OCR

# OCR 구현 예제 (Tesseract + EasyOCR)
# pip install pytesseract easyocr pillow

import pytesseract
from PIL import Image
import easyocr

# ===== 1. Tesseract OCR (오픈소스) =====
# Tesseract 설치 필요: apt-get install tesseract-ocr tesseract-ocr-kor

def tesseract_ocr(image_path):
    """Tesseract로 텍스트 추출"""
    image = Image.open(image_path)
    # 한글 + 영어 인식
    text = pytesseract.image_to_string(image, lang='kor+eng')
    return text

# 상세 정보 (위치, 신뢰도 포함)
def tesseract_detailed(image_path):
    image = Image.open(image_path)
    data = pytesseract.image_to_data(image, lang='kor+eng', output_type=pytesseract.Output.DICT)
    return data

# ===== 2. EasyOCR (딥러닝 기반) =====
def easy_ocr(image_path):
    """EasyOCR로 텍스트 추출 (GPU 지원)"""
    reader = easyocr.Reader(['ko', 'en'])  # 한글, 영어
    results = reader.readtext(image_path)

    # 결과: [(좌표, 텍스트, 신뢰도), ...]
    for (bbox, text, confidence) in results:
        print(f"텍스트: {text}, 신뢰도: {confidence:.2%}")

    return results

# ===== 3. Google Cloud Vision API =====
# pip install google-cloud-vision
from google.cloud import vision

def google_vision_ocr(image_path):
    """Google Vision API로 고품질 OCR"""
    client = vision.ImageAnnotatorClient()

    with open(image_path, 'rb') as f:
        content = f.read()

    image = vision.Image(content=content)
    response = client.text_detection(image=image)
    texts = response.text_annotations

    if texts:
        return texts[0].description  # 전체 텍스트
    return ""

# ===== 4. 이미지 전처리 (정확도 향상) =====
import cv2
import numpy as np

def preprocess_image(image_path):
    """OCR 전 이미지 품질 개선"""
    img = cv2.imread(image_path)
    # 그레이스케일 변환
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    # 노이즈 제거
    denoised = cv2.fastNlMeansDenoising(gray)
    # 이진화 (Adaptive Threshold)
    binary = cv2.adaptiveThreshold(
        denoised, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C,
        cv2.THRESH_BINARY, 11, 2
    )
    return binary

# 사용 예시
# text = tesseract_ocr("document.png")
# results = easy_ocr("receipt.jpg")