refine the gradio app

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.jpg filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+venv

app.py

@@ -1,21 +1,156 @@
+# import gradio as gr
+# import numpy as np
+# from PIL import Image, ImageEnhance
+# from ultralytics import YOLO
+# import cv2
+
+# # Load YOLO model
+# model_path = "./best.pt"
+# modelY = YOLO(model_path)
+# modelY.to('cpu')
+
+# # Preprocessing function
+# def preprocessing(image):
+#     if image.mode != 'RGB':
+#         image = image.convert('RGB')
+#     image = ImageEnhance.Sharpness(image).enhance(2.0)
+#     image = ImageEnhance.Contrast(image).enhance(1.5)
+#     image = ImageEnhance.Brightness(image).enhance(0.8)
+#     width = 448
+#     aspect_ratio = image.height / image.width
+#     height = int(width * aspect_ratio)
+#     return image.resize((width, height))
+
+# # YOLO document detection and cropping
+# def detect_and_crop_document(image):
+#     image_np = np.array(image)
+#     results = modelY(image_np, conf=0.80, device='cpu')
+#     cropped_images = []
+#     predictions = []
+    
+#     for result in results:
+#         for box in result.boxes:
+#             x1, y1, x2, y2 = map(int, box.xyxy[0])
+#             conf = int(box.conf[0] * 100)  # Convert confidence to percentage
+#             cls = int(box.cls[0])
+#             class_name = modelY.names[cls].capitalize()  # Capitalize class names
+#             cropped_image_np = image_np[y1:y2, x1:x2]
+#             cropped_image = Image.fromarray(cropped_image_np)
+#             cropped_images.append(cropped_image)
+#             predictions.append(f"Detected: STNK {class_name} -- (Confidence: {conf}%)")
+    
+#     if not cropped_images:
+#         return None, "No document detected"
+#     return cropped_images, predictions
+
+# # Gradio interface
+# def process_image(image):
+#     preprocessed_image = preprocessing(image)
+#     cropped_images, predictions = detect_and_crop_document(preprocessed_image)
+    
+#     if cropped_images:
+#         return cropped_images, '\n'.join(predictions)
+#     return None, "No document detected"
+
+# with gr.Blocks(css=".gr-button {background-color: #4caf50; color: white; font-size: 16px; padding: 10px 20px; border-radius: 8px;}") as demo:
+#     gr.Markdown(
+#         """
+#         <h1 style="text-align: center; color: #4caf50;">📜 License Registration Classification</h1>
+#         <p style="text-align: center; font-size: 18px;">Upload an image and let the YOLO model detect and crop license documents automatically.</p>
+#         """
+#     )
+#     with gr.Row():
+#         with gr.Column(scale=1, min_width=300):
+#             input_image = gr.Image(type="pil", label="Upload License Image", interactive=True)
+#             with gr.Row():
+#                 clear_btn = gr.Button("Clear")
+#                 submit_btn = gr.Button("Detect Document")
+#         with gr.Column(scale=2):
+#             output_image = gr.Gallery(label="Cropped Documents", interactive=False)
+#             output_text = gr.Textbox(label="Detection Result", interactive=False)
+
+#     submit_btn.click(process_image, inputs=input_image, outputs=[output_image, output_text])
+#     clear_btn.click(lambda: (None, ""), outputs=[output_image, output_text])
+
+# demo.launch()
+
+
+
+
 import gradio as gr
 import numpy as np
 from PIL import Image, ImageEnhance
 from ultralytics import YOLO
 import cv2
+import os
+
+# --- DOCUMENTATION STRINGS (English Only) ---
+
+GUIDELINE_SETUP = """
+## 1. Quick Start Guide: Setup and Run Instructions
+
+This application uses a YOLO model to automatically detect, classify, and extract specific license registration documents (STNK).
+
+1.  **Preparation:** Ensure your image clearly shows the target license document.
+2.  **Upload:** Click the 'Upload License Image' box and select your image (JPG, PNG).
+3.  **Run:** Click the **"Detect Document"** button.
+4.  **Review:** The detected documents will appear in the 'Cropped Documents' gallery, and the 'Detection Result' box will show the classification and confidence score.
+"""
+
+GUIDELINE_INPUT = """
+## 2. Expected Inputs and Preprocessing
+
+| Input Field | Purpose | Requirement |
+| :--- | :--- | :--- |
+| **Upload License Image** | The image containing the license document you want to detect and classify. | Must be an image file (e.g., JPG, PNG). |
+
+### Automatic Preprocessing Steps:
+Before detection, the input image is automatically adjusted to enhance accuracy:
+1.  **Sharpness:** Increased sharpness by 2.0.
+2.  **Contrast:** Increased contrast by 1.5.
+3.  **Brightness:** Slightly reduced brightness by 0.8.
+4.  **Resizing:** The image is resized to a width of 448 pixels while maintaining its original aspect ratio.
+"""
+
+GUIDELINE_OUTPUT = """
+## 3. Expected Outputs (Detection and Classification)
+
+The application produces two outputs based on a successful detection:
+
+1.  **Cropped Documents (Gallery):**
+    *   This gallery displays only the regions of the image where a license document was confidently detected (Confidence > 80%).
+    *   If multiple documents are found, all cropped images will appear here.
+
+2.  **Detection Result (Textbox):**
+    *   A text summary listing each detected document, including its specific class name (e.g., 'STNK Class A'), and the model's confidence level (as a percentage).
+
+### Failure Modes:
+*   If "No document detected" is returned, it means the model did not find a document with a confidence level of 80% or higher, or the image quality was too poor for detection.
+"""
+
+# --- CORE LOGIC ---
 
