Add description

app.py

@@ -24,7 +24,7 @@ DESIRED_SIZE = (640, 480)
 # -----------------------------
 posture_cache = {"landmarks": None, "text": "Initializing...", "counter": 0}
 emotion_cache = {"text": "Initializing...", "counter": 0}
-objects_cache = {"boxes": None, "text": "Initializing...", "counter": 0}
+objects_cache = {"boxes": None, "text": "Initializing...", "object_list_text": "", "counter": 0}
 faces_cache = {"boxes": None, "text": "Initializing...", "counter": 0}
 
 # -----------------------------
@@ -47,6 +47,9 @@ obj_transform = transforms.Compose([transforms.ToTensor()])
 # Initialize the FER emotion detector
 emotion_detector = FER(mtcnn=True)
 
+# Retrieve object categories from model weights metadata
+object_categories = FasterRCNN_ResNet50_FPN_Weights.DEFAULT.meta["categories"]
+
 # -----------------------------
 # Overlay Drawing Functions
 # -----------------------------
@@ -120,11 +123,16 @@ def compute_objects_overlay(image):
 
     threshold = 0.8
     boxes = []
-    for box, score in zip(detections["boxes"], detections["scores"]):
+    object_list = []
+    for box, score, label in zip(detections["boxes"], detections["scores"], detections["labels"]):
         if score > threshold:
             boxes.append(tuple(box.int().cpu().numpy()))
+            label_idx = int(label)
+            label_name = object_categories[label_idx] if label_idx < len(object_categories) else "Unknown"
+            object_list.append(f"{label_name} ({score:.2f})")
     text = f"Detected {len(boxes)} object(s)" if boxes else "No objects detected"
-    return boxes, text
+    object_list_text = " | ".join(object_list) if object_list else "None"
+    return boxes, text, object_list_text
 
 def compute_faces_overlay(image):
     frame_bgr = cv2.cvtColor(np.array(image), cv2.COLOR_RGB2BGR)
@@ -182,14 +190,16 @@ def analyze_objects_current(image):
     objects_cache["counter"] += 1
     current_frame = np.array(image)
     if objects_cache["counter"] % SKIP_RATE == 0 or objects_cache["boxes"] is None:
-        boxes, text = compute_objects_overlay(image)
+        boxes, text, object_list_text = compute_objects_overlay(image)
         objects_cache["boxes"] = boxes
         objects_cache["text"] = text
+        objects_cache["object_list_text"] = object_list_text
 
     output = current_frame.copy()
     if objects_cache["boxes"]:
         output = draw_boxes_overlay(output, objects_cache["boxes"], (255, 255, 0))
-    return output, f"<div style='color: lime !important;'>Object Detection: {objects_cache['text']}</div>"
+    combined_text = f"Object Detection: {objects_cache['text']}<br>Details: {objects_cache['object_list_text']}"
+    return output, f"<div style='color: lime !important;'>{combined_text}</div>"
 
 def analyze_faces_current(image):
     global faces_cache
@@ -206,7 +216,6 @@ def analyze_faces_current(image):
     return output, f"<div style='color: lime !important;'>Face Detection: {faces_cache['text']}</div>"
 
 def analyze_all(image):
-    # Run all analyses on the same image
     current_frame = np.array(image).copy()
     
     # Posture Analysis
@@ -218,7 +227,7 @@ def analyze_all(image):
     emotion_text = compute_emotion_overlay(image)
     
     # Object Detection
-    boxes_obj, objects_text = compute_objects_overlay(image)
+    boxes_obj, objects_text, object_list_text = compute_objects_overlay(image)
     if boxes_obj:
         current_frame = draw_boxes_overlay(current_frame, boxes_obj, (255, 255, 0))
         
@@ -227,26 +236,37 @@ def analyze_all(image):
     if boxes_face:
         current_frame = draw_boxes_overlay(current_frame, boxes_face, (0, 0, 255))
         
