Spaces:

jeyanthangj2004
/

ocr

Runtime error

App Files Files Community

jeyanthangj2004 commited on Dec 18, 2025

Commit

78c7412

verified ·

1 Parent(s): e50ff33

Update app.py

Browse files

Files changed (1) hide show

app.py +377 -381

app.py CHANGED Viewed

@@ -1,381 +1,377 @@
-"""
-eDOCr2 - Engineering Drawing OCR
-Gradio Interface for Hugging Face Spaces
-Extract dimensions, tables, and GD&T symbols from engineering drawings
-"""
-import gradio as gr
-import cv2
-import numpy as np
-import json
-import os
-import time
-from pathlib import Path
-import zipfile
-import tempfile
-from PIL import Image
-# Import eDOCr2 modules
-from edocr2 import tools
-from edocr2.keras_ocr.recognition import Recognizer
-from edocr2.keras_ocr.detection import Detector
-from pdf2image import convert_from_path
-# Global variables for models
-recognizer_gdt = None
-recognizer_dim = None
-detector = None
-alphabet_dim = None
-models_loaded = False
-def load_models():
-    """Load OCR models at startup"""
-    global recognizer_gdt, recognizer_dim, detector, alphabet_dim, models_loaded
-    if models_loaded:
-        return True
-    try:
-        print("🔧 Loading OCR models...")
-        start_time = time.time()
-        # Model paths
-        gdt_model = 'edocr2/models/recognizer_gdts.keras'
-        dim_model = 'edocr2/models/recognizer_dimensions_2.keras'
-        if not os.path.exists(gdt_model) or not os.path.exists(dim_model):
-            print("❌ Model files not found!")
-            return False
-        # Load GD&T recognizer
-        recognizer_gdt = Recognizer(alphabet=tools.ocr_pipelines.read_alphabet(gdt_model))
-        recognizer_gdt.model.load_weights(gdt_model)
-        # Load dimension recognizer
-        alphabet_dim = tools.ocr_pipelines.read_alphabet(dim_model)
-        recognizer_dim = Recognizer(alphabet=alphabet_dim)
-        recognizer_dim.model.load_weights(dim_model)
-        # Load detector
-        detector = Detector()
-        # Warm up models
-        dummy_image = np.zeros((1, 1, 3), dtype=np.float32)
-        _ = recognizer_gdt.recognize(dummy_image)
-        _ = recognizer_dim.recognize(dummy_image)
-        dummy_image = np.zeros((32, 32, 3), dtype=np.float32)
-        _ = detector.detect([dummy_image])
-        end_time = time.time()
-        print(f"✅ Models loaded in {end_time - start_time:.2f} seconds")
-        models_loaded = True
-        return True
-    except Exception as e:
-        print(f"❌ Error loading models: {e}")
-        import traceback
-        traceback.print_exc()
-        return False
-def process_drawing(image_file):
-    """
-    Process an engineering drawing and extract information
-    Args:
-        image_file: Uploaded image file (PIL Image or file path)
-    Returns:
-        tuple: (annotated_image, json_data, csv_file, zip_file, stats_html)
-    """
-    if not models_loaded:
-        return None, "❌ Models not loaded. Please check the logs.", None, None, "Error: Models not loaded"
-    try:
-        start_time = time.time()
-        # Read image
-        if isinstance(image_file, str):
-            # File path
-            if image_file.lower().endswith('.pdf'):
-                img = convert_from_path(image_file)
-                img = np.array(img[0])
-                gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
-                _, img = cv2.threshold(gray, 200, 255, cv2.THRESH_BINARY)
-                img = cv2.merge([img, img, img])
-            else:
-                img = cv2.imread(image_file)
-        else:
-            # PIL Image
-            img = np.array(image_file)
-            if len(img.shape) == 2:  # Grayscale
-                img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
-            elif img.shape[2] == 4:  # RGBA
-                img = cv2.cvtColor(img, cv2.COLOR_RGBA2BGR)
-            else:  # RGB
-                img = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)
-        if img is None:
-            return None, "❌ Could not read image file", None, None, "Error: Invalid image"
-        # Create temporary output directory
-        with tempfile.TemporaryDirectory() as temp_dir:
-            output_dir = temp_dir
-            # Segmentation
-            print("🔍 Segmenting layers...")
-            img_boxes, frame, gdt_boxes, tables, dim_boxes = tools.layer_segm.segment_img(
-                img, autoframe=True, frame_thres=0.7, GDT_thres=0.02, binary_thres=127
-            )
-            # OCR Tables
-            print("📋 Processing tables...")
-            process_img = img.copy()
-            table_results, updated_tables, process_img = tools.ocr_pipelines.ocr_tables(
