yangxiangyuan
a3e8911deb
- 新增作息报时器独立模块，包含完整的日程管理、语音播报和待机功能 - 短链接正式前缀由/l/改为/to/，解决手机小屏下与I、i、1字形混淆问题 - 保留旧前缀/l/、/L/、/I/、/i/兼容已分发的旧短链 - 新增短码大小写兜底匹配，仅唯一匹配时生效避免歧义 - 新增防爆紧急替换功能，可轮换首页鉴权并替换短链接 - 新增多个调试和集成测试脚本，保障数据安全和功能回归
361 lines
16 KiB
Python
361 lines
16 KiB
Python
# -*- coding: utf-8 -*-
|
||
# ============================================================
|
||
# tool_crop_mall_logos.py - 宝龙美食打卡 lab · 导视牌 logo 重裁脚本（方案 A）
|
||
#
|
||
# 病根：原 images/ 是按"等分网格"从斜拍照片硬裁的，透视变形导致越靠边错位越大，
|
||
# 裁切图带白底店名标签、串邻格、切边。
|
||
#
|
||
# 算法流程（经典 CV，离线确定可重复跑）：
|
||
# 1) 展板四边形检测（亮板 vs 暗背景 OTSU + 最大轮廓 approxPolyDP）→ 四点透视矫正拉正
|
||
# 2) 置信照片块检测：HSV 颜色掩膜 (饱和度高 OR 暗) → 闭/开运算 → 连通域，
|
||
# 只保留尺寸落在照片先验区间内的"置信块"（过曝区检不出就检不出，不强求）
|
||
# 3) 全局网格拟合：导视牌是印刷规整网格，矫正后行/列等距 ——
|
||
# 用置信块的最小二乘拟合 行顶线 row_top(r) 与 列中心线 col_center(c)，
|
||
# 过曝检不出的格子直接按几何矩形取，天然不错位
|
||
# 4) 几何兜底格先做"内容密度"校验：空白板面（如 r2c10「待确认」牌上不存在）跳过，
|
||
# 有边框/文字/图案的（如商业街白框）保留
|
||
# 5) 输出统一宽度 jpg + 拼版预览图 + report.json，供人工 / qwen-vl 抽检
|
||
#
|
||
# 用法：
|
||
# python tool_crop_mall_logos.py # 默认参数直接跑
|
||
# python tool_crop_mall_logos.py --pad 4 # 调整裁切外扩像素
|
||
# python tool_crop_mall_logos.py --dry-run # 只出预览和报告，不写 images/
|
||
# ============================================================
|
||
import argparse
|
||
import json
|
||
import os
|
||
import sys
|
||
|
||
import cv2
|
||
import numpy as np
|
||
|
||
DEFAULT_SRC = r'D:\Temp文件\baolong-mall\照片.jpg'
|
||
DEFAULT_OUT = r'd:\Trae_Files\TRAE-Toolbox\public\tools\thought_lab\labs\mall_food_checkin\images'
|
||
DEFAULT_SEED = r'd:\Trae_Files\TRAE-Toolbox\src\server\thought_lab\labs\mall_food_checkin\shops_seed.json'
|
||
DEFAULT_PREVIEW = r'd:\Trae_Files\TRAE-Toolbox\dev_test_scripts\debug\mall_crop_contact.jpg'
|
||
DEFAULT_REPORT = r'd:\Trae_Files\TRAE-Toolbox\dev_test_scripts\debug\mall_crop_report.json'
|
||
|
||
ROWS, COLS = 7, 11
|
||
|
||
|
||
def imread_u(path):
|
||
# Windows 下 cv2.imread 不支持中文路径，用 np.fromfile + imdecode 兜底
|
||
data = np.fromfile(path, dtype=np.uint8)
|
||
return cv2.imdecode(data, cv2.IMREAD_COLOR)
|
||
|
||
|
||
def imwrite_u(path, img, params=None):
|
||
ext = os.path.splitext(path)[1] or '.jpg'
|
||
ok, buf = cv2.imencode(ext, img, params or [])
|
||
if not ok:
|
||
return False
|
||
buf.tofile(path)
|
||
return True
|
||
|
||
|
||
def order_points(pts):
|
||
# 排序为 tl, tr, br, bl
|
||
pts = np.array(pts, dtype='float32')
|
||
s = pts.sum(axis=1)
|
||
d = np.diff(pts, axis=1).ravel()
|
||
tl = pts[np.argmin(s)]
|
||
br = pts[np.argmax(s)]
|
||
tr = pts[np.argmin(d)]
|
||
bl = pts[np.argmax(d)]
|
||
return np.array([tl, tr, br, bl], dtype='float32')
|
||
|
||
|
||
def detect_board_quad(img):
|
||
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
|
||
blur = cv2.GaussianBlur(gray, (7, 7), 0)
|
||
_, th = cv2.threshold(blur, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
|
||
th = cv2.morphologyEx(th, cv2.MORPH_CLOSE, np.ones((25, 25), np.uint8))
|
||
cnts, _ = cv2.findContours(th, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
|
||
if not cnts:
|
||
raise RuntimeError('未找到展板轮廓')
|
||
c = max(cnts, key=cv2.contourArea)
|
||
