cv2.rectangle 加入最近的边界框

Question

我试图在扫描的页面中分离出中世纪手稿中的文字。我正在使用 cv2 来检测区域 ant id 给了我一个非常令人满意的结果。我用增量数字标记了每个矩形，我担心检测到的区域不连续： Here is a sample result of cv2 bounding box zones on a word

这是我使用的代码：

import numpy as np
import cv2
import matplotlib.pyplot as plt
# This is font for labels
font = cv2.FONT_HERSHEY_SIMPLEX
# I load a picture of a page, gray and blur it
im = cv2.imread('test.png')
imgray = cv2.cvtColor(im,cv2.COLOR_BGR2GRAY)
image_blurred = cv2.GaussianBlur(imgray, (5, 5), 0)
image_blurred = cv2.dilate(image_blurred, None)
ret,thresh = cv2.threshold(image_blurred,0,255,0,cv2.THRESH_BINARY + cv2.THRESH_OTSU)
# I try to retrieve contours and hierarchy on the sample
_, contours, hierarchy =    cv2.findContours(thresh,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)
hierarchy = hierarchy[0]
# I read every contours and retrieve the bounding box 
for i,component in enumerate(zip(contours, hierarchy)):
    cnt = component[0]
    currentHierarchy = component[1]
    precision = 0.01
    epsilon = precision*cv2.arcLength(cnt,True)
    approx = cv2.approxPolyDP(cnt,epsilon,True)
    # This is the best combination I found to isolate parents container
    # It gives me the best result (even if I'm not sure what I'm doing)
    # hierarchy[2/3] is "having child" / "having parent"
    # I thought  currentHierarchy[3] < 0 should be better
    # but it gives no result
    if currentHierarchy[2] > 0 and currentHierarchy[3] > 0:
        x,y,w,h = cv2.boundingRect(approx)
        cv2.rectangle(im,(x,y),(x+w,y+h),(0,255,0),2)
        cv2.putText(im,str(i),(x+2,y+2), font, 1,(0,255,0),2,cv2.LINE_AA)

plt.imshow(im)
plt.show()

我想将最近的区域连接在一起，以便对我的页面进行词标记化。在我的示例图片中，我想加入2835、2847、2864、2878、2870和2868。

我该怎么办？我以为我可以将每个框的每个坐标存储在一个数组中，然后测试 (start_x、start_y) 和 (end_x、end_y) - 但对我来说这似乎很糟糕。

能给个提示吗？

谢谢，

Answer 1

我继续我的方法来找出单个单词。虽然不完全准确，但请看下面这张图片：

伪代码：

对灰度图像应用高斯模糊。
执行了 Otsu 的阈值。
执行了几个形态学操作：

3.1 侵蚀，尝试去除图像左上角的细线。

3.2 扩张连接由于之前的操作而分开的单个字母。
找到特定区域上方的等高线并标记它们

编辑

代码：

import numpy as np
import cv2
import matplotlib.pyplot as plt
font = cv2.FONT_HERSHEY_SIMPLEX

im = cv2.imread('corpus.png')
imgray = cv2.cvtColor(im,cv2.COLOR_BGR2GRAY)
image_blurred = cv2.GaussianBlur(imgray, (9, 9), 0)
cv2.imshow('blur', image_blurred)

image_blurred_d = cv2.dilate(image_blurred, None)
cv2.imshow('dilated_blur', image_blurred_d)

ret,thresh = cv2.threshold(image_blurred_d, 127, 255, cv2.THRESH_BINARY_INV +     cv2.THRESH_OTSU)
cv2.imshow('thresh', thresh)

kernel = cv2.getStructuringElement(cv2.MORPH_CROSS, (3, 3))
erosion = cv2.erode(thresh, kernel, iterations = 1)
cv2.imshow('erosion', erosion)

kernel1 = cv2.getStructuringElement(cv2.MORPH_RECT, (3, 3))
dilation = cv2.dilate(erosion, kernel1, iterations = 1)
cv2.imshow('dilation', dilation)

_, contours, hierarchy =    cv2.findContours(dilation, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
count = 0
for cnt in contours:
    if (cv2.contourArea(cnt) > 100):
        x, y, w, h = cv2.boundingRect(cnt)
        cv2.rectangle(im, (x,y), (x+w,y+h), (0, 255, 0), 2)
        count+=1
print('Number of probable words', count)

cv2.imshow('final', im)
cv2.waitKey(0)
cv2.destroyAllWindows()

Answer 2

谢谢 Jeru Luke, we could implement this try on a complete page. The values given were very helpful, overall for kernel adaptation in blurring and eroding operation. The final result on the Bible Historiale Manuscript page 还是很有趣的。我们可以在标识中看到一些 "black holes"，据我所知，这是由于膨胀；这是第一个正在进行的工作。我们将不得不管理大图片和首字母大字母。这是我们用来过滤框、在框上添加标签并将每个片段保存在单独文件中的代码：

for i,component in enumerate(zip(contours, hierarchy)):
    cnt = component[0]
    currentHierarchy = component[1]
    if currentHierarchy[2] > 0 and currentHierarchy[3] > 0:
        x,y,w,h = cv2.boundingRect(approx)
        if h < 300 and h > 110 and w > 110:
            cv2.rectangle(im,(x-5,y-5),(x+w+5,y+h+5),(0,255,0),8)
            cv2.putText(im,str(i),(x+2,y+2), font, 1,(0,255,0),2,cv2.LINE_AA)
            cv2.putText(im,str(cv2.contourArea(cnt)),(x+w-2,y+h-2), font, 1,(0,255,0),2,cv2.LINE_AA)
            cv2.putText(im,str(h)+'/'+str(w),(x+w-2,y+h-2), font, 1,(0,0,255),2,cv2.LINE_AA)
            fragment = im[y:y+h, x:x+w]
            cv2.imwrite("res" + str(i) + ".png", fragment)

cv2.rectangle 加入最近的边界框

cv2.rectangle join closest bounding box

python

opencv

bounding-box