package

app.py

@@ -2,7 +2,8 @@ import io
 import urllib
 import pandas as pd
 import numpy as np
-import fitz
+# import fitz
+from pdf2image import convert_from_path
 import cv2
 import pytesseract
 import requests
@@ -165,19 +166,24 @@ shops = {
     # Add more shops and their respective information here
 }
 
+# def pdf_to_images(pdf_path):
+#     doc = fitz.open(pdf_path)
+#     images = []
+#     for page in doc:
+#         for img in page.get_images(full=True):
+#             xref = img[0]
+#             base_image = doc.extract_image(xref)
+#             image_bytes = base_image["image"]
+#             # You can use PIL to do many things with this image data.
+#             # If you need it as an array for OpenCV, you can do that as follows:
+#             image = Image.open(io.BytesIO(image_bytes))
+#             images.append(np.array(image))
+#     return images
+
 def pdf_to_images(pdf_path):
-    doc = fitz.open(pdf_path)
-    images = []
-    for page in doc:
-        for img in page.get_images(full=True):
-            xref = img[0]
-            base_image = doc.extract_image(xref)
-            image_bytes = base_image["image"]
-            # You can use PIL to do many things with this image data.
-            # If you need it as an array for OpenCV, you can do that as follows:
-            image = Image.open(io.BytesIO(image_bytes))
-            images.append(np.array(image))
-    return images
+    images = convert_from_path(pdf_path)
+    return [cv2.cvtColor(np.array(img), cv2.COLOR_RGB2BGR) for img in images]
+
 
 
 def get_yolo_predictions(image):

packages.txt

@@ -1 +1,2 @@
-tesseract-ocr-all
+tesseract-ocr-all
+poppler