File size: 1,286 Bytes
79fc11d
 
 
 
 
 
 
 
4a27fa8
79fc11d
4a27fa8
 
 
79fc11d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4a27fa8
 
 
 
 
 
 
79fc11d
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
import layoutparser as lp
import pytesseract
from pdf2image import convert_from_path
from PIL import Image

def convert_pdf_to_images(pdf_path):
    return convert_from_path(pdf_path)

# ✅ Use EfficientDet instead of Detectron2 for better compatibility
def analyze_layout(image):
    model = lp.EfficientDetLayoutModel(
        "lp://efficientdet/PubLayNet",
        extra_config=["MODEL.ROI_HEADS.SCORE_THRESH_TEST", 0.6],
        label_map={0: "Text", 1: "Title", 2: "List", 3: "Table", 4: "Figure"}
    )
    layout = model.detect(image)
    return layout

def extract_text_from_blocks(image, layout):
    blocks = []
    for block in layout:
        segment_image = block.crop_image(image)
        text = pytesseract.image_to_string(segment_image)
        blocks.append({
            "type": block.type,
            "text": text.strip(),
            "coordinates": block.coordinates
        })
    return blocks

def extract_key_values(blocks):
    data = {}
    for block in blocks:
        text = block["text"].lower()
        if "invoice" in text:
            data["Invoice Number"] = block["text"]
        elif "total" in text:
            data["Total Amount"] = block["text"]
        elif "customer" in text:
            data["Customer Name"] = block["text"]
    return data