From deb622095f3568f202141541d907d6c53fc80de1 Mon Sep 17 00:00:00 2001 From: kicer Date: Thu, 22 Oct 2026 22:11:33 +0800 Subject: [PATCH] =?UTF-8?q?=E8=87=AA=E5=8A=A8=E8=AF=86=E5=88=AB=E8=BE=B9?= =?UTF-8?q?=E6=A1=86?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- skills/document-photo-to-pdf/SKILL.md | 26 +- .../doc_deskew/auto_quad.py | 500 ++++++++++++++++++ .../document-photo-to-pdf/doc_deskew/grid.py | 11 +- .../doc_deskew/pipeline.py | 72 ++- .../doc_deskew/prepare.py | 94 ++++ .../doc_deskew/preview_quad.py | 12 +- 6 files changed, 682 insertions(+), 33 deletions(-) create mode 100644 skills/document-photo-to-pdf/doc_deskew/auto_quad.py create mode 100644 skills/document-photo-to-pdf/doc_deskew/prepare.py diff --git a/skills/document-photo-to-pdf/SKILL.md b/skills/document-photo-to-pdf/SKILL.md index b62f3fb..6a42572 100644 --- a/skills/document-photo-to-pdf/SKILL.md +++ b/skills/document-photo-to-pdf/SKILL.md @@ -25,11 +25,10 @@ python3 /workspace/skills/document-photo-to-pdf/doc_deskew/pipeline.py <子命 1. **先说再做。** 每次调脚本前用一句话说明这次干什么(要标注步骤编号)。 2. **坐标只能靠眼睛读,禁止一切自建脚本。** 不另造任何纸张处理的辅助的代码,一次性脚本也不行。确实无法达成目的需要新能力=先停下问用户,不许自己造。 3. **不裁切、不放大、不逐角看。** 四个角在同一张网格图上一次读全,直接报 4 组数字。不为了"读准一点"造局部图、加刻度、逐个角反复看。 -4. **每张图读 2 次,且每次都要有目的。** 网格 1 次 + 角标 1 次,看完就交付。 +4. **每张源图对应1网格图、1角标图。** 每轮读网格图 1 次 + 角标 1 次,看完就交付。 - **读之前先说清这次要确认什么。** 说不出目的就不读。"再看一眼确认一下"不算目的。 - **不为读而读。** 允许重读,但必须是被动的、有明确对象的:图没送达/像素没收到、要核对某个具体数字或某条边。没有新对象就直接用手上已有的数字。 - **只读这两类图。** 网格、角标。原图、局部放大图、成品图、自己另造的辅助图都不读。 - - 没把握就按"宁可外扩"给保守值,交给角标图验证,不在读图阶段磨。 5. **一次成件,禁止试错。** 一条 `build` 出件 + 检验。一轮里每页最多跑 1 次 `build`;不调参、不重取角点、不换方法、不"先出一版看看"。不通过就报诊断,停下等确认。 6. **只有用户明确说"再改"才允许修复。** 完整一轮 = `prepare` → `set`(每页一次)→ `build`(一次)→ 看角标 → 交付。这一轮内发现的任何偏差(框偏了、裁到内容、比例不对),一律只报诊断和坐标建议,**不自行改、不重跑、不补做**。用户在本轮交付后明确说"再改/重做"时才能动手,且还是只跑一轮,改完重新过角标关。 7. **指标 ≠ 成品。** 校验只查"框内"像素,框漏掉的内容查不出来。角标图必须亲眼看。 @@ -45,13 +44,16 @@ python3 /workspace/skills/document-photo-to-pdf/doc_deskew/pipeline.py <子命 ## 流程 -### 1 · 出网格图 +### 1 · 出网格图,并输出候选的角点坐标 ```sh python3 /workspace/skills/document-photo-to-pdf/doc_deskew/pipeline.py prepare 图1.jpg 图2.jpg ``` -不传图片名 = 取当前目录所有图片。输出 `out/N-网格-<名称>.png`(100px 红色主线带坐标刻度、50px 蓝色辅助线,两者同宽)。 +输出 `out/N-网格-<名称>.png`(100px 红色主线带坐标刻度、50px 蓝色辅助线,两者同宽)。 +必须显式传入图片名,合并成PDF时即按此传入顺序。 + +网格图上会叠加一组**候选角点**:品红实心圆 = 候选角点。同时按文件名打印 markdown 表格(`图片|左上|右上|右下|左下`,单元格为 `x,y`),可直接对照读数。品红虚线是检出的边线,用来辅助判断线是否贴边。 ### 2 · 从网格图中读出角点,一张图一条命令 @@ -64,6 +66,11 @@ python3 /workspace/skills/document-photo-to-pdf/doc_deskew/pipeline.py prepare 2. 再识别目标点相对相邻蓝线(50px)的偏移; 3. 把目的坐标复述成一句话,例如“右下:x 在 1000 红线右 52px,y 在 1700 红线下 22px → 1052,1722”。 +候选角点怎么用: +- 图上品红圆就是候选值,可直接拿来作参照对照,省去从零找角点; +- 但**必须逐角核一遍**:圆是否在纸角上、品红虚线是否全程贴着纸边(线跑偏比角点偏更容易看出来); +- 候选与自己的判读不一致时,以自己读图的值为准; + 读数要求: - 读之前先定好这一张要报的 4 组数字,看完立刻 `set` 落盘到 `out/corners.json`。 - 角被遮挡:沿两条可见纸边延长交会出顶点。 @@ -104,9 +111,9 @@ python3 /workspace/skills/document-photo-to-pdf/doc_deskew/pipeline.py build \ **只看不改:** 发现问题只记进报告,记录修正前后角标坐标的表格、不重跑 `build`、不补造辅助图。 -| 页码 | 实际使用的角点坐标 | 修正后的角点坐标 | -|---|---|---| -| 1 | x1,y1;x2,y2;x3,y3;x4,y4 | x1',y1';x2',y2';x3',y3';x4',y4' | +| 页码 | 候选的角点坐标 | 实际使用的角点坐标 | 建议修正的角点坐标 | +|---|---|---|---| +| 1 | | x1,y1;x2,y2;x3,y3;x4,y4 | <事后评估后的坐标> | ## 判定与报告 @@ -119,13 +126,12 @@ python3 /workspace/skills/document-photo-to-pdf/doc_deskew/pipeline.py build \ | 内容贴边 | 页边无成片文字级暗像素 | 内容被切,外扩 5px | - **全部通过**:给产物路径、大小、页数、指标,加一句角标图上确认的结果。 -- **"外侧纸面占比 100%"一律当角点错误**,误差是几十到上百 px,回第 2 步重读,不是微调。 - **不达标**:只报诊断+ 建议,**不自行改、不重跑、不换方法**。用户明确说"再改"后,才改动后重跑一轮,然后交用户决策。 - **用户没发话就交付**:即使只差 1px、即使一眼看出能更好,也不许动。报告里可写建议,手不能动。 ## 内容安全 -**禁止用生成式模型处理这类图片。** 生成模型是重绘而非变换,会改写文档内容,且结果看起来完全正常。本流程只做纯几何变换 + 全局等比提亮,文字、金额、印章保持原始像素。 +**禁止用生成式模型处理这类图片。** 生成模型是重绘而非变换,即使只做几何变换,也可能引入伪影或改写文字。本流程只做纯几何变换 + 全局等比提亮,文字信息保持原始像素。 ## 命令速查 @@ -145,6 +151,8 @@ python3 /workspace/skills/document-photo-to-pdf/doc_deskew/pipeline.py build \ | 模块 | 职责 | |---|---| | `grid.py` | 画带坐标的网格图 | +| `auto_quad.py` | 算候选角点 | +| `prepare.py` | 出网格图:叠候选角点与检出边线 | | `preview_quad.py` | 画角标图(叠网格) | | `verify_quad.py` | 角点几何校验 | | `homography.py` | 透视变换 + 提亮 | diff --git a/skills/document-photo-to-pdf/doc_deskew/auto_quad.py b/skills/document-photo-to-pdf/doc_deskew/auto_quad.py new file mode 100644 index 0000000..a987c97 --- /dev/null +++ b/skills/document-photo-to-pdf/doc_deskew/auto_quad.py @@ -0,0 +1,500 @@ +# -*- coding: utf-8 -*- +"""边线检测 + 纸角候选提取(从 edge_clean_c.py v3 抽取的精简模块)。 + +对外只暴露一个函数: + detect(image_path, max_side=1600) -> (corners, info) + +corners:原图像素坐标系下的四角 [(x, y)],顺序 左上、右上、右下、左下; +info :附加信息(处理尺寸、缩放比、各边覆盖率、边线掩膜),供出图与诊断用。 + +注意:本模块只产出**候选**坐标。它不写 corners.json,也不参与出件判定—— +最终角点必须以人工读角标图的结果为准。 +""" +import numpy as np +from PIL import Image, ImageOps, ImageFilter +from collections import deque + +# ---------------- 基础工具 ---------------- +def load_and_scale(path, max_side=1600): + pil = ImageOps.exif_transpose(Image.open(path)).convert("RGB") + w, h = pil.size + s = max_side / max(w, h) + if s < 1: + pil = pil.resize((int(round(w * s)), int(round(h * s))), Image.LANCZOS) + return pil, np.asarray(pil).astype(np.float32) / 255.0 + + +def rgb_to_sv(arr): + maxc = arr.max(axis=-1) + minc = arr.min(axis=-1) + delta = maxc - minc + S = np.zeros_like(maxc, dtype=np.float32) + np.divide(delta, maxc, out=S, where=maxc > 1e-6) + return S.astype(np.float32), maxc.astype(np.float32) + + +def luminance(arr): + return (0.299 * arr[..., 0] + 0.587 * arr[..., 1] + 0.114 * arr[..., 2]).astype(np.float32) + + +def box_mean(img, r): + """O(1)/像素的方框均值(积分图),r 为半径。""" + img = np.asarray(img, dtype=np.float32) + H, W = img.shape + pad = np.zeros((H + 1, W + 1), dtype=np.float32) + pad[1:, 1:] = img + ii = pad.cumsum(0).cumsum(1) + ys = np.arange(H) + xs = np.arange(W) + y0 = np.clip(ys - r, 0, H) + y1 = np.clip(ys + r + 1, 0, H) + x0 = np.clip(xs - r, 0, W) + x1 = np.clip(xs + r + 1, 0, W) + S = (ii[np.ix_(y1, x1)] - ii[np.ix_(y0, x1)] + - ii[np.ix_(y1, x0)] + ii[np.ix_(y0, x0)]) + cnt = (y1 - y0)[:, None] * (x1 - x0)[None, :] + return S / np.maximum(cnt, 1).astype(np.float32) + + +def gaussian_blur_np(img, sigma): + radius = int(np.ceil(sigma * 3)) + if radius < 1: + return img.astype(np.float32) + x = np.arange(-radius, radius + 1, dtype=np.float32) + k = np.exp(-x * x / (2 * sigma * sigma)) + k /= k.sum() + H, W = img.shape + p = np.pad(img, radius, mode="edge") + tmp = np.zeros((H, W), dtype=np.float32) + for i, kv in enumerate(k): + tmp += kv * p[radius:radius + H, i:i + W] + p = np.pad(tmp, ((radius, radius), (0, 0)), mode="edge") + out = np.zeros((H, W), dtype=np.float32) + for i, kv in enumerate(k): + out += kv * p[i:i + H, :] + return out + + +def convolve3x3(img, kernel): + H, W = img.shape + p = np.pad(img, 1, mode="edge") + out = np.zeros((H, W), dtype=np.float32) + for i in range(3): + for j in range(3): + kv = kernel[i, j] + if kv != 0: + out += kv * p[i:i + H, j:j + W] + return out + + +def