如何从图像中提取前景文本？

Question

如何使用opencv完美提取下图中的数字文字？文字颜色是动态的。

Answer 1

我会从 pyimage 搜索中查看这个 post，它基本上为您执行此操作：https://www.pyimagesearch.com/2017/07/17/credit-card-ocr-with-opencv-and-python/。肯定有更好的分类器，但这是一个很好的起点。

Answer 2

很简单。以下代码可以高度优化（我做得很快 - @Silencer 可以做到这一点）并且也可以与其他图像一起工作（测试）（对于某些你将不得不调整一些值）。

import cv2
import numpy as np

# import image
image = cv2.imread('image.png')
cv2.imshow('original', image)
cv2.waitKey(0)

hsv = cv2.cvtColor(image, cv2.COLOR_BGR2HSV)
cv2.imshow('hsv', hsv[:, :, 1])
cv2.waitKey(0)

# this calculate the histogram of the image you input
# if this is under/below a certain value (which depend of the colors in the image), a certain thresh will be choosed among another
hist, bins = np.histogram(hsv.ravel(), 256, [0, 256])
print(hist[-1])

if hist[-1] > 15000:

    # binary
    ret, thresh = cv2.threshold(hsv[:, :, 0], 55, 255, cv2.THRESH_BINARY_INV | cv2.THRESH_OTSU)
    cv2.imshow('second', thresh)
    cv2.waitKey(0)

    # dilation
    kernel = np.ones((1, 1), np.uint8)
    img_dilation = cv2.dilate(thresh, kernel, iterations=1)
    cv2.imshow('dilated', img_dilation)
    cv2.waitKey(0)

    # find contours
    im2, ctrs, hier = cv2.findContours(img_dilation.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

    # sort contours
    sorted_ctrs = sorted(ctrs, key=lambda ctr: cv2.boundingRect(ctr)[0])

    for i, ctr in enumerate(sorted_ctrs):
        # Get bounding box
        x, y, w, h = cv2.boundingRect(ctr)

        # Getting ROI
        roi = image[y:y + h, x:x + w]

        # show ROI
        # cv2.imshow('segment no:'+str(i),roi)
        cv2.rectangle(image, (x, y), (x + w, y + h), (0, 255, 0), 2)
        # cv2.waitKey(0)

        if w > 15 and h > 15:
            cv2.imwrite('roi{}.png'.format(i), roi)

    cv2.imshow('marked areas', image)
    cv2.waitKey(0)

else:
    # binary
    ret, thresh = cv2.threshold(hsv[:, :, 0], 55, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)
    cv2.imshow('second', thresh)
    cv2.waitKey(0)

    # dilation
    kernel = np.ones((1, 1), np.uint8)
    img_dilation = cv2.dilate(thresh, kernel, iterations=1)
    cv2.imshow('dilated', img_dilation)
    cv2.waitKey(0)

    # find contours
    im2, ctrs, hier = cv2.findContours(img_dilation.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

    # sort contours
    sorted_ctrs = sorted(ctrs, key=lambda ctr: cv2.boundingRect(ctr)[0])

    for i, ctr in enumerate(sorted_ctrs):
        # Get bounding box
        x, y, w, h = cv2.boundingRect(ctr)

        # Getting ROI
        roi = image[y:y + h, x:x + w]

        # show ROI
        # cv2.imshow('segment no:'+str(i),roi)
        cv2.rectangle(image, (x, y), (x + w, y + h), (0, 255, 0), 2)
        # cv2.waitKey(0)

        if w > 15 and h > 15:
            cv2.imwrite('roi{}.png'.format(i), roi)

    cv2.imshow('marked areas', image)
    cv2.waitKey(0)

如何从图像中提取前景文本？

How to extract foreground text from an image?

opencv

background-foreground