Python 数字识别（在彩色屏幕上）

Question

我使用 python 搜索图像识别。似乎没有关于从彩色背景中提取数字的教程，所以我关注了THIS TUTORIAL

import cv2
import matplotlib.pyplot as plt 

def detect_edge(image):
''' function Detecting Edges '''

    image_with_edges = cv2.Canny(image , 100, 200)

    images = [image , image_with_edges]

    location = [121, 122]

    for loc, img in zip(location, images):
        plt.subplot(loc)
        plt.imshow(img, cmap='gray')

    plt.savefig('edge.png')
    plt.show()

image = cv2.imread('myscreenshot.png', 0)
detect_edge(image)

这是我的图片：

这是结果：

有什么办法可以打印出这些数字？

Answer 1

这里有一些代码可以为这张图片获取干净的精巧边缘。

import cv2
import numpy as np

# load image
img = cv2.imread("numbers.png");

# change to hue colorspace
hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV);
h,s,v = cv2.split(hsv);

# use clahe to improve contrast 
# (the contrast is pretty good already, so not much change, but good habit to have here)
clahe = cv2.createCLAHE(clipLimit = 10) 
contrast = clahe.apply(v);

# use canny
canny = cv2.Canny(contrast, 20, 110);

# show
cv2.imshow('i', img);
cv2.imshow('v', v);
cv2.imshow('c', contrast);
cv2.imshow("canny", canny);
cv2.waitKey(0);

# save
cv2.imwrite("edges.png", canny);

不使用任何像 pytesseract 之类的 OCR，我看不出有一种明显的方法可以始终将此图像转换为“文本”数字。我会把它留给其他可能知道如何在没有任何模式识别的情况下解决这个问题的人，因为没有它我什至不知道从哪里开始。如果你愿意放弃这个限制，那么 pytessaract 应该没有问题；甚至可能不进行这样的处理。

好的，我填写了图片的数字。由于某种原因，OpenCV 的 findContours 的层次结构不合作，所以我不得不手动完成，这使得这段代码非常笨拙。老实说，如果我要从头开始再试一次，我会尝试找到对每个像素和阈值有贡献的颜色，然后组合蒙版。

import cv2
import numpy as np

# check if small box is in big box
def contained(big, small):
    # big corners
    x,y,w,h = big;
    big_tl = [x, y];
    big_br = [x+w, y+h];

    # small corners
    x,y,w,h = small;
    small_tl = [x, y];
    small_br = [x+w, y+h];

    # check
    if small_tl[0] > big_tl[0] and small_br[0] < big_br[0]:
        if small_tl[1] > big_tl[1] and small_br[1] < big_br[1]:
            return True;
    return False;

# load image
img = cv2.imread("numbers.png");

# change to hue colorspace
hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV);
h,s,v = cv2.split(hsv);

# use clahe to improve contrast 
# (the contrast is pretty good already, so not much change, but good habit to have here)
clahe = cv2.createCLAHE(clipLimit = 10) 
contrast = clahe.apply(v);

# rescale
scale = 2.0;
h, w = img.shape[:2];
h = int(h * scale);
w = int(w * scale);
contrast = cv2.resize(contrast, (w,h), cv2.INTER_LINEAR);
img = cv2.resize(img, (w,h), cv2.INTER_LINEAR);

# use canny
canny = cv2.Canny(contrast, 10, 60);

# show
cv2.imshow('i', img);
cv2.imshow('v', v);
cv2.imshow('c', contrast);
cv2.imshow("canny", canny);
cv2.waitKey(0);

# try to fill in contours
# contours
_, contours, hierarchy = cv2.findContours(canny, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE);

# filter contours by size
# filter out noisy bits and the big grid boxes
filtered = [];
for contour in contours:
    perimeter = cv2.arcLength(contour, True);
    if 50 < perimeter and perimeter < 750:
        filtered.append(contour);

# draw contours again
# create a mask of the contoured image
mask = np.zeros_like(contrast);
mask = cv2.drawContours(mask, filtered, -1, 255, -1);

# close to get rid of annoying little gaps
kernel = np.ones((3,3),np.uint8)
mask = cv2.dilate(mask,kernel,iterations = 1);
mask = cv2.erode(mask,kernel, iterations = 1);

# contours
_, contours, hierarchy = cv2.findContours(mask, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE);

# alright, hierarchy is being stupid, plan B
# SUUUUUPEEERRR JAAAANK
outer_cntrs = [a for a in range(len(contours))];
children = [];
for a in range(len(contours)):
    if a in outer_cntrs:
        # get current box
        big_box = cv2.boundingRect(contours[a]);
        # check against all other boxes
        for b in range(0, len(contours)):
            if b in outer_cntrs:
                small_box = cv2.boundingRect(contours[b]);
                # remove any children
                if contained(big_box, small_box):
                    outer_cntrs.remove(b);
                    children.append(contours[b]);

# # select by hierarchy
top_cntrs = [];
for a in range(len(contours)):
    if a in outer_cntrs:
        top_cntrs.append(contours[a]);

# create a mask of the contoured image
mask = np.zeros_like(contrast);
mask = cv2.drawContours(mask, top_cntrs, -1, 255, -1);
mask = cv2.drawContours(mask, children, -1, 255, -1);

# close
kernel = np.ones((3,3),np.uint8)
mask = cv2.dilate(mask,kernel,iterations = 1);
mask = cv2.erode(mask,kernel, iterations = 1);

# do contours agains because opencv is being super difficult
# honestly, at this point, a fill method would've been better
# contours
_, contours, hierarchy = cv2.findContours(mask, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE);

# fill in
for con in contours:
    cv2.fillPoly(mask, pts = [con], color=(255));
for con in children:
    cv2.fillPoly(mask, pts = [con], color=(0));

# resize back down
h, w = mask.shape;
h = int(h / scale);
w = int(w / scale);
mask = cv2.resize(mask, (w,h));

# show
cv2.imshow("mask", mask);
cv2.waitKey(0);

# save
cv2.imwrite("filled.png", mask);

Answer 2

你可以分三步找到数字

---

• 1. 申请Adaptive-threshold
• 1. 申请erosion
• 1. 使用pytesseract读取

---

1. 自适应阈值结果：

   • 在这里我们看到9 和0 与其他数字不同。我们需要去掉9的边界。

2. 侵蚀结果：

3. Pytesseract 结果：

   • 8 | 1
     
     5 9
     4 @
     3 | 3
     6 | 1
     

   • pytesseract 有多种页面分割模式可供选择

   • 如果你想从输出中删除|，你可以使用re.sub

   • text = re.sub('[^A-Za-z0-9]+', ',', text)
     

   • 结果将是：

     • 8
       1
       5
       9
       4
       3
       3
       6
       1
       

代码：

import cv2
import pytesseract
import re
import numpy as np

image = cv2.imread("7UUGYHw.png")
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
thresh = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_MEAN_C, cv2.THRESH_BINARY, 13, 2)
erode = cv2.erode(thresh, np.array((7, 7)), iterations=1)
text = pytesseract.image_to_string(erode, config="--psm 6")
text = re.sub('[^A-Za-z0-9]+', '\n', text)
print(text)