sobel_magnitude(gray): + kx = np.array([[-1, 0, 1], [-2, 0, 2], [-1, 0, 1]], dtype=np.float32) + ky = np.array([[-1, -2, -1], [0, 0, 0], [1, 2, 1]], dtype=np.float32) + gx = convolve3x3(gray, kx) + gy = convolve3x3(gray, ky) + return np.sqrt(gx * gx + gy * gy) + + +# ---------------- 形态学(Pillow Max/MinFilter)---------------- +def _odd(size): + size = int(size) + if size < 3: + size = 3 + if size % 2 == 0: + size += 1 + return size + + +def dilate(mask, size): + pil = Image.fromarray((mask.astype(np.uint8) * 255)) + return np.asarray(pil.filter(ImageFilter.MaxFilter(_odd(size)))) > 127 + + +def erode(mask, size): + pil = Image.fromarray((mask.astype(np.uint8) * 255)) + return np.asarray(pil.filter(ImageFilter.MinFilter(_odd(size)))) > 127 + + +def closing(mask, size): + return erode(dilate(mask, size), size) + + +def opening(mask, size): + return dilate(erode(mask, size), size) + + +# ---------------- 连通域 & 填孔(降采样图上做)---------------- +def downsample_any(mask, factor): + if factor <= 1: + return mask + H, W = mask.shape + H2, W2 = H // factor, W // factor + return mask[:H2 * factor, :W2 * factor].reshape( + H2, factor, W2, factor).any(axis=(1, 3)) + + +def upsample_nearest(mask_small, target_h, target_w): + h, w = mask_small.shape + yi = np.linspace(0, h - 1, target_h).astype(np.int32) + xi = np.linspace(0, w - 1, target_w).astype(np.int32) + return mask_small[np.ix_(yi, xi)] + + +def fill_holes(mask_small): + H, W = mask_small.shape + bg = ~mask_small + visited = np.zeros((H, W), dtype=bool) + q = deque() + for x in range(W): + if bg[0, x] and not visited[0, x]: + visited[0, x] = True + q.append((0, x)) + if bg[H - 1, x] and not visited[H - 1, x]: + visited[H - 1, x] = True + q.append((H - 1, x)) + for y in range(H): + if bg[y, 0] and not visited[y, 0]: + visited[y, 0] = True + q.append((y, 0)) + if bg[y, W - 1] and not visited[y, W - 1]: + visited[y, W - 1] = True + q.append((y, W - 1)) + while q: + y, x = q.popleft() + if y > 0 and bg[y - 1, x] and not visited[y - 1, x]: + visited[y - 1, x] = True + q.append((y - 1, x)) + if y < H - 1 and bg[y + 1, x] and not visited[y + 1, x]: + visited[y + 1, x] = True + q.append((y + 1, x)) + if x > 0 and bg[y, x - 1] and not visited[y, x - 1]: + visited[y, x - 1] = True + q.append((y, x - 1)) + if x < W - 1 and bg[y, x + 1] and not visited[y, x + 1]: + visited[y, x + 1] = True + q.append((y, x + 1)) + return mask_small | (bg & ~visited) + + +def largest_connected(mask_small): + H, W = mask_small.shape + visited = np.zeros((H, W), dtype=bool) + best = np.zeros_like(mask_small) + best_n = 0 + ys, xs = np.where(mask_small) + for y0, x0 in zip(ys, xs): + if visited[y0, x0]: + continue + stack = [(y0, x0)] + visited[y0, x0] = True + comp = [] + while stack: + y, x = stack.pop() + comp.append((y, x)) + for dy, dx in ((-1, -1), (-1, 0), (-1, 1), (0, -1), + (0, 1), (1, -1), (1, 0), (1, 1)): + ny, nx = y + dy, x + dx + if 0 <= ny < H and 0 <= nx < W and mask_small[ny, nx] and not visited[ny, nx]: + visited[ny, nx] = True + stack.append((ny, nx)) + if len(comp) > best_n: + best_n = len(comp) + best = np.zeros_like(mask_small) + for y, x in comp: + best[y, x] = True + return best + + +# ---------------- 纸面掩膜(整形后只用于限定搜索区域)---------------- +def otsu_threshold(score): + """一维 Otsu:返回使类间方差最大的阈值""" + hist, bin_edges = np.histogram(score, bins=256, range=(0.0, 1.0)) + hist = hist.astype(np.float64) + total = hist.sum() + if total <= 0: + return 