-                tables, process_img, language='eng'
-            )
-            # OCR GD&T
-            print("🎯 Processing GD&T symbols...")
-            gdt_results, updated_gdt_boxes, process_img = tools.ocr_pipelines.ocr_gdt(
-                process_img, gdt_boxes, recognizer_gdt
-            )
-            # OCR Dimensions
-            print("📏 Processing dimensions...")
-            if frame:
-                process_img = process_img[frame.y : frame.y + frame.h, frame.x : frame.x + frame.w]
-            dimensions, other_info, process_img, dim_tess = tools.ocr_pipelines.ocr_dimensions(
-                process_img, detector, recognizer_dim, alphabet_dim, frame, dim_boxes,
-                cluster_thres=20, max_img_size=1048, language='eng', backg_save=False
-            )
-            # Generate mask image
-            print("🎨 Generating visualization...")
-            mask_img = tools.output_tools.mask_img(
-                img, updated_gdt_boxes, updated_tables, dimensions, frame, other_info
-            )
-            # Convert to RGB for display
-            mask_img_rgb = cv2.cvtColor(mask_img, cv2.COLOR_BGR2RGB)
-            # Process and save results
-            print("💾 Saving results...")
-            table_results, gdt_results, dimensions, other_info = tools.output_tools.process_raw_output(
-                output_dir, table_results, gdt_results, dimensions, other_info, save=True
-            )
-            # Prepare JSON data
-            json_data = {
-                'tables': table_results,
-                'gdts': gdt_results,
-                'dimensions': dimensions,
-                'other_info': other_info
-            }
-            json_str = json.dumps(json_data, indent=2)
-            # Save JSON file
-            json_path = os.path.join(output_dir, 'results.json')
-            with open(json_path, 'w') as f:
-                f.write(json_str)
-            # Create CSV file (if exists)
-            csv_files = list(Path(output_dir).glob('*.csv'))
-            csv_path = csv_files[0] if csv_files else None
-            # Create ZIP file with all results
-            zip_path = os.path.join(output_dir, 'edocr2_results.zip')
-            with zipfile.ZipFile(zip_path, 'w', zipfile.ZIP_DEFLATED) as zipf:
-                # Add mask image
-                mask_img_path = os.path.join(output_dir, 'annotated_drawing.png')
-                cv2.imwrite(mask_img_path, mask_img)
-                zipf.write(mask_img_path, 'annotated_drawing.png')
-                # Add JSON
-                zipf.write(json_path, 'results.json')
-                # Add CSV if exists
-                if csv_path:
-                    zipf.write(csv_path, os.path.basename(csv_path))
-            # Copy ZIP to a permanent location
-            permanent_zip = os.path.join(tempfile.gettempdir(), f'edocr2_results_{int(time.time())}.zip')
-            import shutil
-            shutil.copy(zip_path, permanent_zip)
-            end_time = time.time()
-            processing_time = round(end_time - start_time, 2)
-            # Create statistics HTML
-            stats_html = f"""
-            <div style="background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
-                        padding: 20px; border-radius: 10px; color: white; margin: 10px 0;">
-                <h3 style="margin-top: 0;">📊 Processing Results</h3>
-                <div style="display: grid; grid-template-columns: repeat(auto-fit, minmax(150px, 1fr)); gap: 15px; margin-top: 15px;">
-                    <div style="background: rgba(255,255,255,0.2); padding: 15px; border-radius: 8px; text-align: center;">
-                        <div style="font-size: 2em; font-weight: bold;">{len(table_results)}</div>
-                        <div style="font-size: 0.9em; opacity: 0.9;">Tables Found</div>
-                    </div>
-                    <div style="background: rgba(255,255,255,0.2); padding: 15px; border-radius: 8px; text-align: center;">
-                        <div style="font-size: 2em; font-weight: bold;">{len(gdt_results)}</div>
-                        <div style="font-size: 0.9em; opacity: 0.9;">GD&T Symbols</div>
-                    </div>
-                    <div style="background: rgba(255,255,255,0.2); padding: 15px; border-radius: 8px; text-align: center;">
-                        <div style="font-size: 2em; font-weight: bold;">{len(dimensions)}</div>
-                        <div style="font-size: 0.9em; opacity: 0.9;">Dimensions</div>
-                    </div>
-                    <div style="background: rgba(255,255,255,0.2); padding: 15px; border-radius: 8px; text-align: center;">
