import cv2 import os import numpy as np from io import BytesIO from PIL import Image from fastapi import FastAPI, File, UploadFile, HTTPException import easyocr import fitz app = FastAPI() current_directory = os.getcwd() @app.get('/') async def index(): return "Welcome EasyOCR By SENEL" @app.post("/uploadfile/") async def create_upload_file(file: UploadFile = File(...)): try: # Dosyayı bellekte geçici bir nesne olarak tut file_content = await file.read() result = perform_ocr(file_content, file.filename) return result except Exception as e: raise HTTPException(status_code=500, detail=str(e)) def perform_ocr(file_content, file_name): # Dosyayı bellekte geçici bir dosya olarak kullan with BytesIO(file_content) as buffer: if file_name.lower().endswith('.pdf'): # PDF dosyasını işle results = apply_ocr_on_pdf(buffer) elif file_name.lower().endswith(('.jpg', '.jpeg', '.png')): # Resmi doğrudan işle results = apply_ocr_on_image(buffer) else: raise HTTPException(status_code=400, detail="Unsupported file format") return results def apply_ocr_on_pdf(buffer): pdf_document = fitz.open("pdf", buffer.read()) images = [] for page_number in range(pdf_document.page_count): page = pdf_document[page_number] pixmap = page.get_pixmap(dpi=400) image = Image.frombytes("RGB", [pixmap.width, pixmap.height], pixmap.samples) img_array = np.array(image) img_array_bgr = cv2.cvtColor(img_array, cv2.COLOR_RGB2BGR) image = preprocess_image(img_array_bgr) images.append(image) pdf_document.close() results = [] for image in images: reader = easyocr.Reader(['tr'], gpu=True, model_storage_directory=f"{current_directory}/model", user_network_directory=f"{current_directory}/user_network", download_enabled=False) result = reader.readtext(image,min_size=50, detail=0, paragraph=False, width_ths=0.9, blocklist="|[]{}") results.extend(result) return results def apply_ocr_on_image(buffer): reader = easyocr.Reader(['tr'], gpu=True, model_storage_directory=f"{current_directory}/model", user_network_directory=f"{current_directory}/user_network", download_enabled=False) image = cv2.imdecode(np.frombuffer(buffer.read(), np.uint8), cv2.IMREAD_COLOR) image = preprocess_image(image) result = reader.readtext(image, min_size=50, detail=0, paragraph=False, width_ths=1) return result def getSkewAngle(cvImage) -> float: # Prep image, copy, convert to gray scale, blur, and threshold newImage = cvImage.copy() gray = cv2.cvtColor(newImage, cv2.COLOR_BGR2GRAY) blur = cv2.GaussianBlur(gray, (9, 9), 0) thresh = cv2.threshold(blur, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1] # Apply dilate to merge text into meaningful lines/paragraphs. # Use larger kernel on X axis to merge characters into single line, cancelling out any spaces. # But use smaller kernel on Y axis to separate between different blocks of text kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (30, 5)) dilate = cv2.dilate(thresh, kernel, iterations=2) # Find all contours contours, hierarchy = cv2.findContours(dilate, cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE) contours = [cnt for cnt in contours if cv2.contourArea(cnt) > 1000] contours = sorted(contours, key = cv2.contourArea, reverse = True) for c in contours: rect = cv2.boundingRect(c) x,y,w,h = rect cv2.rectangle(newImage,(x,y),(x+w,y+h),(0,255,0),2) # Find largest contour and surround in min area box largestContour = contours[0] print (len(contours)) minAreaRect = cv2.minAreaRect(largestContour) # Determine the angle. Convert it to the value that was originally used to obtain skewed image angle = minAreaRect[-1] if angle < -45: angle = 90 + angle return -1.0 * angle # Rotate the image around its center def rotateImage(cvImage, angle: float): newImage = cvImage.copy() (h, w) = newImage.shape[:2] center = (w // 2, h // 2) M = cv2.getRotationMatrix2D(center, angle, 1.0) newImage = cv2.warpAffine(newImage, M, (w, h), flags=cv2.INTER_CUBIC, borderMode=cv2.BORDER_REPLICATE) return newImage def deskew(cvImage): angle = getSkewAngle(cvImage) check_angle = angle * -1.0 if check_angle > -60 and check_angle < 60: rotated_image = rotateImage(cvImage, -1.0 * angle) else: rotated_image = cvImage return rotated_image def preprocess_image(img): norm_img = np.zeros((img.shape[0], img.shape[1])) img = cv2.normalize(img, norm_img, 0, 255, cv2.NORM_MINMAX) gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1] noiseless_image_bw = cv2.fastNlMeansDenoising(thresh, None, 10, 7, 21) kernel = np.ones((2,2),np.uint8) dilate = cv2.dilate(noiseless_image_bw, kernel, iterations = 1) erosion = cv2.erode(dilate, kernel, iterations = 1) image = cv2.morphologyEx(erosion, cv2.MORPH_CLOSE, kernel) image = cv2.medianBlur(image, 3) image = cv2.bitwise_not(image) kernel = np.ones((2,2),np.uint8) image = cv2.dilate(image, kernel, iterations=1) image = cv2.erode(image, kernel, iterations = 1) image = cv2.bitwise_not(image) image = cv2.cvtColor(image, cv2.COLOR_GRAY2RGB) image = cv2.detailEnhance(img, sigma_s=80, sigma_r=0.8) image = deskew(image) return image