使用Opencv检测图像中的文本区域

Question

我有一个图像，想检测其中的文本区域

我尝试了TiRG_RAW_20110219项目，但结果并不令人满意。如果输入图像为http://imgur.com/yCxOvQS,GD38rCa，则生成http://imgur.com/yCxOvQS,GD38rCa#1作为输出

有人能提出一些替代方案吗。我希望通过只发送文本区域作为输入来改进tesseract的输出

Answer 1

由于没有人发布完整的解决方案，这里有一个方法。通过观察所需的文本是白色的，并且单词是以水平对齐的方式构造的，我们可以使用颜色分割来提取和OCR字母

1. 执行颜色分割。我们加载图像，转换为HSV格式，定义下限/上限范围，并使用^{}执行颜色分割以获得二值遮罩

2. 扩展以连接文本字符。我们使用^{}创建一个水平形状的内核，然后使用^{}扩展以将单个字母组合成一个轮廓

3. 删除非文本轮廓。我们使用^{}查找轮廓，并使用aspect ratio进行过滤以删除非文本字符。由于文本处于水平方向，如果确定轮廓小于预定义的纵横比阈值，则我们通过使用^{}填充轮廓来移除非文本轮廓

4. 执行OCR。我们使用初始遮罩按位和放大图像，以仅分离文本字符，并反转图像，使文本为黑色，背景为白色。最后，我们将图像放入Pytesseract OCR中

---

以下是每个步骤的可视化：

输入图像

由颜色分割生成的掩模

# Load image, convert to HSV format, define lower/upper ranges, and perform
# color segmentation to create a binary mask
image = cv2.imread('1.jpg')
hsv = cv2.cvtColor(image, cv2.COLOR_BGR2HSV)
lower = np.array([0, 0, 218])
upper = np.array([157, 54, 255])
mask = cv2.inRange(hsv, lower, upper)

使用纵横比过滤连接文本轮廓和删除的非文本轮廓的放大图像

# Create horizontal kernel and dilate to connect text characters
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5,3))
dilate = cv2.dilate(mask, kernel, iterations=5)

# Find contours and filter using aspect ratio
# Remove non-text contours by filling in the contour
cnts = cv2.findContours(dilate, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
    x,y,w,h = cv2.boundingRect(c)
    ar = w / float(h)
    if ar < 5:
        cv2.drawContours(dilate, [c], -1, (0,0,0), -1)

按位和同时遮罩和反转，为OCR的结果做好准备

# Bitwise dilated image with mask, invert, then OCR
result = 255 - cv2.bitwise_and(dilate, mask)
data = pytesseract.image_to_string(result, lang='eng',config=' psm 6')
print(data)

PyteSeract OCR使用 psm 6配置设置产生的结果，以假定一个统一的文本块。查看here了解更多配置选项

All women become
like their mothers.
That is their tragedy.
No man does.

That's his.

OSCAR WILDE

完整代码

import cv2
import numpy as np
import pytesseract

pytesseract.pytesseract.tesseract_cmd = r"C:\Program Files\Tesseract-OCR\tesseract.exe"

# Load image, convert to HSV format, define lower/upper ranges, and perform
# color segmentation to create a binary mask
image = cv2.imread('1.jpg')
hsv = cv2.cvtColor(image, cv2.COLOR_BGR2HSV)
lower = np.array([0, 0, 218])
upper = np.array([157, 54, 255])
mask = cv2.inRange(hsv, lower, upper)

# Create horizontal kernel and dilate to connect text characters
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5,3))
dilate = cv2.dilate(mask, kernel, iterations=5)

# Find contours and filter using aspect ratio
# Remove non-text contours by filling in the contour
cnts = cv2.findContours(dilate, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
    x,y,w,h = cv2.boundingRect(c)
    ar = w / float(h)
    if ar < 5:
        cv2.drawContours(dilate, [c], -1, (0,0,0), -1)

# Bitwise dilated image with mask, invert, then OCR
result = 255 - cv2.bitwise_and(dilate, mask)
data = pytesseract.image_to_string(result, lang='eng',config=' psm 6')
print(data)

cv2.imshow('mask', mask)
cv2.imshow('dilate', dilate)
cv2.imshow('result', result)
cv2.waitKey()

HSV下/上颜色范围是使用此HSV颜色阈值脚本确定的

import cv2
import numpy as np

def nothing(x):
    pass

# Load image
image = cv2.imread('1.jpg')

# Create a window
cv2.namedWindow('image')

# Create trackbars for color change
# Hue is from 0-179 for Opencv
cv2.createTrackbar('HMin', 'image', 0, 179, nothing)
cv2.createTrackbar('SMin', 'image', 0, 255, nothing)
cv2.createTrackbar('VMin', 'image', 0, 255, nothing)
cv2.createTrackbar('HMax', 'image', 0, 179, nothing)
cv2.createTrackbar('SMax', 'image', 0, 255, nothing)
cv2.createTrackbar('VMax', 'image', 0, 255, nothing)

