Update

app.py

@@ -4,6 +4,9 @@ import numpy as np
 from PIL import Image
 import mediapipe as mp
 from fer import FER  # Facial emotion recognition
+from ultralytics import YOLO  # YOLOv8 for face detection
+from huggingface_hub import hf_hub_download
+from supervision import Detections
 
 # -----------------------------
 # Configuration
@@ -11,6 +14,17 @@ from fer import FER  # Facial emotion recognition
 SKIP_RATE = 1  # For image processing, always run the analysis
 DESIRED_SIZE = (640, 480)
 
+# -----------------------------
+# Sample Images (Preset Suggested Photos)
+# -----------------------------
+SAMPLE_IMAGES = [
+    "https://upload.wikimedia.org/wikipedia/commons/7/76/Daniel_Diermeier_2020_%28cropped%29.jpg",
+    "https://upload.wikimedia.org/wikipedia/commons/thumb/b/b6/Gilbert_Stuart_Williamstown_Portrait_of_George_Washington.jpg/1200px-Gilbert_Stuart_Williamstown_Portrait_of_George_Washington.jpg",
+    "https://upload.wikimedia.org/wikipedia/commons/thumb/8/8d/President_Barack_Obama.jpg/800px-President_Barack_Obama.jpg",
+    "https://images.wsj.net/im-98527587?width=1280&size=1",
+    "https://media.npr.org/assets/img/2023/11/28/dr.buolamwiniheadshot_c-naima-green-1-_custom-05cd4ce4570c688d00cc558d16c76745abd07539.png"
+]
+
 # -----------------------------
 # Global caches for overlay info and frame counters
 # -----------------------------
@@ -21,17 +35,20 @@ faces_cache = {"boxes": None, "text": "Initializing...", "counter": 0}
 # -----------------------------
 # Initialize Models and Helpers
 # -----------------------------
-# MediaPipe Pose, Face Detection, and Face Mesh
+# MediaPipe Pose and Drawing
 mp_pose = mp.solutions.pose
 pose = mp_pose.Pose()
 mp_drawing = mp.solutions.drawing_utils
 
-mp_face_detection = mp.solutions.face_detection
-face_detection = mp_face_detection.FaceDetection(min_detection_confidence=0.5)
-
 # Initialize the FER emotion detector (using the FER package)
 emotion_detector = FER(mtcnn=True)
 
+# -----------------------------
+# Download YOLOv8 face detection model from Hugging Face
+# -----------------------------
+model_path = hf_hub_download(repo_id="arnabdhar/YOLOv8-Face-Detection", filename="model.pt")
+yolo_face_model = YOLO(model_path)
+
 # -----------------------------
 # Overlay Drawing Functions
 # -----------------------------
@@ -86,21 +103,18 @@ def compute_emotion_overlay(image):
     return text
 
 def compute_faces_overlay(image):
-    frame_bgr = cv2.cvtColor(np.array(image), cv2.COLOR_RGB2BGR)
-    h, w, _ = frame_bgr.shape
-    frame_bgr_small = cv2.resize(frame_bgr, DESIRED_SIZE)
-    small_h, small_w, _ = frame_bgr_small.shape
-    frame_rgb_small = cv2.cvtColor(frame_bgr_small, cv2.COLOR_BGR2RGB)
-    face_results = face_detection.process(frame_rgb_small)
+    """
+    Uses the YOLOv8 face detection model from Hugging Face.
+    Processes the input image and returns bounding boxes using Supervision Detections.
+    """
+    pil_image = image if isinstance(image, Image.Image) else Image.fromarray(image)
+    output = yolo_face_model(pil_image)
+    results = Detections.from_ultralytics(output[0])
     boxes = []
-    if face_results.detections:
-        for detection in face_results.detections:
-            bbox = detection.location_data.relative_bounding_box
-            x = int(bbox.xmin * small_w)
-            y = int(bbox.ymin * small_h)
-            box_w = int(bbox.width * small_w)
-            box_h = int(bbox.height * small_h)
-            boxes.append((x, y, x + box_w, y + box_h))
+    if results.xyxy.shape[0] > 0:
+        for box in results.xyxy:
+            x1, y1, x2, y2 = map(int, box)
+            boxes.append((x1, y1, x2, y2))
         text = f"Detected {len(boxes)} face(s)"
     else:
         text = "No faces detected"
@@ -157,8 +171,11 @@ def compute_facemesh_overlay(image):
 
