Files
agent/skills/document-photo-to-pdf/doc_deskew/homography.py
T
kicer a86b748a6f 重构 document-photo-to-pdf:审核页改为 data.db 驱动并支持一键重生成
run.py 接上 edits/enhance/dpi/status/review,并把运行记录写进会话 data.db;审核页模板移到 skill/web,运行时发布到 .app/doc-review/,页面通过 /api/db 水合并调用通用技能执行接口重生成;移除 make_review.py 与模板注入。
2026-10-23 23:15:52 +08:00

90 lines
3.3 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
# -*- coding: utf-8 -*-
"""纯 numpy 单应变换:等价于 cv2.warpPerspective,只依赖 Pillow + numpy。
与旧实现的区别:
- 按行分块采样,峰值内存从“整页 × 多份 float64”降到几十 MB;
- 只接受 PIL 图,坐标/方向由调用方统一(exif_transpose 已在入口做过);
- 不再提供 CLI,出件统一走技能入口。
"""
import numpy as np
from PIL import Image
def _solve_h(src, dst):
A = []
for (x, y), (u, v) in zip(src, dst):
A.append([x, y, 1, 0, 0, 0, -u * x, -u * y, -u])
A.append([0, 0, 0, x, y, 1, -v * x, -v * y, -v])
_, _, vt = np.linalg.svd(np.asarray(A, dtype=np.float64))
return vt[-1].reshape(3, 3)
def warp_perspective(img, quad, out_size=None, fill=(255, 255, 255),
chunk_rows=256):
"""把 quad 指定的四边形透视校正到 out_size。
quad 顺序:左上、右上、右下、左下(屏幕坐标)。
out_size=None 时按四边形自然边长输出(保留照片原始比例)。
"""
arr = np.asarray(img if img.mode == "RGB" else img.convert("RGB"))
src_h, src_w = arr.shape[:2]
quad = np.asarray(quad, dtype=np.float64)
tl, tr, br, bl = quad
if out_size is None:
w = int(round(max(np.linalg.norm(tr - tl), np.linalg.norm(br - bl))))
h = int(round(max(np.linalg.norm(bl - tl), np.linalg.norm(br - tr))))
out_size = (w, h)
out_w = max(1, int(out_size[0]))
out_h = max(1, int(out_size[1]))
dst = np.array([[0, 0], [out_w - 1, 0],
[out_w - 1, out_h - 1], [0, out_h - 1]],
dtype=np.float64)
Hinv = np.linalg.inv(_solve_h(quad, dst))
out = np.empty((out_h, out_w, 3), dtype=np.uint8)
step = max(1, int(chunk_rows))
for y0 in range(0, out_h, step):
y1 = min(y0 + step, out_h)
ys, xs = np.mgrid[y0:y1, 0:out_w]
dst_h = np.stack([xs.ravel(), ys.ravel(),
np.ones(xs.size)], axis=0).astype(np.float64)
sp = Hinv @ dst_h
den = sp[2]
den = np.where(np.abs(den) < 1e-9, 1e-9, den)
sx = sp[0] / den
sy = sp[1] / den
valid = (sx >= 0) & (sx <= src_w - 1) & (sy >= 0) & (sy <= src_h - 1)
sx = np.clip(sx, 0, src_w - 1)
sy = np.clip(sy, 0, src_h - 1)
x0 = np.floor(sx).astype(np.int32)
x1 = np.minimum(x0 + 1, src_w - 1)
y0i = np.floor(sy).astype(np.int32)
y1i = np.minimum(y0i + 1, src_h - 1)
fx = (sx - x0)[:, None]
fy = (sy - y0i)[:, None]
a = arr[y0i, x0].astype(np.float32)
b = arr[y0i, x1].astype(np.float32)
c = arr[y1i, x0].astype(np.float32)
d = arr[y1i, x1].astype(np.float32)
block = (a * (1 - fx) * (1 - fy) + b * fx * (1 - fy)
+ c * (1 - fx) * fy + d * fx * fy)
block[~valid] = fill
out[y0:y1] = np.clip(block, 0, 255).astype(np.uint8).reshape(
y1 - y0, out_w, 3)
return Image.fromarray(out)
def brighten(img, target=245, pct=97):
"""全局等比提亮:把 pct 分位映射到 target,保持相对对比度。"""
arr = np.asarray(img if img.mode == "RGB" else img.convert("RGB")).astype(np.float32)
hi = float(np.percentile(arr, pct))
if hi > 1.0:
arr = np.clip(arr * (float(target) / hi), 0, 255)
return Image.fromarray(arr.astype(np.uint8))