如何使用 Python 增强图像中的文本检测

Question

我尝试使用 OpenCV Python 检测图像中的文本，特别是带有引号的图像。为此，我首先训练了一些文本图像。我检测图像中文本的每个字符进行训练。对于具有正确文字样式的图像，可以正确检测字符。但是对于某些图像，无法正确检测到文本（字符）区域。我在下面附上了代码。如何修改代码以便正确检测字符

import sys
import numpy as np
import cv2
import os

MIN_CONTOUR_AREA = 100

RESIZED_IMAGE_WIDTH = 20
RESIZED_IMAGE_HEIGHT = 30

def main():
imgTrainingNumbers = cv2.imread("E:\God - Level 4 Research Project\Testings\Tharu\godd/jbpoetry.png") 

if imgTrainingNumbers is None:  
    print ("error: image not read from file \n\n") 
    os.system("pause") 
    return

imgGray = cv2.cvtColor(imgTrainingNumbers, cv2.COLOR_BGR2GRAY)
imgBlurred = cv2.GaussianBlur(imgGray, (5,5), 0)

imgThresh = cv2.adaptiveThreshold(imgBlurred,
                                  255,
                                  cv2.ADAPTIVE_THRESH_GAUSSIAN_C,
                                  cv2.THRESH_BINARY_INV,
                                  11,
                                  2)

cv2.imshow("imgThresh", imgThresh)

imgThreshCopy = imgThresh.copy()

imgContours, npaContours, npaHierarchy = cv2.findContours(imgThreshCopy,
                                             cv2.RETR_EXTERNAL, 
                                             cv2.CHAIN_APPROX_SIMPLE)


npaFlattenedImages =  np.empty((0, RESIZED_IMAGE_WIDTH * RESIZED_IMAGE_HEIGHT))

intClassifications = []

intValidChars = [ord('0'), ord('1'), ord('2'), ord('3'), ord('4'), ord('5'), ord('6'), ord('7'), ord('8'), ord('9'),
                 ord('A'), ord('B'), ord('C'), ord('D'), ord('E'), ord('F'), ord('G'), ord('H'), ord('I'), ord('J'),
                 ord('K'), ord('L'), ord('M'), ord('N'), ord('O'), ord('P'), ord('Q'), ord('R'), ord('S'), ord('T'),
                 ord('U'), ord('V'), ord('W'), ord('X'), ord('Y'), ord('Z'),ord('a'),ord('b'),ord('c'),ord('d'),
                 ord('e'),ord('f'),ord('g'),ord('h'),ord('i'),ord('j'),ord('k'),ord('l'),ord('m'),ord('n'),ord('o'),
                 ord('p'),ord('q'),ord('r'),ord('s'),ord('t'),ord('u'),ord('v'),ord('w'),ord('x'),ord('y'),ord('z') ]


for npaContour in npaContours:
    if cv2.contourArea(npaContour) > MIN_CONTOUR_AREA:
        [intX, intY, intW, intH] = cv2.boundingRect(npaContour)


        cv2.rectangle(imgTrainingNumbers,
                      (intX, intY), 
                      (intX+intW,intY+intH),
                      (0, 0, 255),
                      2)

        imgROI = imgThresh[intY:intY+intH, intX:intX+intW] 
        imgROIResized = cv2.resize(imgROI, (RESIZED_IMAGE_WIDTH, RESIZED_IMAGE_HEIGHT))

        cv2.imshow("imgROI", imgROI)               
        cv2.imshow("imgROIResized", imgROIResized)
        cv2.imshow("training_numbers.png", imgTrainingNumbers)

        intChar = cv2.waitKey(0) 

        if intChar == 27: 
            sys.exit()
        elif intChar in intValidChars:
            print(intChar)
            intClassifications.append(intChar)    
            print(intChar)
            npaFlattenedImage = imgROIResized.reshape((1, RESIZED_IMAGE_WIDTH * RESIZED_IMAGE_HEIGHT)) 
            npaFlattenedImages = np.append(npaFlattenedImages, npaFlattenedImage, 0) 

fltClassifications = np.array(intClassifications, np.float32) 

npaClassifications = fltClassifications.reshape((fltClassifications.size, 1))

print ("\n\ntraining complete !!\n")

np.savetxt("classificationsNEWG.txt", npaClassifications)
np.savetxt("flattened_imagesNEWG.txt", npaFlattenedImages)
cv2.destroyAllWindows()
return
if __name__ == "__main__":
main()

Answer 1

您尝试做的是一种非常幼稚的方法，仅应用阈值并检测轮廓在这里不起作用。围绕这一任务发表了许多研究论文。您可以参考这些并尝试实现或可以使用著名的 tesseract OCR 的 image_to_boxes 功能。您可以从here 下载它，当您使用 python 时，您可以从here 安装 pytesseract - python 包装器用于 tesseract 并使用以下代码来实现您所期望的。

import pytesseract
import cv2

originalImg = cv2.imread('tp.png')
originalImg = cv2.resize(originalImg, None, fx=2.5, fy=2.5)
img = cv2.cvtColor(originalImg, cv2.COLOR_BGR2GRAY)
_,img = cv2.threshold(img,100,255,cv2.THRESH_BINARY)

h, w = img.shape

letters = pytesseract.image_to_boxes(img)
letters = letters.split('\n')
letters = [letter.split() for letter in letters]

for letter in letters:    
    cv2.rectangle(originalImg, (int(letter[1]), h - int(letter[2])), (int(letter[3]), h - int(letter[4])), (0,0,255), 1)

cv2.imshow('', originalImg)

生成的图像

请注意，有很多错误检测，您需要在训练过程中忽略它们。