arianvanp

    1. Estimate the background's global motion between consecutive frames
       with phase correlation (this is the "optical flow" step - the motion
       is a pure translation, so one global vector suffices).
    2. Motion-compensate: shift frame t+1 back by that vector so the
       background lines up with frame t.
    3. Take the absolute difference. The background cancels almost
       perfectly; the letters (which don't move with the background)
       light up.
    4. Average the residual over a SHORT window of consecutive frame pairs
       (long windows smear the letters, because the text itself drifts
       slowly over time), blur lightly, and threshold with Otsu.

    frames = load_gray_frames(src, START_FRAME + PAIRS + 1)
    h, w = frames[0].shape
    acc = np.zeros((h, w), np.float32)

    for i in range(START_FRAME, START_FRAME + PAIRS):
        a, b = frames[i], frames[i + 1]

        # 1) global background motion between the two frames
        (dx, dy), response = cv2.phaseCorrelate(a, b)
        dxi, dyi = int(round(dx)), int(round(dy))
        print(f"pair {i}: background shift = ({dx:+.2f}, {dy:+.2f}) px, "
              f"response = {response:.2f}")

        # 2) motion-compensate frame b by integer (dxi, dyi), then
        # 3) residual = |a - b_shifted| on the overlapping region
        ys = slice(max(0, -dyi), min(h, h - dyi))
        xs = slice(max(0, -dxi), min(w, w - dxi))
        ysb = slice(max(0, dyi), min(h, h + dyi) if dyi < 0 else h)
        # simpler: crop both to the common overlap
        a_ov = a[max(0, -dyi):h - max(0, dyi), max(0, -dxi):w - max(0, dxi)]
        b_ov = b[max(0, dyi):h - max(0, -dyi), max(0, dxi):w - max(0, -dxi)]
        resid = cv2.GaussianBlur(np.abs(a_ov - b_ov), (0, 0), BLUR_SIGMA)
        acc[:resid.shape[0], :resid.shape[1]] += resid

    # 4) normalize + Otsu threshold + light cleanup
    u8 = cv2.normalize(acc, None, 0, 255, cv2.NORM_MINMAX).astype(np.uint8)
    _, mask = cv2.threshold(u8, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
    kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (5, 5))
    mask = cv2.morphologyEx(mask, cv2.MORPH_CLOSE, kernel)

    out = 255 - mask  # black text on white
    cv2.imwrite(dst, out)
    print(f"wrote {dst}")

    # optional: OCR if pytesseract is installed
    try:
        import pytesseract
        text = pytesseract.image_to_string(out, config="--psm 6").strip()
        print("OCR result:\n" + text)
    except ImportError:
        pass