OpenCV 文字区域的提取

1. Detect

先来看main函数和Detect函数

def detect(img):
    # 1.  转化成灰度图
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

    # 2. 形态学变换的预处理，得到可以查找矩形的图片
    dilation = preprocess(gray)

    # 3. 查找和筛选文字区域
    region = findTextRegion(dilation)

    # 4. 用绿线画出这些找到的轮廓
    for box in region:
        cv2.drawContours(img, [box], 0, (0, 255, 0), 2)

    cv2.namedWindow("img", cv2.WINDOW_NORMAL)
    cv2.imshow("img", img)

    # 带轮廓的图片
    cv2.imwrite("contours.png", img)

    cv2.waitKey(0)
    cv2.destroyAllWindows()

2. Preprocess

利用数学形态学（Morphology）进行预处理。

这个过程很重要，是文字区域检测效果好坏的核心代码，尤其是一下几个参数：

• 膨胀的核函数大小，这里用了 30 x 9，可以调节
• 腐蚀的核函数大小，这里用了 24 x 6，可以调节

def preprocess(gray):
    # 1. Sobel算子，x方向求梯度
    sobel = cv2.Sobel(gray, cv2.CV_8U, 1, 0, ksize = 3)
    # 2. 二值化
    ret, binary = cv2.threshold(sobel, 0, 255, cv2.THRESH_OTSU+cv2.THRESH_BINARY)

    # 3. 膨胀和腐蚀操作的核函数
    element1 = cv2.getStructuringElement(cv2.MORPH_RECT, (30, 9))
    element2 = cv2.getStructuringElement(cv2.MORPH_RECT, (24, 6))

    # 4. 膨胀一次，让轮廓突出
    dilation = cv2.dilate(binary, element2, iterations = 1)

    # 5. 腐蚀一次，去掉细节，如表格线等。注意这里去掉的是竖直的线
    erosion = cv2.erode(dilation, element1, iterations = 1)

    # 6. 再次膨胀，让轮廓明显一些
    dilation2 = cv2.dilate(erosion, element2, iterations = 3)

    # 7. 存储中间图片 
    cv2.imwrite("binary.png", binary)
    cv2.imwrite("dilation.png", dilation)
    cv2.imwrite("erosion.png", erosion)
    cv2.imwrite("dilation2.png", dilation2)

    return dilation2

3. findTextRegion

def findTextRegion(img):
    region = []

    # 1. 查找轮廓
    contours, hierarchy = cv2.findContours(img, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)

    # 2. 筛选那些面积小的
    for i in range(len(contours)):
        cnt = contours[i]
        # 计算该轮廓的面积
        area = cv2.contourArea(cnt) 

        # 面积小的都筛选掉
        if(area < 1000):
            continue

        # 轮廓近似，作用很小
        epsilon = 0.001 * cv2.arcLength(cnt, True)
        approx = cv2.approxPolyDP(cnt, epsilon, True)

        # 找到最小的矩形，该矩形可能有方向
        rect = cv2.minAreaRect(cnt)
        print ("rect is: ",rect)
        

        # box是四个点的坐标
        box = cv2.boxPoints(rect)
        box = np.int0(box)

        # 计算高和宽
        height = abs(box[0][1] - box[2][1])
        width = abs(box[0][0] - box[2][0])

        # 筛选那些太细的矩形，留下扁的
        if(height > width * 1.2):
            continue

        region.append(box)

    return region

完整代码:

# coding:utf8



import cv2
import numpy as np

def preprocess(gray):
    # 1. Sobel算子，x方向求梯度
    sobel = cv2.Sobel(gray, cv2.CV_8U, 1, 0, ksize = 3)
    # 2. 二值化
    ret, binary = cv2.threshold(sobel, 0, 255, cv2.THRESH_OTSU+cv2.THRESH_BINARY)

    # 3. 膨胀和腐蚀操作的核函数
    element1 = cv2.getStructuringElement(cv2.MORPH_RECT, (30, 9))
    element2 = cv2.getStructuringElement(cv2.MORPH_RECT, (24, 6))

    # 4. 膨胀一次，让轮廓突出
    dilation = cv2.dilate(binary, element2, iterations = 1)

    # 5. 腐蚀一次，去掉细节，如表格线等。注意这里去掉的是竖直的线
    erosion = cv2.erode(dilation, element1, iterations = 1)

    # 6. 再次膨胀，让轮廓明显一些
    dilation2 = cv2.dilate(erosion, element2, iterations = 3)

    # 7. 存储中间图片 
    cv2.imwrite("binary.png", binary)
    cv2.imwrite("dilation.png", dilation)
    cv2.imwrite("erosion.png", erosion)
    cv2.imwrite("dilation2.png", dilation2)

    return dilation2


def findTextRegion(img):
    region = []

    # 1. 查找轮廓
    binary,contours,hierarchy = cv2.findContours(img, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)

    # 2. 筛选那些面积小的
    for i in range(len(contours)):
        cnt = contours[i]
        # 计算该轮廓的面积
        area = cv2.contourArea(cnt) 

        # 面积小的都筛选掉
        if(area < 1000):
            continue

        # 轮廓近似，作用很小
        epsilon = 0.001 * cv2.arcLength(cnt, True)
        approx = cv2.approxPolyDP(cnt, epsilon, True)

        # 找到最小的矩形，该矩形可能有方向
        rect = cv2.minAreaRect(cnt)
        print ("rect is: ",rect)

        # box是四个点的坐标
        box = cv2.boxPoints(rect)
        box = np.int0(box)

        # 计算高和宽
        height = abs(box[0][1] - box[2][1])
        width = abs(box[0][0] - box[2][0])

        # 筛选那些太细的矩形，留下扁的
        if(height > width * 1.2):
            continue

        region.append(box)

    return region


def detect(img):
    # 1.  转化成灰度图
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

    # 2. 形态学变换的预处理，得到可以查找矩形的图片
    dilation = preprocess(gray)

    # 3. 查找和筛选文字区域
    region = findTextRegion(dilation)

    # 4. 用绿线画出这些找到的轮廓
    for box in region:
        cv2.drawContours(img, [box], 0, (0, 255, 0), 2)

    cv2.namedWindow("img", cv2.WINDOW_NORMAL)
    cv2.imshow("img", img)

    # 带轮廓的图片
    cv2.imwrite("contours.png", img)

    cv2.waitKey(0)
    cv2.destroyAllWindows()


if __name__ == '__main__':
    # 读取文件
    img = cv2.imread('/Users/yuki/Downloads/timg3.jpg')
    detect(img)