-                        <div style="font-size: 2em; font-weight: bold;">{processing_time}s</div>
-                        <div style="font-size: 0.9em; opacity: 0.9;">Processing Time</div>
-                    </div>
-                </div>
-            </div>
-            """
-            print(f"✅ Processing complete in {processing_time}s")
-            return (
-                Image.fromarray(mask_img_rgb),
-                json_str,
-                csv_path if csv_path else None,
-                permanent_zip,
-                stats_html
-            )
-    except Exception as e:
-        error_msg = f"❌ Error processing drawing: {str(e)}"
-        print(error_msg)
-        import traceback
-        traceback.print_exc()
-        return None, error_msg, None, None, f"<div style='color: red;'>{error_msg}</div>"
-# Load models at startup
-print("="*60)
-print("🔧 eDOCr2 - Engineering Drawing OCR")
-print("="*60)
-load_models()
-# Create Gradio interface
-with gr.Blocks(theme=gr.themes.Soft(), title="eDOCr2 - Engineering Drawing OCR") as demo:
-    gr.Markdown("""
-    # 🔧 eDOCr2 - Engineering Drawing OCR
-    Extract **dimensions**, **tables**, and **GD&T symbols** from engineering drawings automatically.
-    Upload your engineering drawing (JPG, PNG, or PDF) and get structured data extracted instantly!
-    """)
-    with gr.Row():
-        with gr.Column(scale=1):
-            gr.Markdown("### 📤 Upload Drawing")
-            image_input = gr.Image(
-                type="pil",
-                label="Engineering Drawing",
-                sources=["upload", "clipboard"],
-                height=400
-            )
-            process_btn = gr.Button(
-                "🚀 Process Drawing",
-                variant="primary",
-                size="lg"
-            )
-            gr.Markdown("""
-            **Supported formats:** JPG, PNG, PDF
-            **Best results:** High-resolution scans with clear text
-            """)
-        with gr.Column(scale=1):
-            gr.Markdown("### 📊 Statistics")
-            stats_output = gr.HTML()
-            gr.Markdown("### 🎨 Annotated Drawing")
-            image_output = gr.Image(
-                label="Processed Drawing",
-                type="pil",
-                height=400
-            )
-    with gr.Row():
-        with gr.Column():
-            gr.Markdown("### 📋 Extracted Data (JSON)")
-            json_output = gr.Textbox(
-                label="Structured Data",
-                lines=15,
-                max_lines=20,
-                show_copy_button=True
-            )
-        with gr.Column():
-            gr.Markdown("### 💾 Download Results")
-            csv_output = gr.File(
-                label="📊 CSV File (if available)",
-                type="filepath"
-            )
-            zip_output = gr.File(
-                label="📦 Complete Results (ZIP)",
-                type="filepath"
-            )
-            gr.Markdown("""
-            **ZIP contains:**
-            - Annotated drawing image
-            - Structured data (JSON)
-            - Tabular data (CSV, if applicable)
-            """)
-    # Examples section
-    gr.Markdown("### 🧪 Try Example Drawings")
-    example_files = []
-    examples_dir = "tests/test_samples"
-    if os.path.exists(examples_dir):
-        for file in os.listdir(examples_dir):
-            if file.endswith(('.jpg', '.png')):
-                example_files.append([os.path.join(examples_dir, file)])
-    if example_files:
-        gr.Examples(
-            examples=example_files[:3],  # Show first 3 examples
-            inputs=image_input,
-            label="Click to load example"
-        )
-    # Footer
-    gr.Markdown("""
-    ---
-    ### 📚 About eDOCr2
-    eDOCr2 is a specialized OCR tool for engineering drawings that can extract:
-    - **Tables**: Title blocks, revision tables, bill of materials
-    - **GD&T Symbols**: Geometric dimensioning and tolerancing
-    - **Dimensions**: Measurements with tolerances
-    - **Other Information**: Additional text and annotations
-    **Research Paper:** [http://dx.doi.org/10.2139/ssrn.5045921](http://dx.doi.org/10.2139/ssrn.5045921)
-    **GitHub:** [github.com/javvi51/edocr2](https://github.com/javvi51/edocr2)
-    **Created by:** Javier Villena Toro | **Deployed by:** Jeyanthan GJ
-    """)
-    # Connect the process button
-    process_btn.click(
-        fn=process_drawing,
-        inputs=image_input,
-        outputs=[image_output, json_output, csv_output, zip_output, stats_output]
-    )
-# Launch the app
-if __name__ == "__main__":
-    demo.launch(
-        server_name="0.0.0.0",
-        server_port=7860,
-        share=False
-    )

