使用Opencv检测图像中的文本区域

时间：2014-06-24 11:41:39

标签： python-2.7 opencv python-tesseract

我有一张图片，想要检测其中的文字区域。

我尝试了TiRG_RAW_20110219项目但效果不理想。如果输入图像为http://imgur.com/yCxOvQS,GD38rCa，则输出http://imgur.com/yCxOvQS,GD38rCa#1。

任何人都可以提出一些替代方案。我希望通过仅将文本区域作为输入发送来改善tesseract的输出。

3 个答案:

答案 0 :(得分：49)

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)

Click to see result

Click to see result

答案 1 :(得分：6)

由于没有人发布完整的解决方案，因此这是一种方法。通过观察到期望的文本为白色并且单词以水平对齐的方式进行观察，我们可以使用颜色分割来提取和OCR字母。

  1. 执行颜色分割。我们使用cv2.inRange加载图像，转换为HSV格式，定义较低/较高范围并执行颜色分割以获得二进制蒙版

  2. 膨胀以连接文本字符。我们使用cv2.getStructuringElement创建一个水平形状的内核，然后使用cv2.dilate进行膨胀以将单个字母组合成一个轮廓

  3. 删除非文本轮廓。我们用cv2.findContours查找轮廓，并使用宽高比过滤以删除非文本字符。由于文本处于水平方向，因此如果确定轮廓小于预定义的宽高比阈值，则通过用cv2.drawContours

    4. 填充轮廓来删除非文本轮廓

  4. 执行OCR。我们按位对扩展后的图像和初始遮罩进行隔离，以仅隔离文本字符并反转图像，以使文本为黑色，背景为白色。最后，我们将图像放入Pytesseract OCR

以下是每个步骤的可视化结果：

输入图片

通过颜色分割生成的遮罩

# 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)

用于通过宽高比过滤连接文本轮廓和去除非文本轮廓的膨胀图像

# 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)

按位运算-以及两个掩码和取反，为OCR准备好结果

# 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)

Pytesseract OCR使用--psm 6配置设置假定统一的文本块的结果。在here中查找更多配置选项

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()

使用此HSV颜色阈值设置脚本确定HSV上下颜色范围

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()

答案 2 :(得分：3)

如果你不介意弄脏手，你可以尝试将这些文本区域扩展到一个更大的矩形区域，您可以一次性进行测试。

我还建议尝试对图像进行几次阈值处理，并将每个图像分别送到tesseract，看看是否有帮助。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。

相关问题
最新问题