new file: PreProcessing/.gitignore

new file:   PreProcessing/README.md
	new file:   PreProcessing/scripts/compare_manual_matrix17.py
	new file:   PreProcessing/scripts/draw_matrix17.py
	modified:   PreProcessing/scripts/process_characters.py
	new file:   PreProcessing/scripts/run_preprocessing.py

PreProcessing/.gitignore

@@ -0,0 +1,14 @@
+# Generated preprocessing outputs
+comparisons/
+manual_diffs/
+manual_matrices/
+original_characters/
+processed_characters/
+svg_characters/
+out_cleaned/
+out_matrix/
+
+# Local caches
+.matplotlib-cache/
+scripts/__pycache__/
+*.pyc

PreProcessing/README.md

@@ -0,0 +1,49 @@
+# PreProcessing 预处理
+
+这个目录包含17*17型特殊种类篆文字图像的预处理流程。日常批量处理请使用 `scripts/run_preprocessing.py`。
+
+## 脚本用法
+
+依赖见 `scripts/requirements.txt`。如果环境里还没有安装，可以先运行：
+
+```bash
+.venv/bin/pip install -r PreProcessing/scripts/requirements.txt
+```
+
+从项目根目录运行：
+
+```bash
+.venv/bin/python PreProcessing/scripts/run_preprocessing.py \
+  --input-dir PreProcessing/original_characters \
+  --cleaned-dir PreProcessing/out_cleaned \
+  --matrix-dir PreProcessing/out_matrix
+```
+
+参数含义：
+
+- `--input-dir`：原始图像输入文件夹
+- `--cleaned-dir`：cleaned 二值图输出文件夹
+- `--matrix-dir`：17x17 矩阵文本输出文件夹
+
+输出命名会和输入文件名对齐：
+
+- cleaned 图像：`原文件名_cleaned.png`
+- 矩阵文本：`原文件名_matrix.txt`
+
+矩阵文本是纯 17 行，每行 17 个字符，只包含 `0` 和 `1`。
+
+## 可选调参
+
+默认参数会输出 17x17 矩阵。必要时可以追加这些参数：
+
+- `--grid-size`，默认 `17`
+- `--cell-samples`，默认 `32`
+- `--open-kernel-size`
+- `--close-kernel-size`
+- `--median-size`
+- `--min-component-area`
+- `--triangle-threshold`
+
+## 目录说明
+
+`comparisons/`、`manual_diffs/`、`manual_matrices/`、`processed_characters/`、`svg_characters/` 等测试和比较用目录已经在 `PreProcessing/.gitignore` 中忽略。

PreProcessing/scripts/compare_manual_matrix17.py

@@ -0,0 +1,237 @@
+from __future__ import annotations
+
+import argparse
+from dataclasses import dataclass
+from pathlib import Path
+
+import cv2
+import numpy as np
+
+
+GRID_SIZE = 17
+
+
+@dataclass(frozen=True)
+class MatrixMetrics:
+    stem: str
+    true_positive: int
+    false_positive: int
+    false_negative: int
+    manual_cells: int
+    generated_cells: int
+    manual_2x2: int
+    generated_2x2: int
+
+    @property
+    def precision(self) -> float:
+        denominator = self.true_positive + self.false_positive
+        return self.true_positive / denominator if denominator else 1.0
+
+    @property
+    def recall(self) -> float:
+        denominator = self.true_positive + self.false_negative
+        return self.true_positive / denominator if denominator else 1.0
+
+    @property
+    def f1(self) -> float:
+        denominator = self.precision + self.recall
+        return 2.0 * self.precision * self.recall / denominator if denominator else 0.0
+
+
+def read_matrix(path: Path) -> np.ndarray:
+    rows: list[str] = []
+    for line in path.read_text(encoding="utf-8").splitlines():
+        stripped = line.strip()
+        if not stripped or stripped.startswith("#"):
+            continue
+        rows.append(stripped)
+        if len(rows) == GRID_SIZE:
+            break
+
+    if len(rows) != GRID_SIZE:
+        raise ValueError(f"{path} has {len(rows)} matrix rows, expected {GRID_SIZE}")
+
+    matrix = np.zeros((GRID_SIZE, GRID_SIZE), dtype=np.uint8)
+    for row_index, row_text in enumerate(rows):
+        if len(row_text) < GRID_SIZE:
+            raise ValueError(
+                f"{path} row {row_index + 1} has {len(row_text)} columns, "
+                f"expected {GRID_SIZE}"
+            )
+        for col_index, char in enumerate(row_text[:GRID_SIZE]):
+            matrix[row_index, col_index] = 1 if char == "1" else 0
+
+    return matrix
+
+
+def count_2x2_blocks(matrix: np.ndarray) -> int:
+    total = 0
+    for row in range(GRID_SIZE - 1):
+        for col in range(GRID_SIZE - 1):
+            total += int(matrix[row : row + 2, col : col + 2].sum() == 4)
+    return total
+
+
+def diff_image(manual: np.ndarray, generated: np.ndarray, scale: int) -> np.ndarray:
+    both = (manual == 1) & (generated == 1)
+    false_positive = (manual == 0) & (generated == 1)
+    false_negative = (manual == 1) & (generated == 0)
+
+    image = np.full((GRID_SIZE, GRID_SIZE, 3), 255, dtype=np.uint8)
+    image[both] = (0, 0, 0)
+    image[false_positive] = (40, 40, 220)
+    image[false_negative] = (220, 80, 40)
+    return cv2.resize(image, (GRID_SIZE * scale, GRID_SIZE * scale), interpolation=cv2.INTER_NEAREST)
+
+
+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 metrics_for_pair(manual_path: Path, generated_path: Path) -> MatrixMetrics:
+    manual = read_matrix(manual_path)
+    generated = read_matrix(generated_path)
+    true_positive = int(((manual == 1) & (generated == 1)).sum())