+"""
+eDOCr2 - Engineering Drawing OCR
+Gradio Interface for Hugging Face Spaces
+Extract dimensions, tables, and GD&T symbols from engineering drawings
+"""
+import gradio as gr
+import cv2
+import numpy as np
+import json
+import os
+import time
+from pathlib import Path
+import zipfile
+import tempfile
+from PIL import Image
+# Import eDOCr2 modules
+from edocr2 import tools
+from edocr2.keras_ocr.recognition import Recognizer
+from edocr2.keras_ocr.detection import Detector
+from pdf2image import convert_from_path
+# Global variables for models
+recognizer_gdt = None
+recognizer_dim = None
+detector = None
+alphabet_dim = None
+models_loaded = False
+def load_models():
+    """Load OCR models at startup"""
+    global recognizer_gdt, recognizer_dim, detector, alphabet_dim, models_loaded
+    if models_loaded:
+        return True
+    try:
+        print("🔧 Loading OCR models...")
+        start_time = time.time()
+        # Model paths
+        gdt_model = 'edocr2/models/recognizer_gdts.keras'
+        dim_model = 'edocr2/models/recognizer_dimensions_2.keras'
+        if not os.path.exists(gdt_model) or not os.path.exists(dim_model):
+            print("❌ Model files not found!")
+            return False
+        # Load GD&T recognizer
+        recognizer_gdt = Recognizer(alphabet=tools.ocr_pipelines.read_alphabet(gdt_model))
+        recognizer_gdt.model.load_weights(gdt_model)
+        # Load dimension recognizer
+        alphabet_dim = tools.ocr_pipelines.read_alphabet(dim_model)
+        recognizer_dim = Recognizer(alphabet=alphabet_dim)
+        recognizer_dim.model.load_weights(dim_model)
+        # Load detector
+        detector = Detector()
+        # Warm up models
+        dummy_image = np.zeros((1, 1, 3), dtype=np.float32)
+        _ = recognizer_gdt.recognize(dummy_image)
+        _ = recognizer_dim.recognize(dummy_image)
+        dummy_image = np.zeros((32, 32, 3), dtype=np.float32)
+        _ = detector.detect([dummy_image])
+        end_time = time.time()
+        print(f"✅ Models loaded in {end_time - start_time:.2f} seconds")
+        models_loaded = True
+        return True
+    except Exception as e:
+        print(f"❌ Error loading models: {e}")
+        import traceback
+        traceback.print_exc()
+        return False
+def process_drawing(image_file):
+    """
+    Process an engineering drawing and extract information
+    Args:
+        image_file: Uploaded image file (PIL Image or file path)
+    Returns:
+        tuple: (annotated_image, json_data, csv_file, zip_file, stats_html)
+    """
+    if not models_loaded:
+        return None, "❌ Models not loaded. Please check the logs.", None, None, "Error: Models not loaded"
+    try:
+        start_time = time.time()
+        # Read image
+        if isinstance(image_file, str):
+            # File path
+            if image_file.lower().endswith('.pdf'):
+                img = convert_from_path(image_file)
+                img = np.array(img[0])
+                gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
+                _, img = cv2.threshold(gray, 200, 255, cv2.THRESH_BINARY)
+                img = cv2.merge([img, img, img])
+            else:
+                img = cv2.imread(image_file)
+        else:
+            # PIL Image
+            img = np.array(image_file)
+            if len(img.shape) == 2:  # Grayscale
+                img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
+            elif img.shape[2] == 4:  # RGBA
+                img = cv2.cvtColor(img, cv2.COLOR_RGBA2BGR)
+            else:  # RGB
+                img = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)
+        if img is None:
+            return None, "❌ Could not read image file", None, None, "Error: Invalid image"
+        # Create temporary output directory
+        with tempfile.TemporaryDirectory() as temp_dir:
+            output_dir = temp_dir
+            # Segmentation
+            print("🔍 Segmenting layers...")
+            img_boxes, frame, gdt_boxes, tables, dim_boxes = tools.layer_segm.segment_img(
+                img, autoframe=True, frame_thres=0.7, GDT_thres=0.02, binary_thres=127
+            )
+            # OCR Tables
+            print("📋 Processing tables...")
+            process_img = img.copy()
+            table_results, updated_tables, process_img = tools.ocr_pipelines.ocr_tables(
+                tables, process_img, language='eng'
+            )
+            # OCR GD&T
+            print("🎯 Processing GD&T symbols...")