+    # Combined Analysis Text
     combined_text = (
-        f"Posture Analysis: {posture_text}<br>"
-        f"Emotion Analysis: {emotion_text}<br>"
-        f"Object Detection: {objects_text}<br>"
-        f"Face Detection: {faces_text}"
+        f"<b>Posture Analysis:</b> {posture_text}<br>"
+        f"<b>Emotion Analysis:</b> {emotion_text}<br>"
+        f"<b>Object Detection:</b> {objects_text}<br>"
+        f"<b>Detected Objects:</b> {object_list_text}<br>"
+        f"<b>Face Detection:</b> {faces_text}"
     )
+    
+    # Image Description Panel (High-Tech)
+    if object_list_text and object_list_text != "None":
+        description_text = f"Image Description: The scene features {object_list_text}."
+    else:
+        description_text = "Image Description: No prominent objects detected."
+        
+    combined_text += f"<br><br><div style='border:1px solid lime; padding:10px; box-shadow: 0 0 10px lime;'><b>{description_text}</b></div>"
+    
     combined_text_html = f"<div style='color: lime !important;'>{combined_text}</div>"
     return current_frame, combined_text_html
 
 # -----------------------------
-# Custom CSS (High-Tech Theme)
+# Custom CSS (High-Tech Neon Theme)
 # -----------------------------
 custom_css = """
 @import url('https://fonts.googleapis.com/css2?family=Orbitron:wght@400;700&display=swap');
 body {
     background-color: #0e0e0e;
-    color: #ffffff;
     font-family: 'Orbitron', sans-serif;
     margin: 0;
     padding: 0;
+    color: #32CD32;
 }
 .gradio-container {
     background: linear-gradient(135deg, #1a1a1a, #333333);
@@ -257,23 +277,14 @@ body {
     max-width: 1200px;
     margin: auto;
 }
-.gradio-title {
-    font-size: 2.5em;
-    color: #32CD32;
-    text-align: center;
-    margin-bottom: 0.2em;
+.gradio-title, .gradio-description, .tab-item, .tab-item * {
+    color: #32CD32 !important;
     text-shadow: 0 0 10px #32CD32;
 }
-.gradio-description {
-    font-size: 1.2em;
-    text-align: center;
-    margin-bottom: 1em;
-    color: #32CD32;
-    text-shadow: 0 0 8px #32CD32;
-}
-input, button, .output, .tab-item {
+input, button, .output {
     border: 1px solid #32CD32;
     box-shadow: 0 0 8px #32CD32;
+    color: #32CD32;
 }
 """
 
@@ -284,7 +295,7 @@ posture_interface = gr.Interface(
     fn=analyze_posture_current,
     inputs=gr.Image(label="Upload an Image for Posture Analysis"),
     outputs=[gr.Image(type="numpy", label="Annotated Output"), gr.HTML(label="Posture Analysis")],
-    title="Posture Analysis",
+    title="Posture",
     description="Detects your posture using MediaPipe with connector lines.",
     live=False
 )
@@ -293,7 +304,7 @@ emotion_interface = gr.Interface(
     fn=analyze_emotion_current,
     inputs=gr.Image(label="Upload an Image for Emotion Analysis"),
     outputs=[gr.Image(type="numpy", label="Annotated Output"), gr.HTML(label="Emotion Analysis")],
-    title="Emotion Analysis",
+    title="Emotion",
     description="Detects facial emotions using FER.",
     live=False
 )
@@ -302,7 +313,7 @@ objects_interface = gr.Interface(
     fn=analyze_objects_current,
     inputs=gr.Image(label="Upload an Image for Object Detection"),
     outputs=[gr.Image(type="numpy", label="Annotated Output"), gr.HTML(label="Object Detection")],
-    title="Object Detection",
+    title="Objects",
     description="Detects objects using a pretrained Faster R-CNN.",
     live=False
 )
@@ -311,7 +322,7 @@ faces_interface = gr.Interface(
     fn=analyze_faces_current,
     inputs=gr.Image(label="Upload an Image for Face Detection"),
     outputs=[gr.Image(type="numpy", label="Annotated Output"), gr.HTML(label="Face Detection")],
-    title="Face Detection",
+    title="Faces",
     description="Detects faces using MediaPipe.",
     live=False
 )
@@ -338,10 +349,8 @@ tabbed_interface = gr.TabbedInterface(
 # -----------------------------
 demo = gr.Blocks(css=custom_css)
 with demo:
-    gr.Markdown("<h1 class='gradio-title'>Multi-Analysis Image App</h1>")
-    gr.Markdown(
-        "<p class='gradio-description'>Upload an image to run high-tech analysis for posture, emotions, objects, and faces.</p>"
-    )
+    gr.Markdown("<h1 class='gradio-title' style='color: #32CD32;'>Multi-Analysis Image App</h1>")
+    gr.Markdown("<p class='gradio-description' style='color: #32CD32;'>Upload an image to run high-tech analysis for posture, emotions, objects, and faces.</p>")
     tabbed_interface.render()
 
 if __name__ == "__main__":