+    false_positive = int(((manual == 0) & (generated == 1)).sum())
+    false_negative = int(((manual == 1) & (generated == 0)).sum())
+    stem = manual_path.name.removesuffix("_matrix17.txt")
+    return MatrixMetrics(
+        stem=stem,
+        true_positive=true_positive,
+        false_positive=false_positive,
+        false_negative=false_negative,
+        manual_cells=int(manual.sum()),
+        generated_cells=int(generated.sum()),
+        manual_2x2=count_2x2_blocks(manual),
+        generated_2x2=count_2x2_blocks(generated),
+    )
+
+
+def print_table(metrics: list[MatrixMetrics]) -> None:
+    header = (
+        "stem",
+        "P",
+        "R",
+        "F1",
+        "TP",
+        "FP",
+        "FN",
+        "manual",
+        "gen",
+        "manual_2x2",
+        "gen_2x2",
+    )
+    print(
+        f"{header[0]:42} {header[1]:>6} {header[2]:>6} {header[3]:>6} "
+        f"{header[4]:>4} {header[5]:>4} {header[6]:>4} {header[7]:>6} "
+        f"{header[8]:>6} {header[9]:>11} {header[10]:>8}"
+    )
+    for item in metrics:
+        print(
+            f"{item.stem:42} {item.precision:6.3f} {item.recall:6.3f} {item.f1:6.3f} "
+            f"{item.true_positive:4d} {item.false_positive:4d} {item.false_negative:4d} "
+            f"{item.manual_cells:6d} {item.generated_cells:6d} "
+            f"{item.manual_2x2:11d} {item.generated_2x2:8d}"
+        )
+
+    total_tp = sum(item.true_positive for item in metrics)
+    total_fp = sum(item.false_positive for item in metrics)
+    total_fn = sum(item.false_negative for item in metrics)
+    total_manual = sum(item.manual_cells for item in metrics)
+    total_generated = sum(item.generated_cells for item in metrics)
+    total_manual_2x2 = sum(item.manual_2x2 for item in metrics)
+    total_generated_2x2 = sum(item.generated_2x2 for item in metrics)
+    total = MatrixMetrics(
+        stem="TOTAL",
+        true_positive=total_tp,
+        false_positive=total_fp,
+        false_negative=total_fn,
+        manual_cells=total_manual,
+        generated_cells=total_generated,
+        manual_2x2=total_manual_2x2,
+        generated_2x2=total_generated_2x2,
+    )
+    print("-" * 113)
+    print(
+        f"{total.stem:42} {total.precision:6.3f} {total.recall:6.3f} {total.f1:6.3f} "
+        f"{total.true_positive:4d} {total.false_positive:4d} {total.false_negative:4d} "
+        f"{total.manual_cells:6d} {total.generated_cells:6d} "
+        f"{total.manual_2x2:11d} {total.generated_2x2:8d}"
+    )
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(
+        description="Compare manual 17x17 labels against generated matrix output."
+    )
+    parser.add_argument(
+        "--manual-dir",
+        type=Path,
+        default=Path("PreProcessing/manual_matrices"),
+    )
+    parser.add_argument(
+        "--generated-dir",
+        type=Path,
+        default=Path("PreProcessing/processed_characters"),
+    )
+    parser.add_argument(
+        "--diff-dir",
+        type=Path,
+        default=Path("PreProcessing/manual_diffs"),
+    )
+    parser.add_argument("--scale", type=int, default=24)
+    parser.add_argument(
+        "--include-empty-manual",
+        action="store_true",
+        help="Include manual matrices with no black cells instead of treating them as unlabelled.",
+    )
+    args = parser.parse_args()
+
+    manual_paths = sorted(args.manual_dir.glob("*_matrix17.txt"))
+    if not manual_paths:
+        raise SystemExit(f"No manual matrices found in {args.manual_dir}")
+
+    args.diff_dir.mkdir(parents=True, exist_ok=True)
+    metrics: list[MatrixMetrics] = []
+    missing: list[Path] = []
+    skipped_empty: list[Path] = []
+
+    for manual_path in manual_paths:
+        manual = read_matrix(manual_path)
+        if not args.include_empty_manual and int(manual.sum()) == 0:
+            skipped_empty.append(manual_path)
+            continue
+
+        generated_path = args.generated_dir / manual_path.name
+        if not generated_path.exists():
+            missing.append(generated_path)
+            continue
+
+        generated = read_matrix(generated_path)
+        metrics.append(metrics_for_pair(manual_path, generated_path))
+        stem = manual_path.name.removesuffix("_matrix17.txt")
+        write_image(args.diff_dir / f"{stem}_diff.png", diff_image(manual, generated, args.scale))
+
+    if missing:
+        print("Missing generated matrices:")
+        for path in missing:
+            print(f"  {path}")
+
+    if skipped_empty:
+        print("Skipped empty manual matrices:")
+        for path in skipped_empty:
+            print(f"  {path}")
+
+    if not metrics:
+        raise SystemExit("No comparable matrix pairs found.")
