FactureOCR / app.py
Soufiane
added table extraction
8a6a4ae
import streamlit as st
from PIL import Image
import pandas as pd
import numpy as np
from invoice import extract_data, extract_tables, INVOICE
def process_image(lang, to_be_extracted, input_image):
data = extract_data(lang, to_be_extracted, input_image)
return data
def main():
st.title("Image Processing App")
st.write("Upload an image and click the 'Process Image' button to process it.")
uploaded_image = st.file_uploader("Upload an image", type=["jpg", "jpeg", "png","webp"])
if uploaded_image is not None:
# Display the uploaded image
st.image(uploaded_image, caption="Uploaded Image", use_column_width=True)
lang = st.selectbox("Select Language", ["french", "english", "arabic"])
pil_image = Image.open(uploaded_image).convert('RGB')
numpy_image = np.array(pil_image)
st.write("Add elements to extract:")
extract_input = st.text_input("Add elements")
extract_list = st.session_state.get("extract_list", INVOICE)
if extract_input:
extract_list.append(extract_input.strip())
st.session_state["extract_list"] = extract_list
# Display the extract list as chips
st.write("Elements to extract:")
for item in extract_list:
st.write(f"`{item}`", unsafe_allow_html=True)
if st.button("Extract information"):
image_info = process_image(lang, extract_list, numpy_image)
df = pd.DataFrame(list(image_info.items()), columns=["Field", "Value"])
st.write("Extracted information:")
st.dataframe(df)
if st.button("Extract Tables"):
csv = extract_tables(lang, numpy_image)
st.download_button(label="Download CSV", data=csv, file_name='data.csv', mime='text/csv')
else:
st.session_state['extract_list'] = INVOICE
if __name__ == "__main__":
main()