将带有文本(和图片)的图像文件分割成块
Segmenting image files with text (and pictures) into blocks
我正在尝试为我拥有的图像中的文本创建边界框。下面就是一个例子。
我想在每条 This is a test
行周围添加一个边界框。不幸的是,我不确定为什么这种方法不能自动识别边界框
import re
import cv2
import numpy as np
import pytesseract
from pytesseract import Output
from matplotlib import pyplot as plt
# Plot character boxes on image using pytesseract.image_to_boxes() function
image = cv2.imread('Image.jpg')
b, g, r = cv2.split(image)
image = cv2.merge([r,g,b])
d = pytesseract.image_to_data(image, output_type=Output.DICT)
print('DATA KEYS: \n', d.keys())
n_boxes = len(d['text'])
for i in range(n_boxes):
# condition to only pick boxes with a confidence > 60%
if int(d['conf'][i]) > 60:
(x, y, w, h) = (d['left'][i], d['top'][i], d['width'][i], d['height'][i])
image = cv2.rectangle(image, (x, y), (x + w, y + h), (0, 255, 0), 2)
b, g, r = cv2.split(image)
rgb_img = cv2.merge([r, g, b])
plt.figure(figsize=(16, 12))
plt.imshow(rgb_img)
plt.title('SAMPLE IMAGE WITH WORD LEVEL BOXES')
plt.show()
这是 Python/OpenCV 的另一种方法。
- 读取输入
- 转换为灰色
- (OTSU) 阈值(黑底白字)
- 应用形态学扩展,水平内核长于字母间距,然后垂直内核更小,以删除页面中行中剩余的细水平线。
- 寻找轮廓
- 在输入上绘制轮廓边界框
- 保存结果
输入:
import cv2
import numpy as np
# load image
img = cv2.imread("test_text.jpg")
# convert to gray
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# threshold the grayscale image
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
# use morphology erode to blur horizontally
#kernel = np.ones((500,3), np.uint8)
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (250, 3))
morph = cv2.morphologyEx(thresh, cv2.MORPH_DILATE, kernel)
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3, 17))
morph = cv2.morphologyEx(morph, cv2.MORPH_OPEN, kernel)
# find contours
cntrs = cv2.findContours(morph, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cntrs = cntrs[0] if len(cntrs) == 2 else cntrs[1]
# Draw contours
result = img.copy()
for c in cntrs:
x,y,w,h = cv2.boundingRect(c)
cv2.rectangle(result, (x, y), (x+w, y+h), (0, 0, 255), 2)
# write result to disk
cv2.imwrite("test_text_threshold.png", thresh)
cv2.imwrite("test_text_morph.png", morph)
cv2.imwrite("test_text_lines.jpg", result)
cv2.imshow("GRAY", gray)
cv2.imshow("THRESH", thresh)
cv2.imshow("MORPH", morph)
cv2.imshow("RESULT", result)
cv2.waitKey(0)
cv2.destroyAllWindows()
阈值图像:
膨胀图像:
结果:
我正在尝试为我拥有的图像中的文本创建边界框。下面就是一个例子。
我想在每条 This is a test
行周围添加一个边界框。不幸的是,我不确定为什么这种方法不能自动识别边界框
import re
import cv2
import numpy as np
import pytesseract
from pytesseract import Output
from matplotlib import pyplot as plt
# Plot character boxes on image using pytesseract.image_to_boxes() function
image = cv2.imread('Image.jpg')
b, g, r = cv2.split(image)
image = cv2.merge([r,g,b])
d = pytesseract.image_to_data(image, output_type=Output.DICT)
print('DATA KEYS: \n', d.keys())
n_boxes = len(d['text'])
for i in range(n_boxes):
# condition to only pick boxes with a confidence > 60%
if int(d['conf'][i]) > 60:
(x, y, w, h) = (d['left'][i], d['top'][i], d['width'][i], d['height'][i])
image = cv2.rectangle(image, (x, y), (x + w, y + h), (0, 255, 0), 2)
b, g, r = cv2.split(image)
rgb_img = cv2.merge([r, g, b])
plt.figure(figsize=(16, 12))
plt.imshow(rgb_img)
plt.title('SAMPLE IMAGE WITH WORD LEVEL BOXES')
plt.show()
这是 Python/OpenCV 的另一种方法。
- 读取输入
- 转换为灰色
- (OTSU) 阈值(黑底白字)
- 应用形态学扩展,水平内核长于字母间距,然后垂直内核更小,以删除页面中行中剩余的细水平线。
- 寻找轮廓
- 在输入上绘制轮廓边界框
- 保存结果
输入:
import cv2
import numpy as np
# load image
img = cv2.imread("test_text.jpg")
# convert to gray
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# threshold the grayscale image
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
# use morphology erode to blur horizontally
#kernel = np.ones((500,3), np.uint8)
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (250, 3))
morph = cv2.morphologyEx(thresh, cv2.MORPH_DILATE, kernel)
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3, 17))
morph = cv2.morphologyEx(morph, cv2.MORPH_OPEN, kernel)
# find contours
cntrs = cv2.findContours(morph, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cntrs = cntrs[0] if len(cntrs) == 2 else cntrs[1]
# Draw contours
result = img.copy()
for c in cntrs:
x,y,w,h = cv2.boundingRect(c)
cv2.rectangle(result, (x, y), (x+w, y+h), (0, 0, 255), 2)
# write result to disk
cv2.imwrite("test_text_threshold.png", thresh)
cv2.imwrite("test_text_morph.png", morph)
cv2.imwrite("test_text_lines.jpg", result)
cv2.imshow("GRAY", gray)
cv2.imshow("THRESH", thresh)
cv2.imshow("MORPH", morph)
cv2.imshow("RESULT", result)
cv2.waitKey(0)
cv2.destroyAllWindows()
阈值图像:
膨胀图像:
结果: