Spaces:
Running
Running
| 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_x2 = int(face_landmarks.landmark[234].x * img2_w) | |
| top_y2 = int(face_landmarks.landmark[10].y * img2_h) | |
| bottom_x2 = int(face_landmarks.landmark[454].x * img2_w) | |
| bottom_y2 = int(face_landmarks.landmark[152].y * img2_h) | |
| face2 = im2[top_y2:bottom_y2, top_x2:bottom_x2] | |
| cv2.rectangle(im2, (top_x2, top_y2), (bottom_x2, bottom_y2), (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) | |