Upload 2 files

apps.py

@@ -0,0 +1,173 @@
+import streamlit as st
+from PIL import Image
+import pytesseract
+import io
+import fitz  # PyMuPDF
+import cv2
+import numpy as np
+import requests
+from transformers import pipeline
+from difflib import SequenceMatcher
+import folium
+from streamlit_folium import st_folium
+import wikipedia
+
+# Load summarization and NER pipeline
+summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
+ner_pipeline = pipeline("ner", aggregation_strategy="simple")
+
+# Streamlit App
+st.set_page_config(page_title="AI Historical Document Decipher", layout="wide")
+st.title("📜 AI-powered Historical Document Deciphering App")
+
+st.sidebar.header("Upload Document")
+uploaded_file = st.sidebar.file_uploader("Upload Image or PDF", type=["jpg", "jpeg", "png", "pdf"])
+
+# Function to convert PDF to image
+def pdf_to_images(pdf_bytes):
+    doc = fitz.open(stream=pdf_bytes, filetype="pdf")
+    images = []
+    for page in doc:
+        pix = page.get_pixmap()
+        img = Image.open(io.BytesIO(pix.tobytes()))
+        images.append(img)
+    return images
+
+# Function to enhance image
+def enhance_image(image):
+    img = np.array(image.convert('RGB'))
+    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
+
+    # Denoise
+    denoised = cv2.fastNlMeansDenoising(gray, h=30)
+
+    # Sharpening
+    kernel = np.array([[0, -1, 0],
+                       [-1, 5,-1],
+                       [0, -1, 0]])
+    sharpened = cv2.filter2D(denoised, -1, kernel)
+
+    # Thresholding (binarization)
+    _, binary = cv2.threshold(sharpened, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
+
+    # Optional: Resize (sometimes helps OCR)
+    scale_percent = 150  # percent of original size
+    width = int(binary.shape[1] * scale_percent / 100)
+    height = int(binary.shape[0] * scale_percent / 100)
+    resized = cv2.resize(binary, (width, height), interpolation=cv2.INTER_CUBIC)
+
+    return resized
+
+# Function to perform OCR
+def perform_ocr(image):
+    custom_oem_psm_config = r'--oem 3 --psm 6 -c preserve_interword_spaces=1'
+    text = pytesseract.image_to_string(image, config=custom_oem_psm_config)
+    return text
+
+# Function to extract named entities
+def extract_entities(text):
+    entities = ner_pipeline(text)
+    extracted = {}
+    for ent in entities:
+        label = ent['entity_group']
+        extracted.setdefault(label, set()).add(ent['word'])
+    return extracted
+
+def get_historical_context(entities):
+    context = {}
+    for label, values in entities.items():
+        for item in values:
+            try:
+                summary = wikipedia.summary(item, sentences=2)
+                context[item] = summary
+            except wikipedia.exceptions.DisambiguationError as e:
+                context[item] = f"Multiple entries found for '{item}': {e.options[:3]}"
+            except wikipedia.exceptions.PageError:
+                context[item] = f"No historical info found for '{item}'."
+            except Exception as e:
+                context[item] = f"Error retrieving info: {e}"
+    return context
+
+# Function to correct OCR errors (suggestions)
+def suggest_corrections(original_text):
+    words = original_text.split()
+    suggestions = {}
+    for word in words:
+        if len(word) > 4 and not word.isnumeric():
+            close_matches = [w for w in ["document", "historical", "archive", "event", "location"] if SequenceMatcher(None, word.lower(), w).ratio() > 0.75]
+            if close_matches:
+                suggestions[word] = close_matches[0]
+    return suggestions
+
+# Function to generate map
+def generate_map(entities):
+    m = folium.Map(location=[20, 0], zoom_start=2)
+    if "LOC" in entities:
+        for location in entities["LOC"]:
+            # Dummy coordinates for demonstration
+            folium.Marker(
+                location=[51.5074, -0.1278],  # Example: London
+                popup=f"Location: {location}",
+                tooltip=location
+            ).add_to(m)
+    return m
+
+if uploaded_file:
+    file_type = uploaded_file.type
+
+    # Display and process the uploaded document
+    if file_type == "application/pdf":
+        images = pdf_to_images(uploaded_file.read())
+    else:
+        images = [Image.open(uploaded_file)]
+
+    for image in images:
+        st.image(image, caption="Uploaded Document", use_container_width=True)
+
+        # Enhance image
+        enhanced = enhance_image(image)
+        st.image(enhanced, caption="Enhanced Image", use_container_width=True, channels="GRAY")
+
+        # Perform OCR
+        ocr_text = perform_ocr(enhanced)
+        st.subheader("Extracted Text (OCR)")
+        st.text_area("Text", ocr_text, height=200)
+
+        # Suggest corrections
+        corrections = suggest_corrections(ocr_text)
+        if corrections:
+            st.subheader("AI Suggestions for Possible Corrections")
+            for original, suggestion in corrections.items():
+                st.markdown(f"**{original}** ➔ *{suggestion}*")
+
+        # Summarize text
+        if len(ocr_text.strip()) > 50:
+            summary = summarizer(ocr_text, max_length=60, min_length=20, do_sample=False)[0]['summary_text']
+            st.subheader("Summary")
+            st.write(summary)
+
+        # Extract entities
+        entities = extract_entities(ocr_text)
+        st.subheader("Key Information")
+        for label, items in entities.items():
+            st.markdown(f"**{label}**: {', '.join(items)}")
+
+        # Provide historical context
+        context = get_historical_context(entities)
+        if context:
+            st.subheader("Historical Context & Insights")
+            for item, info in context.items():
+                st.markdown(f"- **{item}**: {info}")
+
+        # Visualize map
+        st.subheader("Locations Mentioned")
+        map_ = generate_map(entities)
+        st_folium(map_, width=700)
+
+        st.markdown("---")
+
+else:
+    st.info("Upload an image or PDF of a historical document to begin.")
+
+st.sidebar.markdown("---")
+st.sidebar.markdown("Developed by **Cherilyn Marie Deocampo**")

requirements.txt

@@ -0,0 +1,10 @@
+streamlit==1.41.1
+Pillow==10.2.0
+easyocr==1.7.1
+PyMuPDF==1.25.5
+opencv-python==4.11.0.86
+numpy==1.26.4
+transformers==4.49.0
+folium==0.19.5
+streamlit-folium==0.24.0
+wikipedia==1.4.0