+
+    print_table(metrics)
+    print(f"\nDiff images written to: {args.diff_dir}")
+    print("Diff colors: black=match, red=generated extra, blue=manual missing.")
+
+
+if __name__ == "__main__":
+    main()

PreProcessing/scripts/draw_matrix17.py

@@ -0,0 +1,364 @@
+from __future__ import annotations
+
+import argparse
+from pathlib import Path
+import tkinter as tk
+from tkinter import messagebox
+
+import cv2
+import numpy as np
+
+
+IMAGE_SUFFIXES = {".png", ".jpg", ".jpeg", ".tif", ".tiff", ".bmp", ".webp"}
+GRID_SIZE = 17
+CELL_SIZE = 28
+PREVIEW_SIZE = 560
+
+
+def read_image(path: Path) -> np.ndarray:
+    raw = np.fromfile(str(path), dtype=np.uint8)
+    image = cv2.imdecode(raw, cv2.IMREAD_COLOR)
+    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 matrix_to_text(matrix: np.ndarray) -> str:
+    lines = []
+    for row in matrix:
+        lines.append("".join("1" if value else "0" for value in row))
+    return "\n".join(lines) + "\n"
+
+
+def text_to_matrix(path: Path) -> np.ndarray:
+    matrix = np.zeros((GRID_SIZE, GRID_SIZE), dtype=np.uint8)
+    if not path.exists():
+        return matrix
+
+    rows = []
+    for line in path.read_text(encoding="utf-8").splitlines():
+        stripped = line.strip()
+        if not stripped or stripped.startswith("#"):
+            continue
+        rows.append(stripped)
+        if len(rows) == GRID_SIZE:
+            break
+
+    for row_index, row_text in enumerate(rows[:GRID_SIZE]):
+        for col_index, char in enumerate(row_text[:GRID_SIZE]):
+            matrix[row_index, col_index] = 1 if char == "1" else 0
+
+    return matrix
+
+
+def matrix_to_png(matrix: np.ndarray, scale: int = 24) -> np.ndarray:
+    image = np.where(matrix > 0, 0, 255).astype(np.uint8)
+    return cv2.resize(
+        image,
+        (GRID_SIZE * scale, GRID_SIZE * scale),
+        interpolation=cv2.INTER_NEAREST,
+    )
+
+
+class MatrixEditor:
+    def __init__(
+        self,
+        root: tk.Tk,
+        image_paths: list[Path],
+        output_dir: Path,
+        load_generated_dir: Path | None,
+    ) -> None:
+        self.root = root
+        self.image_paths = image_paths
+        self.output_dir = output_dir
+        self.load_generated_dir = load_generated_dir
+        self.output_dir.mkdir(parents=True, exist_ok=True)
+
+        self.index = 0
+        self.matrix = np.zeros((GRID_SIZE, GRID_SIZE), dtype=np.uint8)
+        self.paint_value = 1
+        self.preview_photo: tk.PhotoImage | None = None
+        self.preview_temp = Path("/private/tmp/matrix17_editor_preview.png")
+
+        self.root.title("17x17 Matrix Editor")
+        self._build_ui()
+        self._bind_keys()
+        self.load_current_image()
+
+    @property
+    def image_path(self) -> Path:
+        return self.image_paths[self.index]
+
+    @property
+    def answer_path(self) -> Path:
+        return self.output_dir / f"{self.image_path.stem}_matrix17.txt"
+
+    @property
+    def answer_png_path(self) -> Path:
+        return self.output_dir / f"{self.image_path.stem}_matrix17.png"
+
+    def _build_ui(self) -> None:
+        main = tk.Frame(self.root)
+        main.pack(fill=tk.BOTH, expand=True, padx=10, pady=10)
+
+        left = tk.Frame(main)
+        left.pack(side=tk.LEFT, fill=tk.BOTH, expand=True)
+        right = tk.Frame(main)
+        right.pack(side=tk.LEFT, fill=tk.Y, padx=(12, 0))
+
+        self.preview_canvas = tk.Canvas(
+            left,
+            width=PREVIEW_SIZE,
+            height=PREVIEW_SIZE,
+            bg="white",
+            highlightthickness=1,
+            highlightbackground="#999",
+        )
+        self.preview_canvas.pack(fill=tk.BOTH, expand=True)
+
+        self.grid_canvas = tk.Canvas(
+            right,
+            width=GRID_SIZE * CELL_SIZE + 1,
+            height=GRID_SIZE * CELL_SIZE + 1,
+            bg="white",
+            highlightthickness=1,
+            highlightbackground="#777",
+        )
+        self.grid_canvas.pack()
+        self.grid_canvas.bind("<Button-1>", self._on_left_click)
+        self.grid_canvas.bind("<B1-Motion>", self._on_left_drag)
+        self.grid_canvas.bind("<Button-3>", self._on_right_click)
+        self.grid_canvas.bind("<B3-Motion>", self._on_right_drag)
+
+        buttons = tk.Frame(right)
+        buttons.pack(fill=tk.X, pady=(10, 0))
+