# Set default value for Max HSV trackbars
cv2.setTrackbarPos('HMax', 'image', 179)
cv2.setTrackbarPos('SMax', 'image', 255)
cv2.setTrackbarPos('VMax', 'image', 255)

# Initialize HSV min/max values
hMin = sMin = vMin = hMax = sMax = vMax = 0
phMin = psMin = pvMin = phMax = psMax = pvMax = 0

while(1):
    # Get current positions of all trackbars
    hMin = cv2.getTrackbarPos('HMin', 'image')
    sMin = cv2.getTrackbarPos('SMin', 'image')
    vMin = cv2.getTrackbarPos('VMin', 'image')
    hMax = cv2.getTrackbarPos('HMax', 'image')
    sMax = cv2.getTrackbarPos('SMax', 'image')
    vMax = cv2.getTrackbarPos('VMax', 'image')

    # Set minimum and maximum HSV values to display
    lower = np.array([hMin, sMin, vMin])
    upper = np.array([hMax, sMax, vMax])

    # Convert to HSV format and color threshold
    hsv = cv2.cvtColor(image, cv2.COLOR_BGR2HSV)
    mask = cv2.inRange(hsv, lower, upper)
    result = cv2.bitwise_and(image, image, mask=mask)

    # Print if there is a change in HSV value
    if((phMin != hMin) | (psMin != sMin) | (pvMin != vMin) | (phMax != hMax) | (psMax != sMax) | (pvMax != vMax) ):
        print("(hMin = %d , sMin = %d, vMin = %d), (hMax = %d , sMax = %d, vMax = %d)" % (hMin , sMin , vMin, hMax, sMax , vMax))
        phMin = hMin
        psMin = sMin
        pvMin = vMin
        phMax = hMax
        psMax = sMax
        pvMax = vMax

    # Display result image
    cv2.imshow('image', result)
    if cv2.waitKey(10) & 0xFF == ord('q'):
        break

cv2.destroyAllWindows()

Answer 2

import cv2


def captch_ex(file_name):
    img = cv2.imread(file_name)

    img_final = cv2.imread(file_name)
    img2gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    ret, mask = cv2.threshold(img2gray, 180, 255, cv2.THRESH_BINARY)
    image_final = cv2.bitwise_and(img2gray, img2gray, mask=mask)
    ret, new_img = cv2.threshold(image_final, 180, 255, cv2.THRESH_BINARY)  # for black text , cv.THRESH_BINARY_INV
    '''
            line  8 to 12  : Remove noisy portion 
    '''
    kernel = cv2.getStructuringElement(cv2.MORPH_CROSS, (3,
                                                         3))  # to manipulate the orientation of dilution , large x means horizonatally dilating  more, large y means vertically dilating more
    dilated = cv2.dilate(new_img, kernel, iterations=9)  # dilate , more the iteration more the dilation

    # for cv2.x.x

    _, contours, hierarchy = cv2.findContours(dilated, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)  # findContours returns 3 variables for getting contours

    # for cv3.x.x comment above line and uncomment line below

    #image, contours, hierarchy = cv2.findContours(dilated,cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_NONE)


    for contour in contours:
        # get rectangle bounding contour
        [x, y, w, h] = cv2.boundingRect(contour)

        # Don't plot small false positives that aren't text
        if w < 35 and h < 35:
            continue

        # draw rectangle around contour on original image
        cv2.rectangle(img, (x, y), (x + w, y + h), (255, 0, 255), 2)

        '''
        #you can crop image and send to OCR  , false detected will return no text :)
        cropped = img_final[y :y +  h , x : x + w]

        s = file_name + '/crop_' + str(index) + '.jpg' 
        cv2.imwrite(s , cropped)
        index = index + 1

        '''
    # write original image with added contours to disk
    cv2.imshow('captcha_result', img)
    cv2.waitKey()


file_name = 'your_image.jpg'
captch_ex(file_name)

Answer 3

如果您不介意弄脏手，您可以尝试将这些文本区域扩展为一个更大的矩形区域，然后一次将其馈送给tesseract

我还建议尝试对图像进行多次阈值设置，然后分别将每个阈值输入tesseract，看看这是否有帮助。您可以将输出与字典单词进行比较，以自动确定特定OCR结果是否良好