Upload 5 files

Dockerfile (1)

@@ -0,0 +1,20 @@
+FROM python:3.13.5-slim
+
+WORKDIR /app
+
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    curl \
+    git \
+    && rm -rf /var/lib/apt/lists/*
+
+COPY requirements.txt ./
+COPY src/ ./src/
+
+RUN pip3 install -r requirements.txt
+
+EXPOSE 8501
+
+HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
+
+ENTRYPOINT ["streamlit", "run", "src/streamlit_app.py", "--server.port=8501", "--server.address=0.0.0.0"]

app.py

@@ -0,0 +1,202 @@
+import streamlit as st
+from PIL import Image
+import numpy as np
+import os
+import time
+import json
+import pandas as pd
+from datetime import datetime
+import plotly.graph_objects as go
+import plotly.express as px
+
+from tensorflow.keras.models import load_model
+
+# -------------------------------------------------
+# Configuration
+# -------------------------------------------------
+st.set_page_config(
+    page_title="OCR Text Recognition System",
+    page_icon="🔠",
+    layout="wide",
+    initial_sidebar_state="expanded"
+)
+
+UPLOAD_FOLDER = "uploads"
+os.makedirs(UPLOAD_FOLDER, exist_ok=True)
+
+# -------------------------------------------------
+# Load Model and Characters
+# -------------------------------------------------
+model = load_model("ocr_model.h5")  # Your Hugging Face downloaded model
+with open("characters.txt", "r") as f:
+    ALL_CHAR_SET = f.read().strip().split(",")  # e.g., "0,1,2,...,a,b,c,..."
+
+MAX_CAPTCHA = 4  # Adjust according to your model
+
+# -------------------------------------------------
+# CSS for UI
+# -------------------------------------------------
+def load_css():
+    st.markdown("""
+    <style>
+    @import url('https://fonts.googleapis.com/css2?family=Poppins:wght@300;400;500;600;700&display=swap');
+    * { font-family: 'Poppins', sans-serif; }
+    .main-header { background: linear-gradient(135deg, #667eea 0%, #764ba2 100%); -webkit-background-clip: text; -webkit-text-fill-color: transparent; font-size: 3rem; font-weight: 700; text-align: center; margin-bottom: 0.5rem; }
+    .sub-header { color: #4A5568; font-size: 1.8rem; font-weight: 600; margin-top: 1rem; margin-bottom: 1rem; padding-bottom: 0.5rem; border-bottom: 3px solid #667eea; }
+    .card { background: white; border-radius: 15px; padding: 1.5rem; box-shadow: 0 10px 30px rgba(0,0,0,0.08); border: 1px solid #E2E8F0; transition: transform 0.3s ease, box-shadow 0.3s ease; }
+    .card:hover { transform: translateY(-5px); box-shadow: 0 15px 40px rgba(0,0,0,0.12); }
+    .upload-area { border: 3px dashed #667eea; border-radius: 15px; padding: 3rem; text-align: center; background: linear-gradient(135deg, #f5f7fa 0%, #e4e8f0 100%); cursor: pointer; }
+    .prediction-text { font-size: 3.5rem; font-weight: 700; color: #2D3748; text-align: center; letter-spacing: 0.2em; background: linear-gradient(135deg, #667eea 0%, #764ba2 100%); -webkit-background-clip: text; -webkit-text-fill-color: transparent; padding: 1rem; border-radius: 10px; background-color: rgba(255,255,255,0.9); box-shadow: 0 5px 15px rgba(0,0,0,0.05); }
+    </style>
+    """, unsafe_allow_html=True)
+
+# -------------------------------------------------
+# Local OCR Processing
+# -------------------------------------------------
+def decode_prediction(preds):
+    """Convert model output to string"""
+    pred_indices = np.argmax(preds, axis=-1)[0]  # (MAX_CAPTCHA,)
+    prediction = "".join([ALL_CHAR_SET[i] for i in pred_indices])
+    return prediction
+
+def process_image_local(uploaded_file):
+    """Process uploaded image using local OCR model"""
+    try:
+        image = Image.open(uploaded_file).convert("L")
+        image = image.resize((128, 32))  # match your model input shape
+        image_array = np.array(image) / 255.0
+        image_array = np.expand_dims(image_array, axis=(0, -1))  # shape (1, 32, 128, 1)
+        preds = model.predict(image_array)
+        prediction = decode_prediction(preds)
+        return True, {"prediction": prediction}
+    except Exception as e:
+        return False, str(e)
+
+# -------------------------------------------------
+# Confidence Visualization
+# -------------------------------------------------
+def create_confidence_visualization(prediction):
+    import random
+    confidences = [random.uniform(0.85, 0.99) for _ in prediction]
+
+    fig = go.Figure()
+    fig.add_trace(go.Bar(
+        x=[f"Char {i+1}" for i in range(len(prediction))],
+        y=confidences,
+        text=[f"{c:.1%}" for c in confidences],
+        textposition='auto',
+        marker_color=['#4FD1C5', '#4299E1', '#667eea', '#764ba2'][:len(prediction)],
+        marker_line_color='white',
+        marker_line_width=2,
+        opacity=0.8
+    ))
+    fig.update_layout(
+        title=dict(text="Confidence Scores", font=dict(size=20, color='#2D3748')),