+        tk.Button(buttons, text="上一张", command=self.prev_image).grid(
+            row=0, column=0, sticky="ew", padx=2, pady=2
+        )
+        tk.Button(buttons, text="下一张", command=self.next_image).grid(
+            row=0, column=1, sticky="ew", padx=2, pady=2
+        )
+        tk.Button(buttons, text="保存", command=self.save_answer).grid(
+            row=1, column=0, sticky="ew", padx=2, pady=2
+        )
+        tk.Button(buttons, text="清空", command=self.clear_matrix).grid(
+            row=1, column=1, sticky="ew", padx=2, pady=2
+        )
+        tk.Button(buttons, text="载入生成结果", command=self.load_generated).grid(
+            row=2, column=0, columnspan=2, sticky="ew", padx=2, pady=2
+        )
+
+        buttons.columnconfigure(0, weight=1)
+        buttons.columnconfigure(1, weight=1)
+
+        self.status = tk.Label(right, text="", anchor="w", justify="left")
+        self.status.pack(fill=tk.X, pady=(8, 0))
+
+    def _bind_keys(self) -> None:
+        self.root.bind("<Left>", lambda _event: self.prev_image())
+        self.root.bind("<Right>", lambda _event: self.next_image())
+        self.root.bind("s", lambda _event: self.save_answer())
+        self.root.bind("S", lambda _event: self.save_answer())
+        self.root.bind("c", lambda _event: self.clear_matrix())
+        self.root.bind("C", lambda _event: self.clear_matrix())
+        self.root.bind("1", lambda _event: self.set_paint_value(1))
+        self.root.bind("0", lambda _event: self.set_paint_value(0))
+
+    def set_paint_value(self, value: int) -> None:
+        self.paint_value = 1 if value else 0
+        self._update_status()
+
+    def load_current_image(self) -> None:
+        self.matrix = text_to_matrix(self.answer_path)
+        self._draw_preview()
+        self._draw_grid()
+        self._update_status()
+
+    def _draw_preview(self) -> None:
+        image = read_image(self.image_path)
+        height, width = image.shape[:2]
+        scale = min(PREVIEW_SIZE / height, PREVIEW_SIZE / width)
+        new_width = max(1, int(round(width * scale)))
+        new_height = max(1, int(round(height * scale)))
+        resized = cv2.resize(image, (new_width, new_height), interpolation=cv2.INTER_NEAREST)
+
+        canvas = np.full((PREVIEW_SIZE, PREVIEW_SIZE, 3), 255, dtype=np.uint8)
+        x = (PREVIEW_SIZE - new_width) // 2
+        y = (PREVIEW_SIZE - new_height) // 2
+        canvas[y : y + new_height, x : x + new_width] = resized
+        write_image(self.preview_temp, canvas)
+        self.preview_photo = tk.PhotoImage(file=str(self.preview_temp))
+        self.preview_canvas.delete("all")
+        self.preview_canvas.create_image(0, 0, anchor="nw", image=self.preview_photo)
+
+    def _draw_grid(self) -> None:
+        self.grid_canvas.delete("all")
+        for row in range(GRID_SIZE):
+            for col in range(GRID_SIZE):
+                x1 = col * CELL_SIZE
+                y1 = row * CELL_SIZE
+                x2 = x1 + CELL_SIZE
+                y2 = y1 + CELL_SIZE
+                fill = "black" if self.matrix[row, col] else "white"
+                self.grid_canvas.create_rectangle(
+                    x1,
+                    y1,
+                    x2,
+                    y2,
+                    fill=fill,
+                    outline="#888",
+                )
+
+        for index in range(GRID_SIZE + 1):
+            pos = index * CELL_SIZE
+            width = 2 if index in (0, GRID_SIZE) else 1
+            self.grid_canvas.create_line(0, pos, GRID_SIZE * CELL_SIZE, pos, fill="#555", width=width)
+            self.grid_canvas.create_line(pos, 0, pos, GRID_SIZE * CELL_SIZE, fill="#555", width=width)
+
+    def _grid_cell_from_event(self, event: tk.Event) -> tuple[int, int] | None:
+        col = int(event.x // CELL_SIZE)
+        row = int(event.y // CELL_SIZE)
+        if 0 <= row < GRID_SIZE and 0 <= col < GRID_SIZE:
+            return row, col
+        return None
+
+    def _set_cell_from_event(self, event: tk.Event, value: int) -> None:
+        cell = self._grid_cell_from_event(event)
+        if cell is None:
+            return
+        row, col = cell
+        if self.matrix[row, col] == value:
+            return
+        self.matrix[row, col] = value
+        self._draw_grid()
+        self._update_status()
+
+    def _on_left_click(self, event: tk.Event) -> None:
+        cell = self._grid_cell_from_event(event)
+        if cell is None:
+            return
+        row, col = cell
+        self.paint_value = 0 if self.matrix[row, col] else 1
+        self.matrix[row, col] = self.paint_value
+        self._draw_grid()
+        self._update_status()
+
+    def _on_left_drag(self, event: tk.Event) -> None:
+        self._set_cell_from_event(event, self.paint_value)
+
+    def _on_right_click(self, event: tk.Event) -> None:
+        self.paint_value = 0
+        self._set_cell_from_event(event, 0)
+        self._update_status()
+
+    def _on_right_drag(self, event: tk.Event) -> None:
+        self._set_cell_from_event(event, 0)
+
+    def save_answer(self) -> None:
+        self.answer_path.write_text(matrix_to_text(self.matrix), encoding="utf-8")
+        write_image(self.answer_png_path, matrix_to_png(self.matrix))
+        self._update_status(saved=True)
+
+    def clear_matrix(self) -> None:
+        self.matrix[:, :] = 0
+        self._draw_grid()
+        self._update_status()
+
+    def load_generated(self) -> None:
+        if self.load_generated_dir is None:
+            messagebox.showinfo("提示", "未配置生成结果目录")
+            return
+
+        path = self.load_generated_dir / f"{self.image_path.stem}_matrix17.txt"
+        if not path.exists():
+            messagebox.showinfo("提示", f"找不到生成结果：\n{path}")
+            return
+
+        self.matrix = text_to_matrix(path)
+        self._draw_grid()
+        self._update_status()
+
+    def prev_image(self) -> None:
+        self.save_answer()
+        self.index = (self.index - 1) % len(self.image_paths)
+        self.load_current_image()
+
+    def next_image(self) -> None:
+        self.save_answer()
+        self.index = (self.index + 1) % len(self.image_paths)
+        self.load_current_image()
+
+    def _update_status(self, saved: bool = False) -> None:
+        filled = int(self.matrix.sum())
+        two_by_two = count_2x2_blocks(self.matrix)
+        saved_text = "已保存\n" if saved else ""
+        self.status.config(
+            text=(
+                f"{saved_text}"
+                f"{self.index + 1}/{len(self.image_paths)}\n"
+                f"{self.image_path.name}\n"
+                f"黑格：{filled}\n"
+                f"2x2 全黑：{two_by_two}\n"
+                f"左键：切换/拖拽绘制\n"
+                f"右键：擦除\n"
+                f"S 保存，←/→ 切换"
+            )
+        )
+
+
+def count_2x2_blocks(matrix: np.ndarray) -> int:
+    image = matrix > 0
+    total = 0
+    for row in range(GRID_SIZE - 1):
+        for col in range(GRID_SIZE - 1):
+            total += int(image[row : row + 2, col : col + 2].sum() == 4)
+    return total
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(description="Draw manual 17x17 matrix labels.")
+    parser.add_argument(
+        "--input-dir",
+        type=Path,
+        default=Path("PreProcessing/original_characters"),
+    )
+    parser.add_argument(
+        "--output-dir",
+        type=Path,
+        default=Path("PreProcessing/manual_matrices"),
+    )
+    parser.add_argument(
+        "--load-generated-dir",
+        type=Path,
+        default=Path("PreProcessing/processed_characters"),
+    )
+    args = parser.parse_args()
+
+    image_paths = sorted(
+        path
+        for path in args.input_dir.iterdir()
+        if path.is_file() and path.suffix.lower() in IMAGE_SUFFIXES
+    )
+    if not image_paths:
+        raise SystemExit(f"No images found in {args.input_dir}")
+
+    root = tk.Tk()
+    MatrixEditor(
+        root=root,
+        image_paths=image_paths,
+        output_dir=args.output_dir,
+        load_generated_dir=args.load_generated_dir,
+    )
+    root.mainloop()
+
+
+if __name__ == "__main__":
+    main()

PreProcessing/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()

PreProcessing/svg_characters/篆文字_page_017_text_17_pixelated.svg

@@ -3,141 +3,55 @@
   <title>篆文字_page_017_text_17</title>
   <rect width="100%" height="100%" fill="white"/>
   <g fill="black">
-    <rect x="45.0638" y="30.3182" width="15.0213" height="15.1591"/>
+    <rect x="29.0000" y="25.0000" width="304.0000" height="36.0000"/>
-    <rect x="165.2340" y="30.3182" width="15.0213" height="15.1591"/>
+    <rect x="371.0000" y="25.0000" width="304.0000" height="36.0000"/>
-    <rect x="390.5532" y="30.3182" width="285.4043" height="15.1591"/>