0.5 + p = hist / total + centers = (bin_edges[:-1] + bin_edges[1:]) * 0.5 + w0 = np.cumsum(p) + w1 = 1.0 - w0 + m0 = np.cumsum(p * centers) + mt = m0[-1] + with np.errstate(divide="ignore", invalid="ignore"): + mu0 = m0 / np.maximum(w0, 1e-12) + mu1 = (mt - m0) / np.maximum(w1, 1e-12) + between = w0 * w1 * (mu0 - mu1) ** 2 + between = np.nan_to_num(between, nan=-1.0) + return float(centers[int(np.argmax(between))]) + + +def paper_mask(arr, debug=False): + H, W = arr.shape[:2] + S, V = rgb_to_sv(arr) + # 纸面近白:亮度高、饱和低;木桌面偏色暗。用 Otsu 自动定阈值, + # 再叠加硬约束 V>0.50 防止桌面亮反射被并入。 + score = (V * (1.0 - S)).astype(np.float32) + th = otsu_threshold(score) + th = max(th, 0.50) + bright = (score > th) & (V > 0.50) & (S < 0.45) + if debug: + print(f"[paper_mask] otsu={th:.3f} bright frac={bright.mean():.3f}") + + factor = max(1, min(H, W) // 400) + bs = downsample_any(bright, factor) + + size = _odd(max(5, min(bs.shape) // 60)) + m = closing(bs, size) + m = fill_holes(m) + m = largest_connected(m) + m = closing(m, _odd(max(5, min(bs.shape) // 80))) # 抹掉内凹缺口/阶梯 + m = fill_holes(m) + # 掩膜轻微内收:纸边最外侧 1~2px 常被阴影/暗边吃掉,内收后环带更贴合真实纸边 + m = erode(m, 3) + + paper = upsample_nearest(m, H, W) if factor > 1 else m + if debug: + Image.fromarray((paper * 255).astype(np.uint8)).save("dbg_v3_paper.png") + return paper + + +def boundary_band(paper, k): + """纸面掩膜边界两侧各 k 像素的环带。""" + k = _odd(k) + return dilate(paper, k) & ~erode(paper, k) + + +# ---------------- 边缘图(局部自适应阈值)---------------- +def edge_map(arr, local_gain=1.55, low=0.035): + H = arr.shape[0] + gray = luminance(arr) + sigma = max(1.0, H / 800.0) + blurred = gaussian_blur_np(gray, sigma) + mag = sobel_magnitude(blurred) + local = box_mean(mag, max(3, H // 50)) + th = np.maximum(low, local * local_gain) + return mag > th + + +def boundary_step_filter(arr, paper, r_small=10, r_big=24, step_th=0.055): + """跨纸边亮度阶跃检测:比较掩膜内侧/外侧小窗的 V 均值。 + + 纸边是真实的明暗台阶(阶跃大),木纹/阴影纹理阶跃小。相比固定亮度 + 阈值(V>0.60 / V<0.45),不受整体曝影响。两级窗口:掩膜准确的 + 位置用 r_small,掩膜略有内收/偏移处依靠 r_big 补上。 + """ + _, V = rgb_to_sv(arr) + p = paper.astype(np.float32) + q = 1.0 - p + + def side_means(r): + din = box_mean(p, r) + dout = box_mean(q, r) + vin = box_mean(V * p, r) / np.maximum(din, 1e-6) + vout = box_mean(V * q, r) / np.maximum(dout, 1e-6) + ok = (din > 0.08) & (dout > 0.08) + return np.where(ok, np.abs(vin - vout), 0.0) + + step = np.maximum(side_means(r_small), side_means(r_big)) + return step > step_th + + + +# ---------------- 四角提取(掩膜 -> 四边拟合 -> 交点) ---------------- +def mask_boundary_points(mask): + """掩膜边界像素坐标 (N,2) float32,顺序为 (x, y)""" + inner = erode(mask, 3) + ys, xs = np.where(mask & ~inner) + return np.stack([xs, ys], axis=1).astype(np.float32) + + +def _fit_line(pts): + """总体最小二乘拟直线,返回法向量 n 与 n·p = c""" + c0 = pts.mean(axis=0) + q = pts - c0 + cov = (q.T @ q) / max(len(pts) - 1, 1) + w, v = np.linalg.eigh(cov) + d = v[:, int(np.argmax(w))] # 主方向 + n = np.array([-d[1], d[0]], dtype=np.float64) + nn = np.linalg.norm(n) + if nn < 1e-9: + return np.array([0.0, 1.0]), float(c0[1]) + n = n / nn + return n, float(n @ c0) + + +def _intersect(n1, c1, n2, c2): + A = np.vstack([n1, n2]) + b = np.array([c1, c2], dtype=np.float64) + try: + return np.linalg.solve(A, b) + except np.linalg.LinAlgError: + return None + + +def detect_quad_corners(paper, points=None, robust_px=2.0, group_tol=22.0): + """提取四个纸角,返回 [(x,y)],顺序 左上、右上、右下、左下。 + + 锚点一律取自纸面掩膜边界(稳定,不受噪声小刺影响);points 传入纸边黑线 + 像素时,按到四条基准边的距离分组后重新拟合,得到更贴真实纸边的角点。 + 每个角都有退化与越界检查,不通过就回退到掩膜基准边交点。 + """ + base = mask_boundary_points(paper) + if len(base) < 40: + return [] + bx, by = base[:, 0], base[:, 1] + a_s = bx + by + a_d = bx - by + anchors = np.array([ + base[int(np.argmin(a_s))], # 左上 + base[int(np.argmax(a_d))], # 右上 + base[int(np.argmax(a_s))], # 右下 + base[int(np.argmin(a_d))], # 左下 + ], dtype=np.float64) + + base_lines = [] + for a, b in ((0, 1), (1, 2), (2, 3), (3, 0)): + p0, p1 = anchors[a], anchors[b] + dv = p1 - p0 + L = float(np.linalg.norm(dv)) + if L < 1e-6: + base_lines.append(None) + continue + dv = dv / L + n0 = np.array([-dv[1], dv[0]]) + base_lines.append((n0, float(n0 @ p0))) + + corners = [] + for i in range(4): + l1, l2 = base_lines[i - 1], base_lines[i] + if l1 is None or l2 is None: + corners.append(anchors[i].copy()) + continue + p = _intersect(l1[0], l1[1], l2[0], l2[1]) + corners.append(anchors[i].copy() if p is None else p) + + if points is None: + return [(float(p[0]), float(p[1])) for p in corners] + + pts = np.asarray(points, dtype=np.float64) + if len(pts) < 40: + return [(float(p[0]), float(p[1])) for p in corners] + + dd = [] + for l in base_lines: + if l is None: + dd.append(np.full(len(pts), 1e9)) + else: + dd.append(np.abs(pts @ l[0] - l[1])) + D = np.stack(dd, axis=1) + idx = np.argmin(D, axis=1) + dmin = D[np.arange(len(pts)), idx] + + lines = [] + for i in range(4): + sel = pts[(idx == i) & (dmin <= group_tol)] + if len(sel) < 40: + lines.append(base_lines[i]) + continue + n, c = _fit_line(sel) + for _ in range(2): + res = np.abs(sel @ n - c) + keep = sel[res <= max(robust_px, 1.0) * 2.5] + if len(keep) < 40: + break + n, c = _fit_line(keep) + sel = keep + lines.append((n, c)) + + H, W = paper.shape + for i in range(4): + l1, l2 = lines[i - 1], lines[i] + if l1 is None or l2 is None: + continue + det = l1[0][0] * l2[0][1] - l2[0][0] * l1[0][1] + if abs(det) < 1e-3: # 两边近共线,交点发散 + continue + p = _intersect(l1[0], l1[1], l2[0], l2[1]) + if p is None: + continue + if not (-0.15 * W <= p[0] <= 1.15 * W and -0.15 * H <= p[1] <= 1.15 * H): + continue + corners[i] = p + + return [(float(p[0]), float(p[1])) for p in corners] + + + + +# ---------------- 覆盖率指标 ---------------- +def border_coverage_exact(edges, paper, tol=14): + """沿掩膜逐行/逐列的真实边界测覆盖率(适配斜边,不受 bbox 影响)。 + + 对每一列取掩膜的上/下边界,对每一行取左/右边界,检查 ±tol 内是否有边缘像素。 + """ + H, W = paper.shape + col_has = paper.any(axis=0) + row_has = paper.any(axis=1) + top_hit = top_n = 0 + bot_hit = bot_n = 0 + for x in np.where(col_has)[0]: + ys = np.where(paper[:, x])[0] + y0, y1 = ys.min(), ys.max() + if edges[max(0, y0 - tol):min(H, y0 + tol + 1), x].any(): + top_hit += 1 + top_n += 1 + if edges[max(0, y1 - tol):min(H, y1 + tol + 1), x].any(): + bot_hit += 1 + bot_n += 1 + left_hit = left_n = 0 + right_hit = right_n = 0 + for y in np.where(row_has)[0]: + xs = np.where(paper[y, :])[0] + x0, x1 = xs.min(), xs.max() + if edges[y, max(0, x0 - tol):min(W, x0 + tol + 1)].any(): + left_hit += 1 + left_n += 1 + if edges[y, max(0, x1 - tol):min(W, x1 + tol + 1)].any(): + right_hit += 1 + right_n += 1 + return { + "top": top_hit / max(top_n, 1), + "bottom": bot_hit / max(bot_n, 1), + "left": left_hit / max(left_n, 1), + "right": right_hit / max(right_n, 1), + } + +# ---------------- 对外接口 ---------------- + +def detect(image_path, max_side=1600): + """检测纸张四角,返回 (corners_原图坐标, info)。