+            gdt_results, updated_gdt_boxes, process_img = tools.ocr_pipelines.ocr_gdt(
+                process_img, gdt_boxes, recognizer_gdt
+            )
+            # OCR Dimensions
+            print("📏 Processing dimensions...")
+            if frame:
+                process_img = process_img[frame.y : frame.y + frame.h, frame.x : frame.x + frame.w]
+            dimensions, other_info, process_img, dim_tess = tools.ocr_pipelines.ocr_dimensions(
+                process_img, detector, recognizer_dim, alphabet_dim, frame, dim_boxes,
+                cluster_thres=20, max_img_size=1048, language='eng', backg_save=False
+            )
+            # Generate mask image
+            print("🎨 Generating visualization...")
+            mask_img = tools.output_tools.mask_img(
+                img, updated_gdt_boxes, updated_tables, dimensions, frame, other_info
+            )
+            # Convert to RGB for display
+            mask_img_rgb = cv2.cvtColor(mask_img, cv2.COLOR_BGR2RGB)
+            # Process and save results
+            print("💾 Saving results...")
+            table_results, gdt_results, dimensions, other_info = tools.output_tools.process_raw_output(
+                output_dir, table_results, gdt_results, dimensions, other_info, save=True
+            )
+            # Prepare JSON data
+            json_data = {
+                'tables': table_results,
+                'gdts': gdt_results,
+                'dimensions': dimensions,
+                'other_info': other_info
+            }
+            json_str = json.dumps(json_data, indent=2)
+            # Save JSON file
+            json_path = os.path.join(output_dir, 'results.json')
+            with open(json_path, 'w') as f:
+                f.write(json_str)
+            # Create CSV file (if exists)
+            csv_files = list(Path(output_dir).glob('*.csv'))
+            csv_path = csv_files[0] if csv_files else None
+            # Create ZIP file with all results
+            zip_path = os.path.join(output_dir, 'edocr2_results.zip')
+            with zipfile.ZipFile(zip_path, 'w', zipfile.ZIP_DEFLATED) as zipf:
+                # Add mask image
+                mask_img_path = os.path.join(output_dir, 'annotated_drawing.png')
+                cv2.imwrite(mask_img_path, mask_img)
+                zipf.write(mask_img_path, 'annotated_drawing.png')
+                # Add JSON
+                zipf.write(json_path, 'results.json')
+                # Add CSV if exists
+                if csv_path:
+                    zipf.write(csv_path, os.path.basename(csv_path))
+            # Copy ZIP to a permanent location
+            permanent_zip = os.path.join(tempfile.gettempdir(), f'edocr2_results_{int(time.time())}.zip')
+            import shutil
+            shutil.copy(zip_path, permanent_zip)
+            end_time = time.time()
+            processing_time = round(end_time - start_time, 2)
+            # Create statistics HTML
+            stats_html = f"""
+            <div style="background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
+                        padding: 20px; border-radius: 10px; color: white; margin: 10px 0;">
+                <h3 style="margin-top: 0;">📊 Processing Results</h3>
+                <div style="display: grid; grid-template-columns: repeat(auto-fit, minmax(150px, 1fr)); gap: 15px; margin-top: 15px;">
+                    <div style="background: rgba(255,255,255,0.2); padding: 15px; border-radius: 8px; text-align: center;">
+                        <div style="font-size: 2em; font-weight: bold;">{len(table_results)}</div>
+                        <div style="font-size: 0.9em; opacity: 0.9;">Tables Found</div>
+                    </div>
+                    <div style="background: rgba(255,255,255,0.2); padding: 15px; border-radius: 8px; text-align: center;">
+                        <div style="font-size: 2em; font-weight: bold;">{len(gdt_results)}</div>
+                        <div style="font-size: 0.9em; opacity: 0.9;">GD&T Symbols</div>
+                    </div>
+                    <div style="background: rgba(255,255,255,0.2); padding: 15px; border-radius: 8px; text-align: center;">
+                        <div style="font-size: 2em; font-weight: bold;">{len(dimensions)}</div>
+                        <div style="font-size: 0.9em; opacity: 0.9;">Dimensions</div>
+                    </div>
+                    <div style="background: rgba(255,255,255,0.2); padding: 15px; border-radius: 8px; text-align: center;">
+                        <div style="font-size: 2em; font-weight: bold;">{processing_time}s</div>