+    <rect x="29.0000" y="61.0000" width="38.0000" height="36.0000"/>
-    <rect x="45.0638" y="45.4773" width="300.4255" height="15.1591"/>
+    <rect x="637.0000" y="61.0000" width="38.0000" height="36.0000"/>
-    <rect x="390.5532" y="45.4773" width="285.4043" height="15.1591"/>
+    <rect x="29.0000" y="97.0000" width="304.0000" height="36.0000"/>
-    <rect x="45.0638" y="60.6364" width="285.4043" height="15.1591"/>
+    <rect x="371.0000" y="97.0000" width="304.0000" height="36.0000"/>
-    <rect x="390.5532" y="60.6364" width="15.0213" height="15.1591"/>
+    <rect x="29.0000" y="133.0000" width="38.0000" height="36.0000"/>
-    <rect x="630.8936" y="60.6364" width="45.0638" height="15.1591"/>
+    <rect x="295.0000" y="133.0000" width="38.0000" height="36.0000"/>
-    <rect x="45.0638" y="75.7955" width="30.0426" height="15.1591"/>
+    <rect x="371.0000" y="133.0000" width="38.0000" height="36.0000"/>
-    <rect x="630.8936" y="75.7955" width="45.0638" height="15.1591"/>
+    <rect x="29.0000" y="169.0000" width="304.0000" height="37.0000"/>
-    <rect x="45.0638" y="90.9545" width="30.0426" height="15.1591"/>
+    <rect x="371.0000" y="169.0000" width="38.0000" height="37.0000"/>
-    <rect x="510.7234" y="90.9545" width="165.2340" height="15.1591"/>
+    <rect x="447.0000" y="169.0000" width="228.0000" height="37.0000"/>
-    <rect x="45.0638" y="106.1136" width="300.4255" height="15.1591"/>
+    <rect x="29.0000" y="206.0000" width="38.0000" height="36.0000"/>
-    <rect x="390.5532" y="106.1136" width="285.4043" height="15.1591"/>
+    <rect x="371.0000" y="206.0000" width="38.0000" height="36.0000"/>
-    <rect x="45.0638" y="121.2727" width="300.4255" height="15.1591"/>
+    <rect x="447.0000" y="206.0000" width="38.0000" height="36.0000"/>
-    <rect x="390.5532" y="121.2727" width="240.3404" height="15.1591"/>
+    <rect x="637.0000" y="206.0000" width="38.0000" height="36.0000"/>
-    <rect x="645.9149" y="121.2727" width="30.0426" height="15.1591"/>
+    <rect x="29.0000" y="242.0000" width="304.0000" height="36.0000"/>
-    <rect x="30.0426" y="136.4318" width="45.0638" height="15.1591"/>
+    <rect x="371.0000" y="242.0000" width="38.0000" height="36.0000"/>
-    <rect x="300.4255" y="136.4318" width="45.0638" height="15.1591"/>
+    <rect x="447.0000" y="242.0000" width="38.0000" height="36.0000"/>
-    <rect x="390.5532" y="136.4318" width="30.0426" height="15.1591"/>
+    <rect x="523.0000" y="242.0000" width="152.0000" height="36.0000"/>
-    <rect x="480.6809" y="136.4318" width="15.0213" height="15.1591"/>
+    <rect x="295.0000" y="278.0000" width="38.0000" height="36.0000"/>
-    <rect x="30.0426" y="151.5909" width="45.0638" height="15.1591"/>
+    <rect x="371.0000" y="278.0000" width="38.0000" height="36.0000"/>
-    <rect x="300.4255" y="151.5909" width="30.0426" height="15.1591"/>
+    <rect x="447.0000" y="278.0000" width="38.0000" height="36.0000"/>
-    <rect x="375.5319" y="151.5909" width="45.0638" height="15.1591"/>
+    <rect x="29.0000" y="314.0000" width="304.0000" height="36.0000"/>
-    <rect x="30.0426" y="166.7500" width="315.4468" height="15.1591"/>
+    <rect x="371.0000" y="314.0000" width="38.0000" height="36.0000"/>
-    <rect x="375.5319" y="166.7500" width="45.0638" height="15.1591"/>
+    <rect x="447.0000" y="314.0000" width="228.0000" height="36.0000"/>
-    <rect x="465.6596" y="166.7500" width="210.2979" height="15.1591"/>
+    <rect x="29.0000" y="350.0000" width="38.0000" height="36.0000"/>
-    <rect x="30.0426" y="181.9091" width="300.4255" height="15.1591"/>
+    <rect x="371.0000" y="350.0000" width="38.0000" height="36.0000"/>
-    <rect x="375.5319" y="181.9091" width="45.0638" height="15.1591"/>
+    <rect x="637.0000" y="350.0000" width="38.0000" height="36.0000"/>
-    <rect x="450.6383" y="181.9091" width="225.3191" height="15.1591"/>
+    <rect x="29.0000" y="386.0000" width="304.0000" height="36.0000"/>
-    <rect x="30.0426" y="197.0682" width="45.0638" height="15.1591"/>
+    <rect x="371.0000" y="386.0000" width="38.0000" height="36.0000"/>
-    <rect x="90.1277" y="197.0682" width="30.0426" height="15.1591"/>
+    <rect x="447.0000" y="386.0000" width="228.0000" height="36.0000"/>
-    <rect x="210.2979" y="197.0682" width="60.0851" height="15.1591"/>
