CommonZhuan Preprocessing Scripts 1.0

PreProcessing_MatrixZhuan/.gitignore

@@ -7,6 +7,7 @@ processed_characters/
 svg_characters/
 out_cleaned/
 out_matrix/
+out_svg/
 
 # Local caches
 .matplotlib-cache/

PreProcessing_MatrixZhuan/README.md

@@ -7,16 +7,17 @@
 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
+.venv/bin/pip install -r PreProcessing_MatrixZhuan/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
+.venv/bin/python PreProcessing_MatrixZhuan/scripts/run_preprocessing.py \
+  --input-dir PreProcessing_MatrixZhuan/original_characters \
+  --cleaned-dir PreProcessing_MatrixZhuan/out_cleaned \
+  --matrix-dir PreProcessing_MatrixZhuan/out_matrix \
+  --svg-dir PreProcessing_MatrixZhuan/out_svg
 ```
 
 参数含义：
@@ -24,11 +25,13 @@
 - `--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
+- `--svg-dir`：矢量图 SVG 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`
+- 矢量图：`原文件名.svg`
 
 矩阵文本是纯 17 行，每行 17 个字符，只包含 `0` 和 `1`。
 
@@ -46,4 +49,4 @@
 
 ## 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。
+`comparisons/`、`manual_diffs/`、`manual_matrices/`、`processed_characters/`、`svg_characters/` 等测试和比较用目录已经在 `PreProcessing_MatrixZhuan/.gitignore` 中忽略。

PreProcessing_MatrixZhuan/scripts/run_preprocessing.py

@@ -13,6 +13,7 @@ from process_characters import (
     matrix_map,
     mask_to_display,
     read_image,
+    small_matrix_to_svg,
     write_image,
 )
 
@@ -35,6 +36,7 @@ def process_image(
     image_path: Path,
     cleaned_dir: Path,
     matrix_dir: Path,
+    svg_dir: Path,
     grid_size: int = 17,
     cell_samples: int = 32,
     open_kernel_size: int = 1,
@@ -67,12 +69,24 @@ def process_image(
         matrix_to_text(mapping.matrix),
         encoding="utf-8",
     )
+    height, width = gray.shape
+    svg = small_matrix_to_svg(
+        mapping.matrix,
+        width,
+        height,
+        stem,
+        mapping.x_edges,
+        mapping.y_edges,
+        mapping.triangles,
+    )
+    (svg_dir / f"{stem}.svg").write_text(svg, encoding="utf-8")
 
 
 def process_directory(
     input_dir: Path,
     cleaned_dir: Path,
     matrix_dir: Path,
+    svg_dir: Path,
     grid_size: int = 17,
     cell_samples: int = 32,
     open_kernel_size: int = 1,
@@ -83,6 +97,7 @@ def process_directory(
 ) -> int:
     cleaned_dir.mkdir(parents=True, exist_ok=True)
     matrix_dir.mkdir(parents=True, exist_ok=True)
+    svg_dir.mkdir(parents=True, exist_ok=True)
 
     image_paths = iter_image_paths(input_dir)
     if not image_paths:
@@ -93,6 +108,7 @@ def process_directory(
             image_path=image_path,
             cleaned_dir=cleaned_dir,
             matrix_dir=matrix_dir,
+            svg_dir=svg_dir,
             grid_size=grid_size,
             cell_samples=cell_samples,
             open_kernel_size=open_kernel_size,
@@ -113,6 +129,7 @@ def build_parser() -> argparse.ArgumentParser:
     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("--svg-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)
@@ -129,6 +146,7 @@ def main() -> None:
         input_dir=args.input_dir,
         cleaned_dir=args.cleaned_dir,
         matrix_dir=args.matrix_dir,
+        svg_dir=args.svg_dir,
         grid_size=args.grid_size,
         cell_samples=args.cell_samples,
         open_kernel_size=args.open_kernel_size,