uniface/tools/landmarks.py

# Copyright 2025-2026 Yakhyokhuja Valikhujaev
# Author: Yakhyokhuja Valikhujaev
# GitHub: https://github.com/yakhyo

"""106-point facial landmark detection.

Usage:
    python tools/landmarks.py --source path/to/image.jpg
    python tools/landmarks.py --source path/to/video.mp4
    python tools/landmarks.py --source 0  # webcam
"""

from __future__ import annotations

import argparse
import os
from pathlib import Path

from _common import get_source_type
import cv2

from uniface.detection import SCRFD, RetinaFace
from uniface.landmark import Landmark106


def process_image(detector, landmarker, image_path: str, save_dir: str = 'outputs'):
    """Process a single image."""
    image = cv2.imread(image_path)
    if image is None:
        print(f"Error: Failed to load image from '{image_path}'")
        return

    faces = detector.detect(image)
    print(f'Detected {len(faces)} face(s)')

    if not faces:
        return

    for i, face in enumerate(faces):
        bbox = face.bbox
        x1, y1, x2, y2 = map(int, bbox)
        cv2.rectangle(image, (x1, y1), (x2, y2), (0, 255, 0), 2)

        landmarks = landmarker.get_landmarks(image, bbox)
        print(f'  Face {i + 1}: {len(landmarks)} landmarks')

        for x, y in landmarks.astype(int):
            cv2.circle(image, (x, y), 1, (0, 255, 0), -1)

        cv2.putText(image, f'Face {i + 1}', (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)

    os.makedirs(save_dir, exist_ok=True)
    output_path = os.path.join(save_dir, f'{Path(image_path).stem}_landmarks.jpg')
    cv2.imwrite(output_path, image)
    print(f'Output saved: {output_path}')


def process_video(detector, landmarker, video_path: str, save_dir: str = 'outputs'):
    """Process a video file."""
    cap = cv2.VideoCapture(video_path)
    if not cap.isOpened():
        print(f"Error: Cannot open video file '{video_path}'")
        return

    fps = cap.get(cv2.CAP_PROP_FPS)
    width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
    height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
    total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))

    os.makedirs(save_dir, exist_ok=True)
    output_path = os.path.join(save_dir, f'{Path(video_path).stem}_landmarks.mp4')
    fourcc = cv2.VideoWriter_fourcc(*'mp4v')
    out = cv2.VideoWriter(output_path, fourcc, fps, (width, height))

    print(f'Processing video: {video_path} ({total_frames} frames)')
    frame_count = 0

    while True:
        ret, frame = cap.read()
        if not ret:
            break

        frame_count += 1
        faces = detector.detect(frame)

        for face in faces:
            bbox = face.bbox
            x1, y1, x2, y2 = map(int, bbox)
            cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 255, 0), 2)

            landmarks = landmarker.get_landmarks(frame, bbox)
            for x, y in landmarks.astype(int):
                cv2.circle(frame, (x, y), 1, (0, 255, 0), -1)

        cv2.putText(frame, f'Faces: {len(faces)}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
        out.write(frame)

        if frame_count % 100 == 0:
            print(f'  Processed {frame_count}/{total_frames} frames...')

    cap.release()
    out.release()
    print(f'Done! Output saved: {output_path}')


def run_camera(detector, landmarker, camera_id: int = 0):
    """Run real-time detection on webcam."""
    cap = cv2.VideoCapture(camera_id)
    if not cap.isOpened():
        print(f'Cannot open camera {camera_id}')
        return

    print("Press 'q' to quit")

    while True:
        ret, frame = cap.read()
        if not ret:
            break
        frame = cv2.flip(frame, 1)

        faces = detector.detect(frame)

        for face in faces:
            bbox = face.bbox
            x1, y1, x2, y2 = map(int, bbox)
            cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 255, 0), 2)

            landmarks = landmarker.get_landmarks(frame, bbox)
            for x, y in landmarks.astype(int):
                cv2.circle(frame, (x, y), 1, (0, 255, 0), -1)

        cv2.putText(frame, f'Faces: {len(faces)}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
        cv2.imshow('106-Point Landmarks', frame)

        if cv2.waitKey(1) & 0xFF == ord('q'):
            break

    cap.release()
    cv2.destroyAllWindows()


def main():
    parser = argparse.ArgumentParser(description='Run facial landmark detection')
    parser.add_argument('--source', type=str, required=True, help='Image/video path or camera ID (0, 1, ...)')
    parser.add_argument('--detector', type=str, default='retinaface', choices=['retinaface', 'scrfd'])
    parser.add_argument('--save-dir', type=str, default='outputs', help='Output directory')
    args = parser.parse_args()

    detector = RetinaFace() if args.detector == 'retinaface' else SCRFD()
    landmarker = Landmark106()

    source_type = get_source_type(args.source)

    if source_type == 'camera':
        run_camera(detector, landmarker, int(args.source))
    elif source_type == 'image':
        if not os.path.exists(args.source):
            print(f'Error: Image not found: {args.source}')
            return
        process_image(detector, landmarker, args.source, args.save_dir)
    elif source_type == 'video':
        if not os.path.exists(args.source):
            print(f'Error: Video not found: {args.source}')
            return
        process_video(detector, landmarker, args.source, args.save_dir)
    else:
        print(f"Error: Unknown source type for '{args.source}'")
        print('Supported formats: images (.jpg, .png, ...), videos (.mp4, .avi, ...), or camera ID (0, 1, ...)')


if __name__ == '__main__':
    main()