 def analyze_facemesh(image):
     annotated_image, mask_image, text = compute_facemesh_overlay(image)
-    return (annotated_image, mask_image, 
-            f"<div style='color: #00ff00 !important;'>Facemesh Analysis: {text}</div>")
+    return (
+        annotated_image,
+        mask_image,
+        f"<div style='color: #00ff00 !important;'>Facemesh Analysis: {text}</div>"
+    )
 
 # -----------------------------
 # Main Analysis Functions for Single Image
@@ -203,11 +220,13 @@ def analyze_faces_current(image):
 # -----------------------------
 custom_css = """
 @import url('https://fonts.googleapis.com/css2?family=Orbitron:wght@400;700&display=swap');
+
 body {
     background-color: #121212;
     font-family: 'Orbitron', sans-serif;
-    color: #00ff00;
+    color: #00ff00 !important;
 }
+
 .gradio-container {
     background: linear-gradient(135deg, #2d2d2d, #1a1a1a);
     border: 2px solid #00ff00;
@@ -217,10 +236,13 @@ body {
     max-width: 1200px;
     margin: auto;
 }
-.gradio-title, .gradio-description, .tab-item, .tab-item * {
+
+.gradio-title, .gradio-description, .tab-item, .tab-item *,
+label, .label, .wrap .label, .wrap .input, .wrap .output, .wrap .description {
     color: #00ff00 !important;
     text-shadow: 0 0 10px #00ff00;
 }
+
 input, button, .output {
     border: 1px solid #00ff00;
     box-shadow: 0 0 8px #00ff00;
@@ -236,8 +258,9 @@ 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",
-    description="Detects your posture using MediaPipe with connector lines.",
+    title="<div style='color:#00ff00;'>Posture",
+    description="<div style='color:#00ff00;'>Detects posture using MediaPipe with connector lines.</div>",
+    examples=SAMPLE_IMAGES,  # clickable examples at bottom
     live=False
 )
 
@@ -245,8 +268,9 @@ 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",
-    description="Detects facial emotions using FER.",
+    title="<div style='color:#00ff00;'>Emotion",
+    description="<div style='color:#00ff00;'>Detects facial emotions using FER.</div>",
+    examples=SAMPLE_IMAGES,
     live=False
 )
 
@@ -254,8 +278,9 @@ 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="Faces",
-    description="Detects faces using MediaPipe.",
+    title="<div style='color:#00ff00;'>Faces",
+    description="<div style='color:#00ff00;'>Detects faces using fine-tuned YOLOv8 model.</div>",
+    examples=SAMPLE_IMAGES,
     live=False
 )
 
@@ -267,8 +292,9 @@ facemesh_interface = gr.Interface(
         gr.Image(type="numpy", label="Mask Output"),
         gr.HTML(label="Facemesh Analysis")
     ],
-    title="Facemesh",
-    description="Detects facial landmarks using MediaPipe Face Mesh and outputs both an annotated image and a mask on a black background.",
+    title="<div style='color:#00ff00;'>Facemesh",
+    description="<div style='color:#00ff00;'>Detects facial landmarks using MediaPipe Face Mesh.</div>",
+    examples=SAMPLE_IMAGES,
     live=False
 )
 
@@ -294,6 +320,10 @@ 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, faces, and facemesh landmarks.</p>")
+    
+    # We removed the top-row sample images and now rely on
+    # the built-in Gradio examples at the bottom of each tab.
+    
     tabbed_interface.render()
 
 if __name__ == "__main__":