Python中图片与PDF识别文本(OCR)的全面指南

import pytesseract
from PIL import Image

# 基本识别
text = pytesseract.image_to_string(Image.open('invoice.jpg'))
print(text)

# 进阶配置（指定语言和引擎）
config = r'--oem 3 --psm 6 -l eng+chi_sim'
detailed_text = pytesseract.image_to_string(
    image, 
    config=config
)

import easyocr

reader = easyocr.Reader(['ch_sim','en'])  # 支持80+语言
results = reader.readtext('menu.png', 
                         detail=0,       # 简化输出
                         paragraph=True)  # 保持段落结构

for result in results:
    print(result[1])  # 输出识别文本

from paddleocr import PaddleOCR

ocr = PaddleOCR(use_angle_cls=True, lang="ch")
result = ocr.ocr('contract.jpg', cls=True)

# 结构化输出识别结果
for line in result:
    print(f"位置: {line[0]}, 文本: {line[1][0]}, 置信度: {line[1][1]:.2f}")

# 命令行工具（需单独安装）
ocrmypdf --output-type pdfa input_scanned.pdf output_searchable.pdf

# 文本型PDF提取
import pdfplumber

with pdfplumber.open('text_document.pdf') as pdf:
    all_text = ''.join(page.extract_text() for page in pdf.pages)

# 扫描版PDF处理
from pdf2image import convert_from_path
import pytesseract

images = convert_from_path('scanned_doc.pdf', dpi=300)
for i, image in enumerate(images):
    text = pytesseract.image_to_string(image, lang='eng')
    print(f"Page {i+1}:\n{text}\n{'-'*50}")

import cv2

def preprocess_image(img_path):
    img = cv2.imread(img_path)
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    thresh = cv2.threshold(gray, 0, 255, 
                          cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]
    denoised = cv2.fastNlMeansDenoising(thresh, h=30)
    return denoised

import layoutparser as lp

model = lp.Detectron2LayoutModel('lp://PubLayNet/faster_rcnn_R_50_FPN_3x/config')
image = lp.load_image('paper.png')
layout = model.detect(image)

# 按区域提取文本
text_blocks = [b for b in layout if b.type=='Text']
for block in text_blocks:
    segment_image = block.pad(20).crop_image(image)
    print(pytesseract.image_to_string(segment_image))

from difflib import SequenceMatcher

def ocr_ensemble(img_path):
    tesseract_res = pytesseract.image_to_string(img_path)
    easyocr_res = ''.join(easyocr.Reader(['en']).readtext(img_path, detail=0))
    
    # 相似度加权融合
    similarity = SequenceMatcher(None, tesseract_res, easyocr_res).ratio()
    if similarity > 0.9:
        return max(tesseract_res, easyocr_res, key=len)
    else:
        return f"TESSERACT:\n{tesseract_res}\n\nEASYOCR:\n{easyocr_res}"

# GPU加速（以PaddleOCR为例）
ocr = PaddleOCR(use_gpu=True, gpu_mem=5000)  # 分配5GB显存

# 批量处理并行化
from concurrent.futures import ThreadPoolExecutor

def process_image(img_path):
    return pytesseract.image_to_string(img_path)

with ThreadPoolExecutor(max_workers=8) as executor:
    results = list(executor.map(process_image, image_paths))