 # Load YOLO model
+# NOTE: Ensure 'best.pt' is available in the execution directory.
 model_path = "./best.pt"
-modelY = YOLO(model_path)
-modelY.to('cpu')
+try:
+    modelY = YOLO(model_path)
+    modelY.to('cpu')
+except Exception as e:
+    print(f"Error loading model: {e}")
+    modelY = None
 
 # Preprocessing function
 def preprocessing(image):
     if image.mode != 'RGB':
         image = image.convert('RGB')
+    
+    # Enhancement steps
     image = ImageEnhance.Sharpness(image).enhance(2.0)
     image = ImageEnhance.Contrast(image).enhance(1.5)
     image = ImageEnhance.Brightness(image).enhance(0.8)
+    
+    # Resizing while preserving aspect ratio
     width = 448
     aspect_ratio = image.height / image.width
     height = int(width * aspect_ratio)
@@ -23,53 +158,102 @@ def preprocessing(image):
 
 # YOLO document detection and cropping
 def detect_and_crop_document(image):
+    if modelY is None:
+        return [], ["Model not loaded."]
+        
     image_np = np.array(image)
-    results = modelY(image_np, conf=0.80, device='cpu')
+    # Run inference with confidence threshold 0.80
+    results = modelY(image_np, conf=0.80, device='cpu', verbose=False)
+    
     cropped_images = []
     predictions = []
     
     for result in results:
         for box in result.boxes:
             x1, y1, x2, y2 = map(int, box.xyxy[0])
-            conf = int(box.conf[0] * 100)  # Convert confidence to percentage
-            cls = int(box.cls[0])
-            class_name = modelY.names[cls].capitalize()  # Capitalize class names
+            conf = int(box.conf[0].item() * 100) # Ensure conversion to scalar for item()
+            cls = int(box.cls[0].item())
+            class_name = modelY.names.get(cls, "Unknown").capitalize()
+            
             cropped_image_np = image_np[y1:y2, x1:x2]
-            cropped_image = Image.fromarray(cropped_image_np)
-            cropped_images.append(cropped_image)
-            predictions.append(f"Detected: STNK {class_name} -- (Confidence: {conf}%)")
+            
+            # Check for valid crop size before converting to PIL
+            if cropped_image_np.size > 0:
+                cropped_image = Image.fromarray(cropped_image_np)
+                cropped_images.append(cropped_image)
+                predictions.append(f"Detected: STNK {class_name} -- (Confidence: {conf}%)")
     