失败返回 ([], info)。""" + src = ImageOps.exif_transpose(Image.open(image_path)).convert('RGB') + src_w, src_h = src.size + pil, arr = load_and_scale(image_path, max_side=max_side) + H, W = arr.shape[:2] + + paper = paper_mask(arr) + frac = float(paper.sum()) / (H * W) + + band = boundary_band(paper, _odd(max(15, H // 45))) + edges = edge_map(arr) + step = boundary_step_filter(arr, paper) + cand = closing(edges & band & step, _odd(max(5, H // 160))) + cand = opening(cand, _odd(max(3, H // 500))) + + ey, ex = np.nonzero(cand) + pts = np.stack([ex, ey], axis=1).astype(np.float32) if len(ex) > 40 else None + corners = detect_quad_corners(paper, points=pts) + + scale = min(1.0, float(max_side) / max(src_w, src_h)) + src_pts = [(x / scale, y / scale) for x, y in corners] if corners else [] + info = { + 'source_size': [src_w, src_h], + 'processed_size': [W, H], + 'scale': round(scale, 6), + 'paper_frac': round(frac, 4), + 'edge_pixels': int(cand.sum()), + 'coverage': border_coverage_exact(cand, paper, tol=max(10, H // 110)) if corners else {}, + 'processed_pts': corners, + 'edge_mask_small': cand, # 处理尺寸上的边线掩膜(供叠加出图) + } + return src_pts, info diff --git a/skills/document-photo-to-pdf/doc_deskew/grid.py b/skills/document-photo-to-pdf/doc_deskew/grid.py index a4ae7b6..c2d2e67 100644 --- a/skills/document-photo-to-pdf/doc_deskew/grid.py +++ b/skills/document-photo-to-pdf/doc_deskew/grid.py @@ -11,9 +11,14 @@ LINE_WIDTH = 2 def draw_grid_on(im, step=50, major=100): - """在原图上叠加坐标网格,返回同一个 Image 对象(不落盘)。""" + """在原图上叠加坐标网格,返回叠加后的图像(不落盘)。 + + 先画到独立的 RGBA 图层再合成:RGBA 底图直接画会被 ImageDraw 覆盖, + 半透明线变成实心色,跟角标图上的网格对不上。 + """ W, H = im.size - d = ImageDraw.Draw(im, 'RGBA') + layer = Image.new('RGBA', im.size, (0, 0, 0, 0)) + d = ImageDraw.Draw(layer) try: f = ImageFont.truetype(FONT, 18) except Exception: @@ -33,7 +38,7 @@ def draw_grid_on(im, step=50, major=100): for y in range(0, H, major): d.rectangle([1, y + 1, 46, y + 21], fill=(255, 255, 255, 220)) d.text((2, y + 1), str(y), fill=(0, 0, 200), font=f) - return im + return Image.alpha_composite(im.convert('RGBA'), layer).convert(im.mode) def draw_grid(src, dst, step=50, major=100): diff --git a/skills/document-photo-to-pdf/doc_deskew/pipeline.py b/skills/document-photo-to-pdf/doc_deskew/pipeline.py index b9542a5..532e0b4 100644 --- a/skills/document-photo-to-pdf/doc_deskew/pipeline.py +++ b/skills/document-photo-to-pdf/doc_deskew/pipeline.py @@ -54,8 +54,6 @@ OUT_DIR = 'out' CORNERS = os.path.join(OUT_DIR, 'corners.json') LABELS = ('左上', '右上', '右下', '左下') -IMG_EXT = ('.jpg', '.jpeg', '.png', '.webp', '.bmp', '.tif', '.tiff') - # ---------------------------------------------------------------- 基础工具 @@ -113,18 +111,15 @@ def parse_quad(text): def collect_images(args): - """参数里的图片 + 当前目录全部图片(去重、按自然序)。""" - names = list(args) + """只接受显式传入的图片(去重、按自然序);不再扫描当前目录。""" + names = [n for n in args if n] if not names: - names = [f for f in os.listdir('.') - if f.lower().endswith(IMG_EXT) and os.path.isfile(f)] + raise SystemExit('必须显式指定图片,例如:prepare 图1.jpg 图2.jpg') seen, out = set(), [] for n in names: if n not in seen: seen.add(n) out.append(n) - if not out: - raise SystemExit('没有找到图片:可在命令后面直接列文件名') missing = [n for n in out if not os.path.exists(n)] if missing: raise SystemExit('图片不存在:%s' % ', '.join(missing)) @@ -142,15 +137,38 @@ def out_path(prefix, i, name, ext='.png'): # ---------------------------------------------------------------- prepare -def cmd_prepare(images): +def