MatrixZhuan Preprosessing Scripts 1.0

PreProcessing_MatrixZhuan/scripts/run_preprocessing.py

@@ -0,0 +1,143 @@
+from __future__ import annotations
+
+import argparse
+from pathlib import Path
+
+import cv2
+import numpy as np
+
+from process_characters import (
+    IMAGE_SUFFIXES,
+    binarize_foreground,
+    clean_mask,
+    matrix_map,
+    mask_to_display,
+    read_image,
+    write_image,
+)
+
+
+def matrix_to_text(matrix: np.ndarray) -> str:
+    return "\n".join(
+        "".join("1" if value > 0 else "0" for value in row) for row in matrix
+    ) + "\n"
+
+
+def iter_image_paths(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 process_image(
+    image_path: Path,
+    cleaned_dir: Path,
+    matrix_dir: Path,
+    grid_size: int = 17,
+    cell_samples: int = 32,
+    open_kernel_size: int = 1,
+    close_kernel_size: int = 0,
+    median_size: int = 1,
+    min_component_area: int = 8,
+    triangle_threshold: float = 0.18,
+) -> None:
+    original = read_image(image_path)
+    gray = cv2.cvtColor(original, cv2.COLOR_BGR2GRAY)
+    binary = binarize_foreground(gray)
+    cleaned = clean_mask(
+        binary,
+        open_kernel_size=open_kernel_size,
+        close_kernel_size=close_kernel_size,
+        median_size=median_size,
+        min_component_area=min_component_area,
+        grid_size=grid_size,
+    )
+    mapping = matrix_map(
+        cleaned,
+        grid_size=grid_size,
+        triangle_threshold=triangle_threshold,
+        cell_samples=cell_samples,
+    )
+
+    stem = image_path.stem
+    write_image(cleaned_dir / f"{stem}_cleaned.png", mask_to_display(cleaned))
+    (matrix_dir / f"{stem}_matrix.txt").write_text(
+        matrix_to_text(mapping.matrix),
+        encoding="utf-8",
+    )
+
+
+def process_directory(
+    input_dir: Path,
+    cleaned_dir: Path,
+    matrix_dir: Path,
+    grid_size: int = 17,
+    cell_samples: int = 32,
+    open_kernel_size: int = 1,
+    close_kernel_size: int = 0,
+    median_size: int = 1,
+    min_component_area: int = 8,
+    triangle_threshold: float = 0.18,
+) -> int:
+    cleaned_dir.mkdir(parents=True, exist_ok=True)
+    matrix_dir.mkdir(parents=True, exist_ok=True)
+
+    image_paths = iter_image_paths(input_dir)
+    if not image_paths:
+        raise SystemExit(f"No images found in {input_dir}")
+
+    for image_path in image_paths:
+        process_image(
+            image_path=image_path,
+            cleaned_dir=cleaned_dir,
+            matrix_dir=matrix_dir,
+            grid_size=grid_size,
+            cell_samples=cell_samples,
+            open_kernel_size=open_kernel_size,
+            close_kernel_size=close_kernel_size,
+            median_size=median_size,
+            min_component_area=min_component_area,
+            triangle_threshold=triangle_threshold,
+        )
+        print(f"processed: {image_path.name}")
+
+    return len(image_paths)
+
+
+def build_parser() -> argparse.ArgumentParser:
+    parser = argparse.ArgumentParser(
+        description="Clean seal-script images and export 17x17 matrix text files."
+    )
+    parser.add_argument("--input-dir", type=Path, required=True)
+    parser.add_argument("--cleaned-dir", type=Path, required=True)
+    parser.add_argument("--matrix-dir", type=Path, required=True)
+    parser.add_argument("--grid-size", type=int, default=17)
+    parser.add_argument("--cell-samples", type=int, default=32)
+    parser.add_argument("--open-kernel-size", type=int, default=1)
+    parser.add_argument("--close-kernel-size", type=int, default=0)
+    parser.add_argument("--median-size", type=int, default=1)
+    parser.add_argument("--min-component-area", type=int, default=8)
+    parser.add_argument("--triangle-threshold", type=float, default=0.18)
+    return parser
+
+
+def main() -> None:
+    args = build_parser().parse_args()
+    process_directory(
+        input_dir=args.input_dir,
+        cleaned_dir=args.cleaned_dir,
+        matrix_dir=args.matrix_dir,
+        grid_size=args.grid_size,
+        cell_samples=args.cell_samples,
+        open_kernel_size=args.open_kernel_size,
+        close_kernel_size=args.close_kernel_size,
+        median_size=args.median_size,
+        min_component_area=args.min_component_area,
+        triangle_threshold=args.triangle_threshold,
+    )
+
+
+if __name__ == "__main__":
+    main()