import face_recognition import cv2 import numpy as np import imageSegmentation from mediapipe.tasks.python import vision import Visualization_utilities as vis import time # Get a reference to webcam #0 (the default one) # video_capture = cv2.VideoCapture(0) # Load a sample picture and learn how to recognize it. def get_face_encoding(path): print(f'path: {path}') print('hello') HKID_cropped = imageSegmentation.auto_cropping(path) cv2.imwrite('saved/HKID.jpg', HKID_cropped) HKID_image = face_recognition.load_image_file("saved/HKID.jpg") HKID_face_encoding = face_recognition.face_encodings(HKID_image)[0] return HKID_face_encoding # HKID_image = face_recognition.load_image_file("saved/HKID.jpg") # HKID_face_encoding = face_recognition.face_encodings(HKID_image)[0] # Create arrays of known face encodings and their names # known_face_encodings = [ # HKID_face_encoding # ] # known_face_names = [ # "Marco" # ] # Initialize some variables # face_locations = [] # face_encodings = [] # face_names = [] # process_this_frame = True # score = [] # faces = 0 # number of faces # while True: # # Grab a single frame of video # ret, frame = video_capture.read() # # # Draw a label with a name below the face # # cv2.rectangle(frame, (left, bottom - 35), (right, bottom), (0, 0, 255), cv2.FILLED) # # font = cv2.FONT_HERSHEY_DUPLEX # # cv2.putText(frame, name, (left + 6, bottom - 6), font, 1.0, (255, 255, 255), 1) # # Display the resulting image # cv2.imshow('Video', frame) # # Hit 'q' on the keyboard to quit! # if cv2.waitKey(1) & 0xFF == ord('q'): # break # frames are the snapshot of the video def process_frame(frame, process_this_frame, face_locations, faces, face_names, score): hkid_face_encoding = get_face_encoding("image") print(f'encoding: {hkid_face_encoding}') known_face_encodings = [ hkid_face_encoding ] known_face_names = [ "recognized" ] # Only process every other frame of video to save time if process_this_frame: face_names = [] # Resize frame of video to 1/4 size for faster face recognition processing # if frame != None: # print(f'frame: {len(frame)}') # try: # small_frame = cv2.imread(image_dir) small_frame = cv2.resize(frame, (0, 0), fx=0.25, fy=0.25) # else: # print('fram has nth') # Convert the image from BGR color (which OpenCV uses) to RGB color (which face_recognition uses) rgb_small_frame = cv2.cvtColor(small_frame, cv2.COLOR_BGR2RGB) # Find all the faces and face encodings in the current frame of video face_locations = face_recognition.face_locations(rgb_small_frame) face_encodings = face_recognition.face_encodings(rgb_small_frame, face_locations) faces = len(face_encodings) # number of faces for face_encoding in face_encodings: # See if the face is a match for the known face(s) matches = face_recognition.compare_faces(known_face_encodings, face_encoding) name = "Unknown" # # If a match was found in known_face_encodings, just use the first one. # if True in matches: # first_match_index = matches.index(True) # name = known_face_names[first_match_index] # Or instead, use the known face with the smallest distance to the new face face_distances = face_recognition.face_distance(known_face_encodings, face_encoding) best_match_index = np.argmin(face_distances) print(face_distances) if matches[best_match_index] and face_distances[best_match_index] < 0.45: score.append(face_distances[best_match_index]) name = known_face_names[best_match_index] else: score = [] face_names.append(name) # if len(score) > 20: # avg_score = sum(score) / len(score) # Display the results if faces > 1 : # Define the text and font properties text = "More than 1 person detected!" font = cv2.FONT_HERSHEY_DUPLEX font_scale = 1 font_thickness = 2 # Calculate the text size window_height = frame.shape[0] window_width = frame.shape[1] text_size, _ = cv2.getTextSize(text, font, font_scale, font_thickness) # Calculate the text position text_x = int((window_width - text_size[0]) / 2) text_y = window_height - int(text_size[1] / 2) cv2.putText(frame, text, (text_x, text_y), font, font_scale, (255, 255, 255), font_thickness, cv2.LINE_AA) for (top, right, bottom, left), name in zip(face_locations, face_names): # Scale back up face locations since the frame we detected in was scaled to 1/4 size top *= 4 right *= 4 bottom *= 4 left *= 4 # Draw a box around the face cv2.rectangle(frame, (left, top), (right, bottom), (65, 181, 41), 4) # Define the name box properties name_box_color = (44, 254, 0) name_box_alpha = 0.7 name_box_thickness = -1 # Define the text properties font = cv2.FONT_HERSHEY_TRIPLEX font_scale = 1 font_thickness = 2 text_color = (255, 255, 255) # Calculate the text size text_width, text_height = cv2.getTextSize(name, font, font_scale, font_thickness)[0] # Draw the name box cv2.rectangle(frame, (left, bottom - 35), (right, bottom), name_box_color, name_box_thickness) cv2.rectangle(frame, (left, bottom - 35), (right, bottom), name_box_color, cv2.FILLED) # Draw the name text cv2.putText(frame, name, (left + 70, bottom - 6), font, font_scale, text_color, font_thickness) process_this_frame = process_this_frame frame = cv2.cvtColor(frame, cv2.COLOR_RGB2BGR) return frame, process_this_frame, face_locations, faces, face_names, score def convert_distance_to_percentage(distance, threshold): if distance < threshold: score = 80 score += distance / 0.45 * 20 else: score = (1 - distance) * 100 return score # percent = convert_distance_to_percentage(avg_score, 0.45) # print(f'avg_score = {percent:.2f}% : Approved!') # # Release handle to the webcam # video_capture.release() # cv2.destroyAllWindows()