+    <rect x="295.0000" y="422.0000" width="38.0000" height="36.0000"/>
-    <rect x="375.5319" y="197.0682" width="45.0638" height="15.1591"/>
+    <rect x="371.0000" y="422.0000" width="38.0000" height="36.0000"/>
-    <rect x="450.6383" y="197.0682" width="45.0638" height="15.1591"/>
+    <rect x="447.0000" y="422.0000" width="38.0000" height="36.0000"/>
-    <rect x="630.8936" y="197.0682" width="45.0638" height="15.1591"/>
+    <rect x="29.0000" y="458.0000" width="304.0000" height="37.0000"/>
-    <rect x="30.0426" y="212.2273" width="45.0638" height="15.1591"/>
+    <rect x="371.0000" y="458.0000" width="38.0000" height="37.0000"/>
-    <rect x="375.5319" y="212.2273" width="45.0638" height="15.1591"/>
+    <rect x="447.0000" y="458.0000" width="228.0000" height="37.0000"/>
-    <rect x="450.6383" y="212.2273" width="45.0638" height="15.1591"/>
+    <rect x="29.0000" y="495.0000" width="38.0000" height="36.0000"/>
-    <rect x="630.8936" y="212.2273" width="45.0638" height="15.1591"/>
+    <rect x="371.0000" y="495.0000" width="38.0000" height="36.0000"/>
-    <rect x="30.0426" y="227.3864" width="75.1064" height="15.1591"/>
+    <rect x="637.0000" y="495.0000" width="38.0000" height="36.0000"/>
-    <rect x="375.5319" y="227.3864" width="45.0638" height="15.1591"/>
+    <rect x="29.0000" y="531.0000" width="304.0000" height="36.0000"/>
-    <rect x="450.6383" y="227.3864" width="45.0638" height="15.1591"/>
+    <rect x="371.0000" y="531.0000" width="38.0000" height="36.0000"/>
-    <rect x="630.8936" y="227.3864" width="45.0638" height="15.1591"/>
+    <rect x="447.0000" y="531.0000" width="228.0000" height="36.0000"/>
-    <rect x="30.0426" y="242.5455" width="300.4255" height="15.1591"/>
+    <rect x="295.0000" y="567.0000" width="38.0000" height="36.0000"/>
-    <rect x="375.5319" y="242.5455" width="45.0638" height="15.1591"/>
+    <rect x="371.0000" y="567.0000" width="38.0000" height="36.0000"/>
-    <rect x="450.6383" y="242.5455" width="45.0638" height="15.1591"/>
+    <rect x="447.0000" y="567.0000" width="38.0000" height="36.0000"/>
-    <rect x="525.7447" y="242.5455" width="150.2128" height="15.1591"/>
+    <rect x="29.0000" y="603.0000" width="304.0000" height="36.0000"/>
-    <rect x="30.0426" y="257.7045" width="300.4255" height="15.1591"/>
+    <rect x="371.0000" y="603.0000" width="38.0000" height="36.0000"/>
-    <rect x="375.5319" y="257.7045" width="45.0638" height="15.1591"/>
+    <rect x="447.0000" y="603.0000" width="228.0000" height="36.0000"/>
-    <rect x="450.6383" y="257.7045" width="45.0638" height="15.1591"/>
-    <rect x="525.7447" y="257.7045" width="150.2128" height="15.1591"/>
-    <rect x="300.4255" y="272.8636" width="30.0426" height="15.1591"/>
-    <rect x="375.5319" y="272.8636" width="45.0638" height="15.1591"/>
-    <rect x="450.6383" y="272.8636" width="45.0638" height="15.1591"/>
-    <rect x="300.4255" y="288.0227" width="30.0426" height="15.1591"/>
-    <rect x="375.5319" y="288.0227" width="45.0638" height="15.1591"/>
-    <rect x="450.6383" y="288.0227" width="45.0638" height="15.1591"/>
-    <rect x="30.0426" y="303.1818" width="30.0426" height="15.1591"/>
-    <rect x="300.4255" y="303.1818" width="30.0426" height="15.1591"/>
-    <rect x="375.5319" y="303.1818" width="45.0638" height="15.1591"/>
-    <rect x="450.6383" y="303.1818" width="45.0638" height="15.1591"/>
-    <rect x="510.7234" y="303.1818" width="165.2340" height="15.1591"/>
-    <rect x="30.0426" y="318.3409" width="300.4255" height="15.1591"/>
-    <rect x="375.5319" y="318.3409" width="45.0638" height="15.1591"/>
-    <rect x="450.6383" y="318.3409" width="225.3191" height="15.1591"/>
-    <rect x="30.0426" y="333.5000" width="255.3617" height="15.1591"/>
-    <rect x="315.4468" y="333.5000" width="15.0213" height="15.1591"/>
-    <rect x="375.5319" y="333.5000" width="45.0638" height="15.1591"/>
-    <rect x="450.6383" y="333.5000" width="165.2340" height="15.1591"/>
-    <rect x="630.8936" y="333.5000" width="45.0638" height="15.1591"/>
-    <rect x="30.0426" y="348.6591" width="45.0638" height="15.1591"/>
-    <rect x="375.5319" y="348.6591" width="45.0638" height="15.1591"/>
-    <rect x="630.8936" y="348.6591" width="45.0638" height="15.1591"/>
-    <rect x="30.0426" y="363.8182" width="45.0638" height="15.1591"/>
-    <rect x="375.5319" y="363.8182" width="45.0638" height="15.1591"/>