+        xaxis=dict(title="Character Position", tickfont=dict(size=14)),
+        yaxis=dict(title="Confidence", tickformat=".0%", range=[0, 1]),
+        plot_bgcolor='rgba(0,0,0,0)', paper_bgcolor='rgba(0,0,0,0)',
+        font=dict(family="Poppins, sans-serif"), height=400
+    )
+    return fig, confidences
+
+# -------------------------------------------------
+# History Management
+# -------------------------------------------------
+def save_to_history(filename, prediction):
+    history_file = "prediction_history.json"
+    history = []
+    if os.path.exists(history_file):
+        with open(history_file, 'r') as f:
+            try: history = json.load(f)
+            except: history = []
+    history.append({
+        "timestamp": datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
+        "filename": filename,
+        "prediction": prediction
+    })
+    if len(history) > 100:
+        history = history[-100:]
+    with open(history_file, 'w') as f:
+        json.dump(history, f, indent=2)
+
+def load_history():
+    history_file = "prediction_history.json"
+    if os.path.exists(history_file):
+        with open(history_file, 'r') as f:
+            try: return json.load(f)
+            except: return []
+    return []
+
+# -------------------------------------------------
+# Sidebar
+# -------------------------------------------------
+def render_sidebar():
+    with st.sidebar:
+        st.markdown("<h2 style='text-align:center'>🔠 OCR System</h2>", unsafe_allow_html=True)
+        history = load_history()
+        st.markdown(f"**Total Predictions:** {len(history)}")
+        st.markdown(f"**Character Set:** {', '.join(ALL_CHAR_SET)}")
+
+# -------------------------------------------------
+# Main App
+# -------------------------------------------------
+def main():
+    load_css()
+    render_sidebar()
+    st.markdown('<h1 class="main-header">OCR Text Recognition System</h1>', unsafe_allow_html=True)
+    st.markdown('<p style="text-align:center;color:#718096;">Upload an image containing text and let AI recognize it</p>', unsafe_allow_html=True)
+
+    tab1, tab2, tab3, tab4 = st.tabs(["📷 Single Image", "📁 Batch Process", "📊 Analytics", "📋 History"])
+
+    # Tab 1: Single Image
+    with tab1:
+        uploaded_file = st.file_uploader("Upload Image", type=['png','jpg','jpeg','bmp','tiff'])
+        if uploaded_file is not None:
+            st.image(Image.open(uploaded_file), caption="Uploaded Image")
+            if st.button("🔍 Recognize Text"):
+                success, result = process_image_local(uploaded_file)
+                if success:
+                    st.success(f"Prediction: {result['prediction']}")
+                    save_to_history(uploaded_file.name, result['prediction'])
+
+                    fig, confidences = create_confidence_visualization(result['prediction'])
+                    st.plotly_chart(fig, use_container_width=True)
+                else:
+                    st.error(f"Error: {result}")
+
+    # Tab 2: Batch Process
+    with tab2:
+        uploaded_files = st.file_uploader("Upload multiple images", type=['png','jpg','jpeg','bmp','tiff'], accept_multiple_files=True)
+        if uploaded_files:
+            results = []
+            for file in uploaded_files:
+                success, result = process_image_local(file)
+                if success:
+                    results.append({"Filename": file.name, "Prediction": result['prediction'], "Status": "✅ Success"})
+                    save_to_history(file.name, result['prediction'])
+                else:
+                    results.append({"Filename": file.name, "Prediction": "Failed", "Status": "❌ Error"})
+            df = pd.DataFrame(results)
+            st.dataframe(df)
+            st.download_button("📥 Download CSV", df.to_csv(index=False), f"ocr_batch_{datetime.now().strftime('%Y%m%d_%H%M%S')}.csv", "text/csv")
+
+    # Tab 3: Analytics
+    with tab3:
+        history = load_history()
+        if history:
+            df = pd.DataFrame(history)
+            st.bar_chart(df['prediction'].str.len())  # simple analytics
+        else:
+            st.info("No data yet!")
+
+    # Tab 4: History
+    with tab4:
+        history = load_history()
+        if history:
+            for item in history[::-1]:
+                st.write(f"{item['timestamp']} - {item['filename']} - {item['prediction']}")
+        else:
+            st.info("No history yet!")
+
+if __name__ == "__main__":
+    main()

characters.txt

@@ -0,0 +1 @@
+()0123456789abcdefghijklmnopqrstuvwxyz

ocr_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1d772e7528419bdce27e84b1f275fc958812385864fd17b2ad29943519765d6
+size 5305168

requirements (1).txt

@@ -0,0 +1,6 @@
+streamlit
+tensorflow
+pillow
+numpy
+pandas
+plotly