peri = cv2.arcLength(c, True)
|
||
approx = cv2.approxPolyDP(c, 0.02 * peri, True)
|
||
if len(approx) == 4:
|
||
return order_points(approx.reshape(4, 2))
|
||
rect = cv2.minAreaRect(c)
|
||
return order_points(cv2.boxPoints(rect))
|
||
|
||
|
||
def warp_board(img, quad):
|
||
(tl, tr, br, bl) = quad
|
||
w = int(max(np.linalg.norm(tr - tl), np.linalg.norm(br - bl)))
|
||
h = int(max(np.linalg.norm(bl - tl), np.linalg.norm(br - tr)))
|
||
m = cv2.getPerspectiveTransform(quad, np.array([[0, 0], [w - 1, 0], [w - 1, h - 1], [0, h - 1]], dtype='float32'))
|
||
return cv2.warpPerspective(img, m, (w, h))
|
||
|
||
|
||
def detect_confident_blocks(warped):
|
||
"""颜色掩膜 + 尺寸先验，只返回高置信照片块（过曝区检不出不强求）"""
|
||
hsv = cv2.cvtColor(warped, cv2.COLOR_BGR2HSV)
|
||
s = hsv[:, :, 1]
|
||
v = hsv[:, :, 2]
|
||
mask = (((s > 45) | (v < 140)).astype(np.uint8)) * 255
|
||
mask[:60, :] = 0
|
||
mask[-60:, :] = 0
|
||
mask[:, :60] = 0
|
||
mask[:, -60:] = 0
|
||
mask = cv2.morphologyEx(mask, cv2.MORPH_CLOSE, np.ones((9, 9), np.uint8))
|
||
mask = cv2.morphologyEx(mask, cv2.MORPH_OPEN, np.ones((7, 7), np.uint8))
|
||
n, labels, stats, cents = cv2.connectedComponentsWithStats(mask, 8)
|
||
h, w = warped.shape[:2]
|
||
blocks = []
|
||
for i in range(1, n):
|
||
x, y, bw, bh, area = stats[i]
|
||
cx, cy = cents[i]
|
||
if area < 30000:
|
||
continue
|
||
if cy < 0.17 * h or cx < 0.06 * w:
|
||
continue
|
||
if not (180 <= bw <= 360 and 150 <= bh <= 300):
|
||
continue
|
||
blocks.append({'x': int(x), 'y': int(y), 'w': int(bw), 'h': int(bh),
|
||
'cx': float(cx), 'cy': float(cy), 'area': int(area)})
|
||
return blocks
|
||
|
||
|
||
def fit_grid(blocks):
|
||
"""用置信块拟合全局网格：行顶线 / 列中心线 / 照片宽高
|
||
列：全局 cx 聚类（不依赖"检满 11 格的行"，过曝行缺块也不错位）
|
||
行：cy 聚类 + 行距推算行号（缺行不影响编号）"""
|
||
# ---- 列：全局 cx 聚类 ----
|
||
by_cx = sorted(blocks, key=lambda b: b['cx'])
|
||
col_clusters = []
|
||
for b in by_cx:
|
||
if col_clusters and b['cx'] - col_clusters[-1][-1]['cx'] < 120:
|
||
col_clusters[-1].append(b)
|
||
else:
|
||
col_clusters.append([b])
|
||
if len(col_clusters) != COLS:
|
||
raise RuntimeError('列聚类=%d（期望 %d）' % (len(col_clusters), COLS))
|
||
col_center = [float(np.mean([b['cx'] for b in c])) for c in col_clusters]
|
||
|
||
# ---- 行：cy 聚类 + 行距推号 ----
|
||
by_cy = sorted(blocks, key=lambda b: b['cy'])
|
||
row_clusters = []
|
||
for b in by_cy:
|
||
if row_clusters and b['cy'] - row_clusters[-1][-1]['cy'] < 120:
|
||
row_clusters[-1].append(b)
|
||
else:
|
||
row_clusters.append([b])
|
||
cys = [float(np.mean([b['cy'] for b in c])) for c in row_clusters]
|
||
diffs = [cys[i + 1] - cys[i] for i in range(len(cys) - 1)]
|
||
step = float(np.median([d for d in diffs if d < 400])) if diffs else 290.0
|
||
row_idx = [int(round((cy - cys[0]) / step)) for cy in cys]
|
||
if len(set(row_idx)) != len(row_idx) or max(row_idx) >= ROWS or min(row_idx) < 0:
|
||
raise RuntimeError('行聚类异常: %s' % row_idx)
|
||
|
||
# ---- 行顶线最小二乘拟合（检出的行 -> 预测全部 7 行）----
|
||
pts = [(float(ri), float(np.mean([b['y'] for b in c]))) for ri, c in zip(row_idx, row_clusters)]
|
||
if len(pts) >= 2:
|
||