+                        <div style="font-size: 0.9em; opacity: 0.9;">Processing Time</div>
+                    </div>
+                </div>
+            </div>
+            """
+            print(f"✅ Processing complete in {processing_time}s")
+            return (
+                Image.fromarray(mask_img_rgb),
+                json_str,
+                csv_path if csv_path else None,
+                permanent_zip,
+                stats_html
+            )
+    except Exception as e:
+        error_msg = f"❌ Error processing drawing: {str(e)}"
+        print(error_msg)
+        import traceback
+        traceback.print_exc()
+        return None, error_msg, None, None, f"<div style='color: red;'>{error_msg}</div>"
+# Load models at startup
+print("="*60)
+print("🔧 eDOCr2 - Engineering Drawing OCR")
+print("="*60)
+load_models()
+# Create Gradio interface
+with gr.Blocks(theme=gr.themes.Soft(), title="eDOCr2 - Engineering Drawing OCR") as demo:
+    gr.Markdown("""
+    # 🔧 eDOCr2 - Engineering Drawing OCR
+    Extract **dimensions**, **tables**, and **GD&T symbols** from engineering drawings automatically.
+    Upload your engineering drawing (JPG, PNG, or PDF) and get structured data extracted instantly!
+    """)
+    with gr.Row():
+        with gr.Column(scale=1):
+            gr.Markdown("### 📤 Upload Drawing")
+            image_input = gr.Image(
+                type="pil",
+                label="Engineering Drawing",
+                sources=["upload", "clipboard"],
+                height=400
+            )
+            process_btn = gr.Button(
+                "🚀 Process Drawing",
+                variant="primary",
+                size="lg"
+            )
+            gr.Markdown("""
+            **Supported formats:** JPG, PNG, PDF
+            **Best results:** High-resolution scans with clear text
+            """)
+        with gr.Column(scale=1):
+            gr.Markdown("### 📊 Statistics")
+            stats_output = gr.HTML()
+            gr.Markdown("### 🎨 Annotated Drawing")
+            image_output = gr.Image(
+                label="Processed Drawing",
+                type="pil",
+                height=400
+            )
+    with gr.Row():
+        with gr.Column():
+            gr.Markdown("### 📋 Extracted Data (JSON)")
+            json_output = gr.Textbox(
+                label="Structured Data",
+                lines=15,
+                max_lines=20,
+                show_copy_button=True
+            )
+        with gr.Column():
+            gr.Markdown("### 💾 Download Results")
+            csv_output = gr.File(
+                label="📊 CSV File (if available)",
+                type="filepath"
+            )
+            zip_output = gr.File(
+                label="📦 Complete Results (ZIP)",
+                type="filepath"
+            )
+            gr.Markdown("""
+            **ZIP contains:**
+            - Annotated drawing image
+            - Structured data (JSON)
+            - Tabular data (CSV, if applicable)
+            """)
+    # Examples section
+    gr.Markdown("### 🧪 Try Example Drawings")
+    example_files = []
+    examples_dir = "tests/test_samples"
+    if os.path.exists(examples_dir):
+        for file in os.listdir(examples_dir):
+            if file.endswith(('.jpg', '.png')):
+                example_files.append([os.path.join(examples_dir, file)])
+    if example_files:
+        gr.Examples(
+            examples=example_files[:3],  # Show first 3 examples
+            inputs=image_input,
+            label="Click to load example"
+        )
+    # Footer
+    gr.Markdown("""
+    ---
+    ### 📚 About eDOCr2
+    eDOCr2 is a specialized OCR tool for engineering drawings that can extract:
+    - **Tables**: Title blocks, revision tables, bill of materials
+    - **GD&T Symbols**: Geometric dimensioning and tolerancing
+    - **Dimensions**: Measurements with tolerances
+    - **Other Information**: Additional text and annotations
+    **Research Paper:** [http://dx.doi.org/10.2139/ssrn.5045921](http://dx.doi.org/10.2139/ssrn.5045921)
+    **GitHub:** [github.com/javvi51/edocr2](https://github.com/javvi51/edocr2)
+    **Created by:** Javier Villena Toro | **Deployed by:** Jeyanthan GJ
+    """)
+    # Connect the process button
+    process_btn.click(
+        fn=process_drawing,
+        inputs=image_input,
+        outputs=[image_output, json_output, csv_output, zip_output, stats_output]
+    )
+# Launch the app
+if __name__ == "__main__":
+    demo.launch()