CommonZhuan Preprocessing Scripts 1.0

PreProcessing_Common/scripts/make_clean_comparisons.py

@@ -0,0 +1,164 @@
+from __future__ import annotations
+
+import argparse
+from pathlib import Path
+
+import cv2
+import numpy as np
+
+
+IMAGE_SUFFIXES = {".png", ".jpg", ".jpeg", ".tif", ".tiff", ".bmp", ".webp"}
+
+
+def read_gray(path: Path) -> np.ndarray:
+    raw = np.fromfile(str(path), dtype=np.uint8)
+    image = cv2.imdecode(raw, cv2.IMREAD_GRAYSCALE)
+    if image is None:
+        raise ValueError(f"Cannot read image: {path}")
+    return image
+
+
+def write_image(path: Path, image: np.ndarray) -> None:
+    ok, encoded = cv2.imencode(path.suffix, image)
+    if not ok:
+        raise ValueError(f"Cannot encode image: {path}")
+    encoded.tofile(str(path))
+
+
+def fit_on_canvas(image: np.ndarray, width: int, height: int) -> np.ndarray:
+    scale = min(width / image.shape[1], height / image.shape[0])
+    resized_width = max(1, int(round(image.shape[1] * scale)))
+    resized_height = max(1, int(round(image.shape[0] * scale)))
+    resized = cv2.resize(
+        image,
+        (resized_width, resized_height),
+        interpolation=cv2.INTER_AREA,
+    )
+    canvas = np.full((height, width), 255, dtype=np.uint8)
+    x = (width - resized_width) // 2
+    y = (height - resized_height) // 2
+    canvas[y : y + resized_height, x : x + resized_width] = resized
+    return canvas
+
+
+def make_comparison(
+    original_path: Path,
+    cleaned_path: Path,
+    output_path: Path,
+    panel_size: int,
+    label_height: int,
+) -> None:
+    original = read_gray(original_path)
+    cleaned = read_gray(cleaned_path)
+    panel_width = panel_size
+    panel_height = panel_size
+
+    original_panel = fit_on_canvas(original, panel_width, panel_height)
+    cleaned_panel = fit_on_canvas(cleaned, panel_width, panel_height)
+    divider = np.full((panel_height + label_height, 2), 210, dtype=np.uint8)
+    comparison = np.full(
+        (panel_height + label_height, panel_width * 2 + divider.shape[1]),
+        255,
+        dtype=np.uint8,
+    )
+    comparison[:panel_height, :panel_width] = original_panel
+    comparison[:panel_height, panel_width + divider.shape[1] :] = cleaned_panel
+    comparison[:, panel_width : panel_width + divider.shape[1]] = divider
+
+    baseline = panel_height + 24
+    cv2.putText(
+        comparison,
+        "original",
+        (12, baseline),
+        cv2.FONT_HERSHEY_SIMPLEX,
+        0.7,
+        0,
+        2,
+        cv2.LINE_AA,
+    )
+    cv2.putText(
+        comparison,
+        "cleaned",
+        (panel_width + divider.shape[1] + 12, baseline),
+        cv2.FONT_HERSHEY_SIMPLEX,
+        0.7,
+        0,
+        2,
+        cv2.LINE_AA,
+    )
+    cv2.putText(
+        comparison,
+        original_path.stem,
+        (12, panel_height + label_height - 12),
+        cv2.FONT_HERSHEY_SIMPLEX,
+        0.45,
+        80,
+        1,
+        cv2.LINE_AA,
+    )
+    write_image(output_path, comparison)
+
+
+def iter_originals(input_dir: Path) -> list[Path]:
+    return sorted(
+        path
+        for path in input_dir.iterdir()
+        if path.is_file() and path.suffix.lower() in IMAGE_SUFFIXES
+    )
+
+
+def build_parser() -> argparse.ArgumentParser:
+    parser = argparse.ArgumentParser(
+        description="Create side-by-side original/cleaned comparison images."
+    )
+    parser.add_argument(
+        "--original-dir",
+        type=Path,
+        default=Path("PreProcessing_Common/original_characters"),
+    )
+    parser.add_argument(
+        "--cleaned-dir",
+        type=Path,
+        default=Path("PreProcessing_Common/cleaned_characters"),
+    )
+    parser.add_argument(
+        "--output-dir",
+        type=Path,
+        default=Path("PreProcessing_Common/comparisons"),
+    )
+    parser.add_argument("--panel-size", type=int, default=520)
+    parser.add_argument("--label-height", type=int, default=72)
+    return parser
+
+
+def main() -> None:
+    args = build_parser().parse_args()
+    args.output_dir.mkdir(parents=True, exist_ok=True)
+
+    originals = iter_originals(args.original_dir)
+    if not originals:
+        raise SystemExit(f"No images found in {args.original_dir}")
+
+    count = 0
+    for original_path in originals:
+        cleaned_path = args.cleaned_dir / f"{original_path.stem}_cleaned.png"
+        if not cleaned_path.exists():
+            print(f"missing cleaned image: {cleaned_path}")
+            continue
+
+        make_comparison(
+            original_path=original_path,
+            cleaned_path=cleaned_path,
+            output_path=args.output_dir / f"{original_path.stem}_comparison.png",
+            panel_size=args.panel_size,
+            label_height=args.label_height,
+        )
+        print(f"comparison: {original_path.name}")
+        count += 1
+
+    if count == 0:
+        raise SystemExit("No comparisons were written.")
+
+
+if __name__ == "__main__":
+    main()