我具有结构化表格图像中的数据。数据如下:
我尝试使用此代码从该图像中提取文本:
import pytesseract
from PIL import Image
value=Image.open("data/pic_table3.png")
text = pytesseract.image_to_string(value, lang="eng")
print(text)
并且,这是输出:
EA域
传统角色
未来角色
技术e封闭平台¢开放平台
e物理e虚拟化应用程序和| e专有e组织间集成e筒状复合材料e P2P集成应用程序
e EAI技术e软件即服务
e企业系统e面向服务
e自动交易架构
e“信息化”
互动
但是,预期的数据输出应根据列和行进行对齐。我该怎么办?
据我所知,我们不能通过使用pytesseract来做到这一点。
您必须先对图像进行预处理,以除去表格中的线条和点,然后再将其投入OCR。这是使用OpenCV的一种方法。
这里是经过处理的图像:
Pytesseract的结果
EA Domains Traditional role Future role
Technology Closed platforms Open platforms
Physical Virtualized
Applications and Proprietary Inter-organizational
Integration Siloed composite
P2P integrations applications
EAI technology Software as a Service
Enterprise Systems Service-Oriented
Automating transactions Architecture
“‘Informating”
interactions
代码
import cv2
import pytesseract
pytesseract.pytesseract.tesseract_cmd = r"C:\Program Files\Tesseract-OCR\tesseract.exe"
# Load image, grayscale, and Otsu's threshold
image = cv2.imread('1.png')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
# Remove horizontal lines
horizontal_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (50,1))
detect_horizontal = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, horizontal_kernel, iterations=2)
cnts = cv2.findContours(detect_horizontal, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
cv2.drawContours(thresh, [c], -1, (0,0,0), 2)
# Remove vertical lines
vertical_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1,15))
detect_vertical = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, vertical_kernel, iterations=2)
cnts = cv2.findContours(detect_vertical, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
cv2.drawContours(thresh, [c], -1, (0,0,0), 3)
# Dilate to connect text and remove dots
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (10,1))
dilate = cv2.dilate(thresh, kernel, iterations=2)
cnts = cv2.findContours(dilate, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
area = cv2.contourArea(c)
if area < 500:
cv2.drawContours(dilate, [c], -1, (0,0,0), -1)
# Bitwise-and to reconstruct image
result = cv2.bitwise_and(image, image, mask=dilate)
result[dilate==0] = (255,255,255)
# OCR
data = pytesseract.image_to_string(result, lang='eng',config='--psm 6')
print(data)
cv2.imshow('thresh', thresh)
cv2.imshow('result', result)
cv2.imshow('dilate', dilate)
cv2.waitKey()