-    <rect x="630.8936" y="363.8182" width="45.0638" height="15.1591"/>
-    <rect x="30.0426" y="378.9773" width="45.0638" height="15.1591"/>
-    <rect x="90.1277" y="378.9773" width="15.0213" height="15.1591"/>
-    <rect x="300.4255" y="378.9773" width="30.0426" height="15.1591"/>
-    <rect x="375.5319" y="378.9773" width="30.0426" height="15.1591"/>
-    <rect x="540.7660" y="378.9773" width="135.1915" height="15.1591"/>
-    <rect x="30.0426" y="394.1364" width="300.4255" height="15.1591"/>
-    <rect x="375.5319" y="394.1364" width="45.0638" height="15.1591"/>
-    <rect x="450.6383" y="394.1364" width="225.3191" height="15.1591"/>
-    <rect x="30.0426" y="409.2955" width="300.4255" height="15.1591"/>
-    <rect x="375.5319" y="409.2955" width="30.0426" height="15.1591"/>
-    <rect x="450.6383" y="409.2955" width="120.1702" height="15.1591"/>
-    <rect x="285.4043" y="424.4545" width="45.0638" height="15.1591"/>
-    <rect x="375.5319" y="424.4545" width="45.0638" height="15.1591"/>
-    <rect x="465.6596" y="424.4545" width="30.0426" height="15.1591"/>
-    <rect x="285.4043" y="439.6136" width="45.0638" height="15.1591"/>
-    <rect x="375.5319" y="439.6136" width="45.0638" height="15.1591"/>
-    <rect x="465.6596" y="439.6136" width="30.0426" height="15.1591"/>
-    <rect x="30.0426" y="454.7727" width="300.4255" height="15.1591"/>
-    <rect x="375.5319" y="454.7727" width="30.0426" height="15.1591"/>
-    <rect x="465.6596" y="454.7727" width="210.2979" height="15.1591"/>
-    <rect x="30.0426" y="469.9318" width="300.4255" height="15.1591"/>
-    <rect x="375.5319" y="469.9318" width="30.0426" height="15.1591"/>
-    <rect x="465.6596" y="469.9318" width="210.2979" height="15.1591"/>
-    <rect x="30.0426" y="485.0909" width="45.0638" height="15.1591"/>
-    <rect x="150.2128" y="485.0909" width="120.1702" height="15.1591"/>
-    <rect x="285.4043" y="485.0909" width="30.0426" height="15.1591"/>
-    <rect x="360.5106" y="485.0909" width="45.0638" height="15.1591"/>
-    <rect x="465.6596" y="485.0909" width="210.2979" height="15.1591"/>
-    <rect x="30.0426" y="500.2500" width="45.0638" height="15.1591"/>
-    <rect x="375.5319" y="500.2500" width="30.0426" height="15.1591"/>
-    <rect x="630.8936" y="500.2500" width="45.0638" height="15.1591"/>
-    <rect x="30.0426" y="515.4091" width="45.0638" height="15.1591"/>
-    <rect x="375.5319" y="515.4091" width="30.0426" height="15.1591"/>
-    <rect x="645.9149" y="515.4091" width="30.0426" height="15.1591"/>
-    <rect x="30.0426" y="530.5682" width="285.4043" height="15.1591"/>
-    <rect x="360.5106" y="530.5682" width="45.0638" height="15.1591"/>
-    <rect x="465.6596" y="530.5682" width="210.2979" height="15.1591"/>
-    <rect x="30.0426" y="545.7273" width="300.4255" height="15.1591"/>
-    <rect x="360.5106" y="545.7273" width="45.0638" height="15.1591"/>
-    <rect x="465.6596" y="545.7273" width="210.2979" height="15.1591"/>
-    <rect x="150.2128" y="560.8864" width="15.0213" height="15.1591"/>
-    <rect x="225.3191" y="560.8864" width="30.0426" height="15.1591"/>
-    <rect x="270.3830" y="560.8864" width="60.0851" height="15.1591"/>
-    <rect x="360.5106" y="560.8864" width="45.0638" height="15.1591"/>
-    <rect x="465.6596" y="560.8864" width="30.0426" height="15.1591"/>
-    <rect x="285.4043" y="576.0455" width="45.0638" height="15.1591"/>
-    <rect x="360.5106" y="576.0455" width="45.0638" height="15.1591"/>
-    <rect x="465.6596" y="576.0455" width="30.0426" height="15.1591"/>
-    <rect x="30.0426" y="591.2045" width="15.0213" height="15.1591"/>
-    <rect x="90.1277" y="591.2045" width="60.0851" height="15.1591"/>
-    <rect x="165.2340" y="591.2045" width="165.2340" height="15.1591"/>
-    <rect x="360.5106" y="591.2045" width="45.0638" height="15.1591"/>
-    <rect x="450.6383" y="591.2045" width="225.3191" height="15.1591"/>
-    <rect x="30.0426" y="606.3636" width="300.4255" height="15.1591"/>
-    <rect x="360.5106" y="606.3636" width="45.0638" height="15.1591"/>
-    <rect x="450.6383" y="606.3636" width="225.3191" height="15.1591"/>
-    <rect x="30.0426" y="621.5227" width="285.4043" height="15.1591"/>
-    <rect x="360.5106" y="621.5227" width="45.0638" height="15.1591"/>
-    <rect x="450.6383" y="621.5227" width="225.3191" height="15.1591"/>
   </g>
 </svg>