cmd_prepare(images, auto_quad=True): os.makedirs(OUT_DIR, exist_ok=True) - from grid import draw_grid + import prepare as prep data = load_corners() + cand = {} for i, name in enumerate(images, 1): dst = out_path('网格', i, name) - draw_grid(name, dst) + if auto_quad: + corners, info = prep.detect_corners(name) + if corners: + prep.render(name, dst, corners=corners, + edge_mask=info.get('edge_mask_small'), + scale=info.get('scale', 1.0)) + cand[name] = corners + else: + prep.render(name, dst) + else: + prep.render(name, dst) data.setdefault(name, None) save_corners({k: v for k, v in data.items() if v}) + + if cand: + print('[候选角点] 已叠加到网格图(品红实心圆 = 候选角点,品红虚线 = 候选四边形,黑 = 检出边线)') + print('') + print('| 图片 | 左上 | 右上 | 右下 | 左下 |') + print('|---|---|---|---|---|') + for name, pts in cand.items(): + cells = ['%d,%d' % (round(p[0]), round(p[1])) for p in pts] + print('| %s | %s |' % (name, ' | '.join(cells))) + print('') + print('[仅供参考] 候选值不得直接写入 corners.json,一律以角标图人工判读为准') + print('\n网格图已写入 %s/' % OUT_DIR) print('下一步:照着网格图读数,把角点写进 %s:' % CORNERS) for i, name in enumerate(images, 1): @@ -201,12 +219,29 @@ def cmd_show(): return 0 + # ---------------------------------------------------------------- 角标图 +def grid_path(name): + """找 prepare 生成的网格图(out/N-网格-<图名>.png);没有返回 None。""" + base = os.path.splitext(os.path.basename(name))[0] + if not os.path.isdir(OUT_DIR): + return None + # 用完整的 "-网格-.png" 后缀精确匹配,避免 a.jpg / 合同a.jpg 这类包含关系串图 + want = '-网格-%s.png' % base + hits = [fn for fn in os.listdir(OUT_DIR) + if fn[:1].isdigit() and fn.endswith(want)] + if not hits: + return None + # 同名网格图有多份时取最新的一份(防止旧轮次的残留文件) + fn = max(hits, key=lambda f: os.path.getmtime(os.path.join(OUT_DIR, f))) + return os.path.join(OUT_DIR, fn) + + def draw_marks(name, pts, dst): - """把四角画回原图(底图叠加与网格图相同的网格),供人工核查。""" + """把四角叠加到已生成的网格图上(找不到网格图时退回原图并即时叠网格)。""" from preview_quad import draw_quad - im = draw_quad(name, pts, with_grid=True) + im = draw_quad(name, pts, base_path=grid_path(name), with_grid=True) im.save(dst) return dst @@ -353,8 +388,10 @@ def main(): epilog=__doc__) sub = ap.add_subparsers(dest='cmd', required=True) - p = sub.add_parser('prepare', help='出网格图(out/1-网格-*.png)') - p.add_argument('images', nargs='*', help='图片名,省略则取当前目录所有图片') + p = sub.add_parser('prepare', help='出网格图(out/1-网格-*.png),叠加候选角点') + p.add_argument('images', nargs='*', help='图片名(必填,可多个)') + p.add_argument('--no-auto-quad', action='store_true', + help='不跑候选角点检测,只出纯网格图') p = sub.add_parser('set', help='把一张图的角点写进 out/corners.json') p.add_argument('image', metavar='IMG', help='图片名(一次一张)') @@ -380,7 +417,7 @@ def main(): help='另存边角放大块,便于细看') p = sub.add_parser('all', help='prepare + build 一步到位') - p.add_argument('images', nargs='*') + p.add_argument('images', nargs='*', help='图片名(必填,可多个)') p.add_argument('--out', default='文档_校正.pdf') p.add_argument('--paper', default=None) p.add_argument('--dpi', type=int, default=100) @@ -390,7 +427,8 @@ def main(): args = ap.parse_args() if args.cmd == 'prepare': - return cmd_prepare(collect_images(args.images)) + return cmd_prepare(collect_images(args.images), + auto_quad=not args.no_auto_quad) if args.cmd == 'set': return cmd_set(args) if args.cmd == 'show': diff --git a/skills/document-photo-to-pdf/doc_deskew/prepare.py b/skills/document-photo-to-pdf/doc_deskew/prepare.py new file mode 100644 index 0000000..4207e72 --- /dev/null +++ b/skills/document-photo-to-pdf/doc_deskew/prepare.py @@ -0,0 +1,94 @@ +# -*- coding: utf-8 -*- +"""prepare 阶段的出图逻辑:坐标网格图 + 脚本候选角点/边线叠加。 + +产物 + out/N-网格-<图名>.png 网格 + 候选角点(人工读数的主依据) + +约定 + - 候选角点只做**参考**:不落盘、不写 corners.json、不参与出件, + 由 pipeline 直接在终端打成 markdown 表格供对照; + - 图上不写字,避免遮挡纸面内容。 +""" +import math +import os +import sys + +from PIL import Image, ImageDraw + +sys.path.insert(0, os.path.dirname(os.path.abspath(__file__))) +from grid import draw_grid_on + +COLOR_EDGE = (0, 0, 0) # 黑:脚本检出的边线像素 +COLOR_CAND = (255, 0, 180) # 品红:候选四边形与角点 +LABELS = ('左上', '右上', '右下', '左下') + + +def _dashed(d, p0, p1, fill, width=2, dash=14, gap=9): + dx, dy = p1[0] - p0[0], p1[1] - p0[1] + L = math.hypot(dx, dy) + if L < 1e-6: + return + ux, uy = dx / L, dy / L + t = 0.0 + while t < L: + a, b = t, min(t + dash, L) + d.line([(p0[0] + ux * a, p0[1] + uy * a), + (p0[0] + ux * b, p0[1] + uy * b)], fill=fill, width=width) + t += dash + gap + + +def _extend(p0, p1, px): + dx, dy = p1[0] - p0[0], p1[1] - p0[1] + L = math.hypot(dx, dy) + if L < 1e-6: + return p0, p1 + ux, uy = dx / L, dy / L + return (p0[0] - ux * px, p0[1] - uy * px), (p1[0] + ux * px, p1[1] + uy * px) + + +def render(src, dst, corners=None, edge_mask=None, scale=1.0, extend_px=None): + """画网格图;corners 非空时叠加候选边线与角点。""" + im = Image.open(src).convert('RGBA') + + if edge_mask is not None: + m = Image.fromarray((edge_mask * 255).astype('uint8'), 'L') + if m.size != im.size: + m = m.resize(im.size, Image.NEAREST) + lay = Image.new('RGBA', im.size, (0, 0, 0, 0)) + lay.paste(COLOR_EDGE + (200,), (0, 0), m.point(lambda v: 255 if v > 127 else 0)) + im = Image.alpha_composite(im, lay) + + im = draw_grid_on(im) + if not corners: + im.convert('RGB').save(dst, quality=92) + return dst + + d = ImageDraw.Draw(im, 'RGBA') + n = len(corners) + ext = extend_px if extend_px is not None else max(30, im.size[1] // 36) + for i in range(n): + a, b = _extend(corners[i], corners[(i + 1) % n], ext) + _dashed(d, a, b, COLOR_CAND + (240,), width=2) + + for x, y in corners: + d.ellipse([x - 14, y - 14, x + 14, y + 14], + outline=(255, 255, 255, 255), width=4) + d.ellipse([x - 8, y - 8, x + 8, y + 8], fill=COLOR_CAND + (255,)) + d.ellipse([x - 2, y - 2, x + 2, y + 2], fill=(255, 255, 255, 255)) + + im.convert('RGB').save(dst, quality=92) + return dst + + +def detect_corners(src, max_side=1600): + """调用 auto_quad 取候选角点;失败返回 (None, None),不抛异常打断 prepare。""" + try: + import auto_quad + pts, info = auto_quad.detect(src, max_side=max_side) + return (pts or None), info + except Exception as e: # 检测失败不该阻塞流程 + print('[提示] 候选角点检测跳过:%s' % e) + return None, None + + + diff --git a/skills/document-photo-to-pdf/doc_deskew/preview_quad.py b/skills/document-photo-to-pdf/doc_deskew/preview_quad.py index 5e763f9..3a5b803 100644 --- a/skills/document-photo-to-pdf/doc_deskew/preview_quad.py +++ b/skills/document-photo-to-pdf/doc_deskew/preview_quad.py @@ -63,10 +63,14 @@ def get_font(size=26): return ImageFont.load_default() -def draw_quad(img_path, pts, scale=1.0, with_grid=False): - im = Image.open(img_path).convert('RGB') - # 角标图默认叠上与网格图同一套网格:坐标读数与框边可以对着看 - if with_grid: +def draw_quad(img_path, pts, scale=1.0, base_path=None, with_grid=False): + """在底图上叠加四角标注。 + + base_path 非空时直接用该图当底图(通常是 prepare 生成的网格图,连同候选标记一起继承); + 为空时退回原图,with_grid=True 则即时叠一层网格。 + """ + im = Image.open(base_path or img_path).convert('RGB') + if with_grid and base_path is None: from grid import draw_grid_on im = draw_grid_on(im) if scale != 1.0: