Duplicate from beykun18/Face-ID-Mediapipe

Co-authored-by: Bey Kun Chan <beykun18@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,31 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,13 @@
+---
+title: Face ID
+emoji: ⚡
+colorFrom: green
+colorTo: red
+sdk: gradio
+sdk_version: 3.4.1
+app_file: app.py
+pinned: false
+duplicated_from: beykun18/Face-ID-Mediapipe
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,81 @@
+from sklearn.metrics.pairwise import cosine_similarity
+from sentence_transformers import SentenceTransformer
+import datasets
+import gradio as gr
+import numpy as np
+import torchvision.transforms as transforms
+import mediapipe as mp
+import cv2
+
+#model = SentenceTransformer('clip-ViT-B-16')
+model = SentenceTransformer('clip-ViT-B-32')
+dataset = datasets.load_dataset('brendenc/celeb-identities')
+    
+def predict(im1, im2):
+    # Convert the PIL Image to a numpy array
+    im1 = np.array(im1)
+    im2 = np.array(im2)
+    face1 = im1.copy()
+    face2 = im2.copy()
+
+    img1_h, img1_w, _ = im1.shape
+    img2_h, img2_w, _ = im2.shape
+
+    # Locate face using mediapipe
+    mp_face_mesh = mp.solutions.face_mesh
+
+    with mp_face_mesh.FaceMesh(max_num_faces=1, refine_landmarks=True, min_detection_confidence=0.5, min_tracking_confidence=0.5) as face_mesh:
+        results1 = face_mesh.process(im1)
+        results2 = face_mesh.process(im2)
+
+        if results1.multi_face_landmarks:
+            for face_landmarks in results1.multi_face_landmarks:
+                # get location of face detected
+                top_x = int(face_landmarks.landmark[234].x * img1_w)
+                top_y = int(face_landmarks.landmark[10].y * img1_h)
+                bottom_x = int(face_landmarks.landmark[454].x * img1_w)
+                bottom_y = int(face_landmarks.landmark[152].y * img1_h)
+                
+                face1 = im1[top_y:bottom_y, top_x:bottom_x]
+                cv2.rectangle(im1, (top_x, top_y), (bottom_x, bottom_y), (0, 255, 0), 2)
+
+        if results2.multi_face_landmarks:
+            for face_landmarks in results2.multi_face_landmarks:
+                # get location of face detected
+                top_x = int(face_landmarks.landmark[234].x * img2_w)
+                top_y = int(face_landmarks.landmark[10].y * img2_h)
+                bottom_x = int(face_landmarks.landmark[454].x * img2_w)
+                bottom_y = int(face_landmarks.landmark[152].y * img2_h)
+                
+                face2 = im2[top_y:bottom_y, top_x:bottom_x]
+                cv2.rectangle(im2, (top_x, top_y), (bottom_x, bottom_y), (0, 255, 0), 2)
+
+    # Convert the tensor back to a PIL Image
+    face1 = transforms.ToPILImage()(face1)
+    im1 = transforms.ToPILImage()(im1)
+    face2 = transforms.ToPILImage()(face2)
+    im2 = transforms.ToPILImage()(im2)
+    
+  
+    embeddings = model.encode([face1, face2])
+    sim = cosine_similarity(embeddings)
+    sim = sim[0, 1]
+    if sim > 0.82:
+        return im1, im2, sim, "SAME PERSON, AUTHORIZE PAYMENT"
+    else:
+        return im1, im2, sim, "DIFFERENT PEOPLE, DON'T AUTHORIZE PAYMENT"
+
+
+interface = gr.Interface(fn=predict, 
+                         inputs= [gr.Image(value = dataset['train']['image'][10], type="pil", source="webcam"), 
+                                  gr.Image(value = dataset['train']['image'][17], type="pil", source="webcam")], 
+                         outputs= [gr.Image(),
+                                   gr.Image(),
+								   gr.Number(label="Similarity"),
+                                   gr.Textbox(label="Message")],
+                         title = 'Face ID',
+                         description = 'This app uses face biometrics and a similarity to function as a Face ID application.The similarity score ranges from -1 to 1.'
+                         )
+
+interface.launch(debug=True)
+#interface.launch(share=True)

requirements.txt

@@ -0,0 +1,7 @@
+scikit-learn
+datasets
+sentence_transformers
+mediapipe
+numpy
+torchvision
+opencv-python