|
|
from fastapi import FastAPI |
|
|
from pydantic import BaseModel |
|
|
import easyocr |
|
|
import numpy as np |
|
|
from PIL import Image |
|
|
import cv2 |
|
|
import base64 |
|
|
import io |
|
|
import os |
|
|
|
|
|
app = FastAPI(title="OCR Base64 API") |
|
|
|
|
|
model_storage_dir = '/code/.EasyOCR' |
|
|
os.makedirs(model_storage_dir, exist_ok=True) |
|
|
|
|
|
reader = easyocr.Reader(['en'], gpu=False, model_storage_directory=model_storage_dir) |
|
|
|
|
|
class ImageRequest(BaseModel): |
|
|
image_base64: str |
|
|
|
|
|
def preprocess_image(image): |
|
|
gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY) |
|
|
scale_percent = 200 |
|
|
width = int(gray.shape[1] * scale_percent / 100) |
|
|
height = int(gray.shape[0] * scale_percent / 100) |
|
|
resized = cv2.resize(gray, (width, height), interpolation=cv2.INTER_LINEAR) |
|
|
_, thresh = cv2.threshold(resized, 150, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU) |
|
|
return thresh |
|
|
|
|
|
@app.post("/extract-text/") |
|
|
def extract_text(request: ImageRequest): |
|
|
try: |
|
|
b64_data = request.image_base64 |
|
|
if "base64," in b64_data: |
|
|
b64_data = b64_data.split("base64,")[1] |
|
|
|
|
|
image_bytes = base64.b64decode(b64_data) |
|
|
image = Image.open(io.BytesIO(image_bytes)).convert("RGB") |
|
|
img_np = np.array(image) |
|
|
|
|
|
processed_img = preprocess_image(img_np) |
|
|
|
|
|
results = reader.readtext(processed_img) |
|
|
extracted_text = [text.replace(" ", "") for _, text, _ in results] |
|
|
|
|
|
text_result = " ".join(extracted_text) if extracted_text else "" |
|
|
|
|
|
return { |
|
|
"success": True, |
|
|
"text": text_result |
|
|
} |
|
|
|
|
|
except Exception as e: |
|
|
return { |
|
|
"success": False, |
|
|
"error": str(e) |
|
|
} |
|
|
|
|
|
@app.get("/") |
|
|
def read_root(): |
|
|
return {"message": "API is running!"} |
