KNN w/ Webcam

[shiveksachdev]

• face_recognition version: 1.2.3
• Python version: Python 3.7.3
• Operating System: Windows 10

Description

Running Face Recognition from Webcam but it's not accurate. ("facerec_from_webcam_faster.py"). I'm assuming that the problem is because it uses only 1 image per person - therefore wanting to switch to KNN.

But the sample KNN code doesn't work with Webcam - KNN in the example works with images as input and labels faces with rectangle boxes as output.

I've been trying to get it to input from web cam and use KNN but it keeps on crashing.

Looks to me like a basic coding problem - anyone able to help me with this?

Thanks

[fadi212]

Can you share the code ? Will have to see where the problem lies. One thing that you may want to check is if you are using opencv or not ?

[shiveksachdev]

Can you share the code ? Will have to see where the problem lies. One thing that you may want to check is if you are using opencv or not ?

Managed to get it to work!

import math
from sklearn import neighbors
import os
import os.path
import pickle
from PIL import Image, ImageDraw
import face_recognition
from face_recognition.face_recognition_cli import image_files_in_folder
import cv2

# ALLOWED_EXTENSIONS = {'png', 'jpg', 'jpeg'}

def train(train_dir, model_save_path=None, n_neighbors=None, knn_algo='ball_tree', verbose=False):
    X = []
    y = []

    # Loop through each person in the training set
    for class_dir in os.listdir(train_dir):
        if not os.path.isdir(os.path.join(train_dir, class_dir)):
            continue

        # Loop through each training image for the current person
        for img_path in image_files_in_folder(os.path.join(train_dir, class_dir)):
            image = face_recognition.load_image_file(img_path)
            face_bounding_boxes = face_recognition.face_locations(image)

            if len(face_bounding_boxes) != 1:
                # If there are no people (or too many people) in a training image, skip the image.
                if verbose:
                    print("Image {} not suitable for training: {}".format(img_path, "Didn't find a face" if len(face_bounding_boxes) < 1 else "Found more than one face"))
            else:
                # Add face encoding for current image to the training set
                X.append(face_recognition.face_encodings(image, known_face_locations=face_bounding_boxes)[0])
                y.append(class_dir)

    # Determine how many neighbors to use for weighting in the KNN classifier
    if n_neighbors is None:
        n_neighbors = int(round(math.sqrt(len(X))))
        if verbose:
            print("Chose n_neighbors automatically:", n_neighbors)

    # Create and train the KNN classifier
    knn_clf = neighbors.KNeighborsClassifier(n_neighbors=n_neighbors, algorithm=knn_algo, weights='distance')
    knn_clf.fit(X, y)

    # Save the trained KNN classifier
    if model_save_path is not None:
        with open(model_save_path, 'wb') as f:
            pickle.dump(knn_clf, f)

    return knn_clf

def predict(X_img_path, knn_clf=None, model_path=None, distance_threshold=0.6):
    # if not os.path.isfile(X_img_path) or os.path.splitext(X_img_path)[1][1:] not in ALLOWED_EXTENSIONS:
        # raise Exception("Invalid image path: {}".format(X_img_path))

    if knn_clf is None and model_path is None:
        raise Exception("Must supply knn classifier either thourgh knn_clf or model_path")

    # Load a trained KNN model (if one was passed in)
    if knn_clf is None:
        with open(model_path, 'rb') as f:
            knn_clf = pickle.load(f)

    # Load image file and find face locations
    # X_img = face_recognition.load_image_file(X_img_path)
    X_face_locations = face_recognition.face_locations(X_img_path)

    # If no faces are found in the image, return an empty result.
    if len(X_face_locations) == 0:
        return []

    # Find encodings for faces in the test iamge
    faces_encodings = face_recognition.face_encodings(X_img_path, known_face_locations=X_face_locations)

    # Use the KNN model to find the best matches for the test face
    closest_distances = knn_clf.kneighbors(faces_encodings, n_neighbors=1)
    are_matches = [closest_distances[0][i][0] <= distance_threshold for i in range(len(X_face_locations))]

    # Predict classes and remove classifications that aren't within the threshold
    return [(pred, loc) if rec else ("unknown", loc) for pred, loc, rec in zip(knn_clf.predict(faces_encodings), X_face_locations, are_matches)]

# def show_prediction_labels_on_image(img_path, predictions):
    pil_image = Image.open(img_path).convert("RGB")
    draw = ImageDraw.Draw(pil_image)

    for name, (top, right, bottom, left) in predictions:
        # Draw a box around the face using the Pillow module
        draw.rectangle(((left, top), (right, bottom)), outline=(0, 0, 255))

        # There's a bug in Pillow where it blows up with non-UTF-8 text
        # when using the default bitmap font
        name = name.encode("UTF-8")

        # Draw a label with a name below the face
        text_width, text_height = draw.textsize(name)
        draw.rectangle(((left, bottom - text_height - 10), (right, bottom)), fill=(0, 0, 255), outline=(0, 0, 255))
        draw.text((left + 6, bottom - text_height - 5), name, fill=(255, 255, 255, 255))

    # Remove the drawing library from memory as per the Pillow docs
    del draw

    # Display the resulting image
    pil_image.show()

if __name__ == "__main__":
    # print("Training KNN classifier...")
      classifier = train("knn_examples/train", model_save_path="trained_knn_model.clf", n_neighbors=2)
    # print("Training complete!")

    video_capture = cv2.VideoCapture(0)

    while True:
        ret, frame = video_capture.read()
        rgb_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)

        # Find all people in the image using a trained classifier model
        # Note: You can pass in either a classifier file name or a classifier model instance
        predictions = predict(X_img_path=rgb_frame, model_path="trained_knn_model.clf")

        for name, (top, right, bottom, left) in predictions:
            cv2.rectangle(frame, (left, top), (right, bottom), (0, 0, 255), 2)

            # 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

# Release handle to the webcam
video_capture.release()
cv2.destroyAllWindows()

[fadi212]

What I see is you would have to change the Predict function for video. I will work on that but try changing that.

[fadi212]

By the way, can you please tell me how many images you used per class and how did you collect those images ?

[shiveksachdev]

By the way, can you please tell me how many images you used per class and how did you collect those images ?

It's actually working with the code I pasted. Thanks :)