Question

我正在尝试识别用卡通字体编写的数字，因此传统工具（例如pytesser）并没有真正起作用。但是，我能够使用cv2.matchTemplate和10位数的库获得非常准确的单位数识别。我基本上将每个数字视为一个符号，只是试图找到最佳匹配。

import cv2
import numpy as np

def match_char(im1, im2):
    result = cv2.matchTemplate(im1,im2,cv2.TM_CCOEFF_NORMED)
    min_val, max_val, min_loc, max_loc = cv2.minMaxLoc(result)
    return max_va

def process_image(im, i):
    try:
        gray = cv2.cvtColor(im, cv2.COLOR_BGR2GRAY)
        a, t = cv2.threshold(gray, 220, 255, cv2.THRESH_BINARY_INV)
        return t
    except:
        print("Error while processing the image")
        pass

def process_lib(im, i):
    try:
        gray = cv2.cvtColor(im, cv2.COLOR_BGR2GRAY)

        a, t = cv2.threshold(gray, 220, 255, cv2.THRESH_BINARY)
        return t
    except:
        print("Error while processing the image")
        pass

def process_num():
    test = cv2.imread('test.png')
    test = process_image(test, 11)
    test = cv2.resize(test, (0,0), fx=2.2, fy=2.2) #best
    scores = [] 

    for i in range(10):
        img = cv2.imread('char-{}.png'.format(i))
        img = process_lib(img, i)
        scores.append(match_char(img, test))

    win = scores.index(max(scores))
    print("The best match is {} with {}".format(win, scores[win]))

问题是我无法将其扩展为多位数字。即使生成两位数字并尝试匹配它们，程序也始终将单个数字标识为最佳匹配。如果我将搜索限制为两位数字，它有时会得到一个数字正确，但从不两者都有。当然，这不是最优雅的解决方案，但它似乎最简单，甚至不起作用。

Answer 1

您应该定义一个阈值并过滤此阈值下面的cv2.matchTemplate结果

我认为以下代码适合您：

import cv2 as cv
import numpy as np

img_rgb = cv.imread('image.png')
img_gray = cv.cvtColor(img_rgb, cv.COLOR_BGR2GRAY)
template = cv.imread('template.png',0)
w, h = template.shape[::-1]
res = cv.matchTemplate(img_gray,template,cv.TM_CCOEFF_NORMED)
threshold = 0.8
loc = np.where( res >= threshold)
for pt in zip(*loc[::-1]):
    cv.rectangle(img_rgb, pt, (pt[0] + w, pt[1] + h), (0,0,255), 2)
cv.imwrite('res.png',img_rgb)

了解更多信息see

OpenCV - 识别一系列符号

1 个答案: