클로드 코드로 영상 속 얼굴 블러·모자이크하는 법

brew install ffmpeg uv

curl -L -o face_detection_yunet_2023mar.onnx "https://github.com/opencv/opencv_zoo/raw/main/models/face_detection_yunet/face_detection_yunet_2023mar.onnx"

ffmpeg -ss 144 -to 184 -i interview.webm -c:v libx264 -crf 18 -preset medium -pix_fmt yuv420p -c:a aac -b:a 160k -movflags +faststart clip.mp4

ffmpeg -nostats -i clip.mp4 -an -vf "select='gt(scene,0.3)',metadata=print:file=-" -f null - 2>/dev/null | grep pts_time

ffmpeg -i clip.mp4 -filter_complex "[0:v]crop=100:160:484:220,boxblur=20:3[face];[0:v][face]overlay=484:220" \  -c:v libx264 -crf 18 -pix_fmt yuv420p -c:a copy -movflags +faststart box.mp4

"""Find the faces in every frame of a video and mark the one wearing yellow.Usage: faces.py clip.mp4 faces.json"""import jsonimport sysimport cv2import numpy as npsrc, out = sys.argv[1], sys.argv[2]video = cv2.VideoCapture(src)width = int(video.get(cv2.CAP_PROP_FRAME_WIDTH))height = int(video.get(cv2.CAP_PROP_FRAME_HEIGHT))detector = cv2.FaceDetectorYN.create(    "face_detection_yunet_2023mar.onnx", "", (width, height), score_threshold=0.6)def shirt(frame, x, y, w, h):    """Median hue and saturation of the area under the face, where the shirt is."""    top, bottom = min(height, y + int(h * 1.3)), min(height, y + int(h * 2.3))    left, right = max(0, x), min(width, x + w)    if bottom <= top or right <= left:        return 0, 0    hsv = cv2.cvtColor(frame[top:bottom, left:right], cv2.COLOR_BGR2HSV)    return int(np.median(hsv[..., 0])), int(np.median(hsv[..., 1]))frames = []while True:    ok, frame = video.read()    if not ok:        break    _, found = detector.detect(frame)    faces = []    for face in found if found is not None else []:        x, y, w, h = (int(v) for v in face[:4])        hue, sat = shirt(frame, x, y, w, h)        faces.append(            {                "box": [x, y, w, h],                "score": round(float(face[14]), 2),                "yellow": 20 <= hue <= 35 and sat >= 100,            }        )    frames.append(faces)json.dump({"width": width, "height": height, "frames": frames}, open(out, "w"))counts = {}for faces in frames:    key = (len(faces), sum(f["yellow"] for f in faces))    counts[key] = counts.get(key, 0) + 1print(f"{len(frames)} frames")for (n, yellow), count in sorted(counts.items()):    print(f"  {count:4} frames: {n} face(s), {yellow} in yellow")

uv run --with opencv-python-headless faces.py clip.mp4 faces.json

"""Hide the face in yellow: follow it through faces.json and blur or pixelate it.Usage: hide.py clip.mp4 faces.json blur|pixelate out.mp4 85,692,931The last argument is the frames where the shot changes; a box never carries across one."""import jsonimport subprocessimport sysimport cv2import numpy as npsrc, faces_path, style, out = sys.argv[1:5]cuts = {int(f) for f in sys.argv[5].split(",")}data = json.load(open(faces_path))width, height = data["width"], data["height"]HOLD = 12  # frames to keep the last box when the face isn't foundPAD = 0.35  # grow the box by this much of its size on every sideSMOOTH = 2  # average each box with this many frames on either sidedef center(box):    x, y, w, h = box    return x + w / 2, y + h / 2# 1. Pick the face in yellow in each frame, nearest to where it was before.track, last, missed, held = [], None, 0, 0for i, faces in enumerate(data["frames"]):    if i in cuts:        last = None    yellow = [f["box"] for f in faces if f["yellow"]]    if last is not None and yellow:        lx, ly = center(last)        yellow.sort(key=lambda b: (center(b)[0] - lx) ** 2 + (center(b)[1] - ly) ** 2)    if yellow:        last, missed = yellow[0], 0    elif last is not None and missed < HOLD:        missed += 1        held += 1    else:        last = None    track.append(last)# 2. Smooth the boxes so the cover doesn't jitter, without crossing a cut.smoothed = []for i, box in enumerate(track):    if box is None:        smoothed.append(None)        continue    lo = max([0] + [c for c in cuts if c <= i])    hi = min([len(track)] + [c for c in cuts if c > i])    near = [b for b in track[max(lo, i - SMOOTH) : min(hi, i + SMOOTH + 1)] if b is not None]    smoothed.append([sum(b[k] for b in near) / len(near) for k in range(4)])covered = sum(b is not None for b in smoothed)print(f"{covered} of {len(smoothed)} frames covered, {held} held from the frame before")def hide(frame, box):    x, y, w, h = box    x0, y0 = max(0, int(x - w * PAD)), max(0, int(y - h * PAD))    x1, y1 = min(width, int(x + w * (1 + PAD))), min(height, int(y + h * (1 + PAD)))    region = frame[y0:y1, x0:x1]    rw, rh = x1 - x0, y1 - y0    if style == "pixelate":        cells = 8  # blocks across the face, whatever its size        small = cv2.resize(region, (cells, max(1, rh * cells // rw)), interpolation=cv2.INTER_AREA)        frame[y0:y1, x0:x1] = cv2.resize(small, (rw, rh), interpolation=cv2.INTER_NEAREST)        return    k = max(3, (rw // 2) | 1)    blurred = cv2.GaussianBlur(region, (k, k), 0)    mask = np.zeros((rh, rw), np.float32)    cv2.ellipse(mask, (rw // 2, rh // 2), (rw // 2, rh // 2), 0, 0, 360, 1.0, -1)    mask = cv2.GaussianBlur(mask, (0, 0), rw / 20)[..., None]    frame[y0:y1, x0:x1] = (blurred * mask + region * (1 - mask)).astype(np.uint8)# 3. Draw each frame and hand it to ffmpeg, which adds the original sound.encoder = subprocess.Popen(    ["ffmpeg", "-v", "error", "-y", "-f", "rawvideo", "-pix_fmt", "bgr24",     "-s", f"{width}x{height}", "-r", "25", "-i", "-", "-i", src,     "-map", "0:v", "-map", "1:a", "-c:v", "libx264", "-crf", "18", "-pix_fmt", "yuv420p",     "-c:a", "copy", "-movflags", "+faststart", out],    stdin=subprocess.PIPE,)video = cv2.VideoCapture(src)for box in smoothed:    ok, frame = video.read()    if not ok:        break    if box is not None:        hide(frame, box)    encoder.stdin.write(frame.tobytes())encoder.stdin.close()encoder.wait()

for style in blur pixelate; do  uv run --with opencv-python-headless hide.py clip.mp4 faces.json $style $style.mp4 85,692,931done

ffmpeg -v error -i blur.mp4 -vf "select='between(n,692,930)*not(mod(n-692,10))',scale=320:-2,tile=6x4" -frames:v 1 -fps_mode vfr close-tiles.png

Footage: "Interview on extreme weather with physical geographer Hannah Cloke" by the Royal Society, CC BY 3.0, cut, and the interviewer's face blurredLicense: https://creativecommons.org/licenses/by/3.0/