-    if not cropped_images:
-        return None, "No document detected"
     return cropped_images, predictions
 
-# Gradio interface
+# Gradio interface function
 def process_image(image):
+    if image is None:
+        raise gr.Error("Please upload an image.")
+        
     preprocessed_image = preprocessing(image)
     cropped_images, predictions = detect_and_crop_document(preprocessed_image)
     
     if cropped_images:
         return cropped_images, '\n'.join(predictions)
-    return None, "No document detected"
+    
+    # If no documents are detected with sufficient confidence
+    return [], "No document detected (Confidence threshold not met or image is unclear)."
+
+# --- GRADIO UI SETUP ---
+
+# Define example paths (NOTE: Replace with actual paths if needed)
+examples = [
+    ["./licence2.jpg"],
+    ["./licence.jpg"],
+]
 
 with gr.Blocks(css=".gr-button {background-color: #4caf50; color: white; font-size: 16px; padding: 10px 20px; border-radius: 8px;}") as demo:
+    
     gr.Markdown(
         """
-        <h1 style="text-align: center; color: #4caf50;">📜 License Registration Classification</h1>
-        <p style="text-align: center; font-size: 18px;">Upload an image and let the YOLO model detect and crop license documents automatically.</p>
+        <h1 style="color: #4caf50;">License Registration Classification</h1>
+        <p style="font-size: 18px;">Upload an image and let the YOLO model detect and crop license documents automatically.</p>
         """
     )
+    
+    # 1. GUIDELINES SECTION
+    with gr.Accordion("User Guidelines and Documentation", open=False):
+        gr.Markdown(GUIDELINE_SETUP)
+        gr.Markdown("---")
+        gr.Markdown(GUIDELINE_INPUT)
+        gr.Markdown("---")
+        gr.Markdown(GUIDELINE_OUTPUT)
+        
+    gr.Markdown("---")
+    
+    # 2. APPLICATION INTERFACE
     with gr.Row():
         with gr.Column(scale=1, min_width=300):
             input_image = gr.Image(type="pil", label="Upload License Image", interactive=True)
             with gr.Row():
                 clear_btn = gr.Button("Clear")
                 submit_btn = gr.Button("Detect Document")
+        
         with gr.Column(scale=2):
-            output_image = gr.Gallery(label="Cropped Documents", interactive=False)
-            output_text = gr.Textbox(label="Detection Result", interactive=False)
+            output_image = gr.Gallery(label="Cropped Documents", interactive=False, object_fit="contain")
+            output_text = gr.Textbox(label="Detection Result", interactive=False, lines=5)
 
     submit_btn.click(process_image, inputs=input_image, outputs=[output_image, output_text])
-    clear_btn.click(lambda: (None, ""), outputs=[output_image, output_text])
+    clear_btn.click(lambda: (None, ""), outputs=[output_image, output_text, input_image], show_progress=False)
+
+    gr.Markdown("---")
+
+    # 3. EXAMPLES SECTION
+    gr.Markdown("## Sample Data for Testing")
+    
+    gr.Examples(
+        examples=examples,
+        inputs=input_image,
+        outputs=[output_image, output_text],
+        fn=process_image,
+        cache_examples=False,
+        label="Click to load and run a sample detection.",
+    )
 
+demo.queue()
 demo.launch()

requirements.txt

@@ -1,6 +1,8 @@
-gradio
 ultralytics
 pillow
 numpy
 opencv-python
-torch
+torch
+numpy<2
+gradio==3.50.2 
+gradio-client==0.6.1