Upload 4 files

embeddings_app.py

@@ -0,0 +1,42 @@
+import os
+from tqdm import tqdm
+from glob import glob
+import numpy as np
+import cv2 as cv2
+import insightface
+from insightface.app import FaceAnalysis
+from insightface.data  import get_image as ins_get_image
+import cv2
+from insightface.app import FaceAnalysis
+import matplotlib.pyplot as plt
+import utils
+import streamlit as st
+from utils import app
+
+def get_embeddings(db_dir):
+    names = []
+    embeddings = []
+
+    # Traverse through each subfolder
+    for root, dirs, files in os.walk(db_dir):
+        for folder in dirs:
+            if folder == ".ipynb_checkpoints":
+                continue
+            img_paths = glob(os.path.join(root, folder, '*'))
+            for img_path in img_paths:
+                img = cv2.imread(img_path)
+                if img is None:
+                    continue
+                faces = app.get(img)
+                if len(faces) != 1:
+                    continue
+                face = faces[0]
+                names.append(folder)
+                embeddings.append(face.normed_embedding)
+
+    if embeddings:
+        embeddings = np.stack(embeddings, axis=0)
+        np.save(os.path.join(db_dir, "embeddings.npy"), embeddings)
+        np.save(os.path.join(db_dir, "names.npy"), names)
+    else:
+        st.warning("No embeddings generated. Please ensure that there are valid images with detected faces.")

image_app.py

@@ -0,0 +1,65 @@
+import streamlit as st
+import cv2
+import numpy as np
+from embeddings import app
+import os
+from tqdm import tqdm
+from glob import glob
+import numpy as np
+import cv2 as cv2
+import insightface
+from insightface.app import FaceAnalysis
+from insightface.data  import get_image as ins_get_image
+import cv2
+from insightface.app import FaceAnalysis
+import matplotlib.pyplot as plt
+import utils
+from utils import app
+
+
+# Define function to recognize faces and display bounding boxes
+def recognize_and_display(input_img, known_embeddings, names, app):
+    # Perform face analysis on the input image
+    faces = app.get(input_img)
+
+    # Check if any face is detected
+    if len(faces) == 0:
+        # If no face detected, draw bounding box with "unknown" text for the whole image
+        input_img_with_bb = input_img.copy()
+        cv2.putText(input_img_with_bb, "Unknown", (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2)
+        st.image(cv2.cvtColor(input_img_with_bb, cv2.COLOR_BGR2RGB), caption='No face detected', use_column_width=True)
+        return "No face detected"
+    else:
+        # Process each detected face separately
+        for face in faces:
+            # Retrieve the embedding for the detected face
+            detected_embedding = face.normed_embedding
+
+            # Calculate similarity scores with known embeddings
+            scores = np.dot(detected_embedding, np.array(known_embeddings).T)
+            scores = np.clip(scores, 0., 1.)
+
+            # Find the index with the highest score
+            idx = np.argmax(scores)
+            max_score = scores[idx]
+
+            # Check if the maximum score is above a certain threshold (adjust as needed)
+            threshold = 0.7
+            if max_score >= threshold:
+                recognized_name = names[idx]
+            else:
+                recognized_name = "Unknown"
+
+            # Draw bounding box around the detected face
+            bbox = face.bbox.astype(int)
+            cv2.rectangle(input_img, (bbox[0], bbox[1]), (bbox[2], bbox[3]), (0, 0, 255), 10)
+            # Write recognized name within the bounding box
+            cv2.putText(input_img, recognized_name, (bbox[0], bbox[1] - 10), cv2.FONT_HERSHEY_SIMPLEX, 5.0, (0, 255, 0), 10)
+
+        # Display the image with bounding boxes using Streamlit
+        st.image(cv2.cvtColor(input_img, cv2.COLOR_BGR2RGB), caption='Face Recognition Result', use_column_width=True)
+
+        if "Unknown" in names:
+            return "Face not recognized"
+        else:
+            return f"All faces recognized"

utils.py

@@ -0,0 +1,15 @@
+import os
+from tqdm import tqdm
+from glob import glob
+import numpy as np
+import cv2 as cv2
+import insightface
+from insightface.app import FaceAnalysis
+from insightface.data  import get_image as ins_get_image
+import cv2
+from insightface.app import FaceAnalysis
+import matplotlib.pyplot as plt
+
+
+app = FaceAnalysis(name='buffalo_l')
+app.prepare(ctx_id=0, det_size=(640, 640),)

webcam_app.py

@@ -0,0 +1,66 @@
+import os
+import cv2
+import numpy as np
+import streamlit as st
+import insightface
+from insightface.app import FaceAnalysis
+from insightface.data  import get_image as ins_get_image
+from glob import glob
+from tqdm import tqdm
+from streamlit_webrtc import webrtc_streamer, VideoTransformerBase
+import shutil
+import zipfile
+import image_app
+from utils import app
+from embeddings_app import get_embeddings
+
+
+class FaceRecognitionTransformer(VideoTransformerBase):
+    def __init__(self):
+        self.app = FaceAnalysis(name='buffalo_l')
+        self.app.prepare(ctx_id=0, det_size=(640, 640))
+        self.names = None
+        self.embeddings = None
+
+    def _recognize_faces(self, frame):
+        if self.names is None or self.embeddings is None:
+            return frame
+
+        # Perform face analysis on the frame
+        faces = self.app.get(frame)
+
+        # Process each detected face separately
+        for face in faces:
+            # Retrieve the embedding for the detected face
+            detected_embedding = face.normed_embedding
+
+            # Calculate similarity scores with known embeddings
+            scores = np.dot(detected_embedding, np.array(self.embeddings).T)
+            scores = np.clip(scores, 0., 1.)
+
+            # Find the index with the highest score
+            idx = np.argmax(scores)
+            max_score = scores[idx]
+
+            # Check if the maximum score is above a certain threshold (adjust as needed)
+            threshold = 0.7
+            if max_score >= threshold:
+                recognized_name = self.names[idx]
+            else:
+                recognized_name = "Unknown"
+
+            # Draw bounding box around the detected face
+            bbox = face.bbox.astype(int)
+            cv2.rectangle(frame, (bbox[0], bbox[1]), (bbox[2], bbox[3]), (0, 255, 0), 2)
+            # Write recognized name within the bounding box
+            cv2.putText(frame, recognized_name, (bbox[0], bbox[1] - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.9, (0, 255, 0), 2)
+            
+            # Debug print
+            print("Detected face:", recognized_name, "with confidence:", max_score)
+
+        return frame
+
+    def transform(self, frame):
+        frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+        frame = self._recognize_faces(frame)
+        return frame