xB, yB))) in enumerate(segments):
# extract the segment ROI, count the total number of
# thresholded pixels in the segment, and then compute
# the area of the segment
segROI = roi[yA:yB, xA:xB]
total = cv2.countNonZero(segROI)
area = (xB - xA) * (yB - yA)
# if the total number of non-zero pixels is greater than
# 50% of the area, mark the segment as "on"
if total / float(area) > 0.5:
on[i]= 1
# lookup the digit and draw it on the image
digit = DIGITS_LOOKUP[tuple(on)]
digits.append(digit)
cv2.rectangle(output, (x, y), (x + w, y + h), (0, 255, 0), 1)
cv2.putText(output, str(digit), (x - 10, y - 10),
cv2.FONT_HERSHEY_SIMPLEX, 0.65, (0, 255, 0), 2)
# display the digits
print(u"{}{}.{}{}.{}{} \u00b0C".format(*digits))
cv2.imshow("Input", image)
cv2.imshow("Output", output)
cv2.waitKey(0)
将numpy导入为np
进口cv2
导入imutils
#导入必要的包
从imutils.perspective导入四点变换
从imutils导入等高线
导入imutils
进口cv2
#定义数字段字典,以便我们能够识别
#恒温器上的每个数字
数字\u查找={
(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
}
#加载图像
image=cv2.imread('d4.jpg')
#创建hsv
hsv=cv2.cvt颜色(图像,cv2.COLOR\u BGR2HSV)
#设置颜色下限和上限
低值=(60180160)
高值=(179255255)
#对HSV图像进行阈值设置
掩码=cv2.inRange(hsv、低值、高值)
#在蒙版中查找轮廓
ret,cont,hierarchy=cv2.findContours(掩码,cv2.RETR\u外部,cv2.CHAIN\u近似值\u简单)
#选择最大的轮廓
最大面积=0
对于cont中的cnt:
如果cv2.轮廓面积(cnt)>最大面积:
cont=cnt
最大面积=cv2。轮廓面积(cnt)
#获取边界框的参数
x、 y,w,h=cv2.boundingRect(续)
#创建并显示子图像
roi=图像[y:y+h,x:x+w]
cv2.imshow(“结果”,投资回报率)
#在原始图像上绘制框并显示图像
cv2.矩形(图像,(x,y),(x+w,y+h),(0,0255),2)
cv2.imshow(“图像”,图像)
灰度=cv2.CVT颜色(roi,cv2.COLOR\u BGR2GRAY)
retval,threshold=cv2.threshold(灰度,10255,cv2.THRESH_二进制)
retval2,threshold2=cv2.threshold(灰度,125255,cv2.THRESH_BINARY+cv2.THRESH_OTSU)
cv2.imshow(“阈值”,阈值2)
cv2.等待键(0)
cv2.destroyAllWindows()
#在阈值图像中查找轮廓,然后初始化
#数字轮廓列表
cnts=cv2.findContentours(threshold2.copy(),cv2.RETR_EXTERNAL,
cv2.链条(近似简单)
cnts=imutils.GRAP_轮廓(cnts)
digitCnts=[]
#在候选数字区域上循环
对于碳纳米管中的碳:
#计算轮廓的边界框
(x,y,w,h)=cv2.boundingRect(c)
#如果轮廓足够大,它必须是一个数字
如果w>=15和(h>=30和h 0.5:
关于[i]=1
#查找数字并将其绘制在图像上
数字=数字\u查找[元组(打开)]
数字。追加(数字)
cv2.矩形(输出,(x,y),(x+w,y+h),(0,255,0),1)
cv2.putText(输出,str(数字),(x-10,y-10),
cv2.FONT_HERSHEY_SIMPLEX,0.65,(0,255,0),2)
#显示数字
打印(u{}{}.{}{}.{}{}{}\u00b0C.format(*位))
cv2.imshow(“输入”,图像)
cv2.imshow(“输出”,输出)
cv2.等待键(0)
在修复我的OCR方面会有很大的帮助我认为您创建的查找表是用于
七位数显示
,而不是七位数OCR
。至于显示的大小是固定的,我想您可以尝试将其分割为单独的区域,并使用模板匹配
或k-means
进行识别
这是我的预处理步骤:
(1) 在HSV
mask = cv2.inRange(hsv, (50, 100, 180), (70, 255, 255))
(2) 通过使用LUT投影和识别标准七位数字来尝试分离:
(3) 在检测到的绿色显示屏上尝试
因此,正如我在评论中所说,有两个问题:
threshold2 = cv2.morphologyEx(threshold, cv2.MORPH_OPEN, np.ones((3,3), np.uint8))
2b)前一张图像上的放大:
threshold2 = cv2.dilate(threshold2, np.ones((5,1), np.uint8), iterations=1)
2c)由于放大到上边框,将图像的顶部裁剪为单独的数字:
height, width = threshold2.shape[:2]
threshold2 = threshold2[5:height,5:width]
请注意,这里显示的图像没有我所说的白色边框。试着在一个新窗口中打开图像,你就会明白我的意思
因此,在解决了这些问题后,轮廓非常好,它们应该是什么样子的,如图所示:
cnts = cv2.findContours(threshold2.copy(), cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE)
cnts = imutils.grab_contours(cnts)
digitCnts = []
# loop over the digit area candidates
for c in cnts:
# compute the bounding box of the contour
(x, y, w, h) = cv2.boundingRect(c)
# if the contour is sufficiently large, it must be a digit
if w <= width * 0.5 and (h >= height * 0.2):
digitCnts.append(c)
# sort the contours from left-to-right, then initialize the
# actual digits themselves
cv2.drawContours(image2, digitCnts, -1, (0, 0, 255))
cv2.imwrite("cnts-sort.jpg", image2)
我通读了这些评论,似乎LUT中的一些条目可能是错误的。所以我要让你们自己去弄清楚。以下是找到的单个数字(但未识别):
或者,您可以使用tesseract来识别这些检测到的数字
希望有帮助 如果您查看上的OpenCV文档,它会提到要查找的对象应该是白色的,背景应该是黑色的。尝试使用,
THRESH\u BINARY\u INV
而不是THRESH\u BINARY
。错误表明它没有找到任何轮廓。但它仍然没有打印任何我要求修复OCR的内容。你能在你的系统上运行它并验证错误是什么吗?请@RickM。Rick提到的问题肯定是相关的。从这里开始,您这边的一些调试工作不会有什么坏处(即使只是简单地将变量打印到控制台)如果您对实现此排序功能感兴趣,请选择过滤条件w>=15和(h>=30和h)
# loop over each of the digits
j = 0
for c in digitCnts:
# extract the digit ROI
(x, y, w, h) = cv2.boundingRect(c)
roi = threshold2[y:y + h, x:x + w]
cv2.imwrite("roi" + str(j) + ".jpg", roi)
j += 1
# compute the width and height of each of the 7 segments
# we are going to examine
(roiH, roiW) = roi.shape
(dW, dH) = (int(roiW * 0.25), int(roiH * 0.15))
dHC = int(roiH * 0.05)
# define the set of 7 segments
segments = [
((0, 0), (w, dH)), # top
((0, 0), (dW, h // 2)), # top-left
((w - dW, 0), (w, h // 2)), # top-right
((0, (h // 2) - dHC) , (w, (h // 2) + dHC)), # center
((0, h // 2), (dW, h)), # bottom-left
((w - dW, h // 2), (w, h)), # bottom-right
((0, h - dH), (w, h)) # bottom
]
on = [0] * len(segments)
# loop over the segments
for (i, ((xA, yA), (xB, yB))) in enumerate(segments):
# extract the segment ROI, count the total number of
# thresholded pixels in the segment, and then compute
# the area of the segment
segROI = roi[yA:yB, xA:xB]
total = cv2.countNonZero(segROI)
area = (xB - xA) * (yB - yA)
# if the total number of non-zero pixels is greater than
# 50% of the area, mark the segment as "on"
if area != 0:
if total / float(area) > 0.5:
on[i] = 1
# lookup the digit and draw it on the image
try:
digit = DIGITS_LOOKUP[tuple(on)]
digits.append(digit)
cv2.rectangle(roi, (x, y), (x + w, y + h), (0, 255, 0), 1)
cv2.putText(roi, str(digit), (x - 10, y - 10),
cv2.FONT_HERSHEY_SIMPLEX, 0.65, (0, 255, 0), 2)
except KeyError:
continue