ra, rb = np.polyfit([p[0] for p in pts], [p[1] for p in pts], 1)
|
||
row_top = [float(rb + ra * r) for r in range(ROWS)]
|
||
else:
|
||
row_top = [pts[0][1] + step * r for r in range(ROWS)]
|
||
|
||
pw = float(np.median([b['w'] for b in blocks]))
|
||
ph = float(np.median([b['h'] for b in blocks]))
|
||
grid = {}
|
||
for ri, c in zip(row_idx, row_clusters):
|
||
for b in c:
|
||
ci = int(np.argmin([abs(cc - b['cx']) for cc in col_center]))
|
||
key = (ri, ci)
|
||
if key not in grid or b['area'] > grid[key]['area']:
|
||
grid[key] = b
|
||
return {'row_top': row_top, 'col_center': col_center, 'pw': pw, 'ph': ph,
|
||
'grid': grid, 'rows_found': sorted(set(row_idx)), 'step': step}
|
||
|
||
|
||
def trim_label(crop):
|
||
"""裁掉底部白底店名标签条 —— 间隙定位法（逐行扫描对死区/剖面重叠太脆弱）：
|
||
1) 向量化行剖面：gap 行=全宽白(dark<0.03 且 mean>=180)；text 行=dark 0.08~0.7 且 mean 100~215
|
||
2) 在底部 50% 内找连续 gap 段，自底向上取第一个同时满足以下条件的段作为裁切线：
|
||
a. 段下方有 >=8 个 text 行（标签文字）
|
||
b. 最后一个 text 行距裁切图底边 <=20 行（标签贴着底边；商业街白框的文字在格子中部，被排除）
|
||
c. 段上方 10 行内 gap 行 <5（上面是照片内容，不是另一段白）
|
||
找不到合格间隙 → 不裁。"""
|
||
g = cv2.cvtColor(crop, cv2.COLOR_BGR2GRAY)
|
||
h = g.shape[0]
|
||
if h < 40:
|
||
return crop
|
||
gf = g.astype(np.float32)
|
||
dark = (gf < 160).mean(axis=1)
|
||
mean = gf.mean(axis=1)
|
||
# 列结构指标：文字行 dark 集中在中部（字），间隙/阴影行全宽均匀分布
|
||
w = g.shape[1]
|
||
c0, c1 = int(w * 0.2), int(w * 0.8)
|
||
dark_c = (gf[:, c0:c1] < 160).mean(axis=1)
|
||
dark_o = ((gf[:, :c0] < 160).sum(axis=1) + (gf[:, c1:] < 160).sum(axis=1)) / float(w - (c1 - c0))
|
||
ratio = (dark_c + 0.004) / (dark_o + 0.004)
|
||
# 阈值按实测剖面放宽：角落阴影区标签白底 mean 仅 120~180、间隙行 dark 到 0.09；
|
||
# 稀疏字行(DQ 两字 dark~0.05)靠 ratio 与阴影白区分
|
||
is_text = (dark >= 0.04) & (mean <= 220) & (ratio > 2.5)
|
||
is_gap = (dark < 0.12) & (mean >= 165) & (~is_text)
|
||
lo = h - 1 - int(h * 0.5)
|
||
runs = []
|
||
y = h - 1
|
||
while y > lo:
|
||
if is_gap[y]:
|
||
y2 = y
|
||
while y2 > lo and is_gap[y2]:
|
||
y2 -= 1
|
||
runs.append((y2 + 1, y))
|
||
y = y2
|
||
else:
|
||
y -= 1
|
||
for (start, end) in runs: # runs 自底向上收集，天然从最低段开始
|
||
if end - start + 1 < 4: # 标签内部笔画间的假间隙通常只有 1~3 行
|
||
continue
|
||
below = is_text[end + 1:h] if end + 1 < h else np.zeros(0, bool)
|
||
if below.sum() < 8:
|
||
continue
|
||
last_text = end + 1 + int(np.max(np.nonzero(below)))
|
||
below_any = (is_text | is_gap)[end + 1:h] if end + 1 < h else np.zeros(0, bool)
|
||
if not below_any.any():
|
||
continue
|
||
last_below = end + 1 + int(np.max(np.nonzero(below_any)))
|
||
# 底边允许一段阴影带(既非 text 也非 gap)；标签文字与底边之间只允许留白/阴影
|
||
if (h - 1) - last_below > 20:
|
||
continue
|
||
# 文字与底边内容之间允许留白/阴影：实测最大 32 行(r6c0 兜底矩形探到板面)；
|
||
# 商业街白框的文字距底边 60 行，仍被排除
|
||
if last_below - last_text > 35:
|
||
continue
|
||
above = is_gap[max(0, start - 10):start]
|
||
if above.sum() >= 5:
|
||
continue
|
||
return crop[:start]
|
||
return crop
|
||
|
||
|
||
def region_has_content(warped, x, y, w, h):
|
||
# 空白板面平滑（边缘密度/标准差低）；有 logo/边框/文字的区域高
|
||
hh, ww = warped.shape[:2]
|
||
x0, y0 = max(0, x), max(0, y)
|
||
x1, y1 = min(ww, x + w), min(hh, y + h)
|
||
if x1 - x0 < 20 or y1 - y0 < 20:
|
||
return False
|
||
roi = cv2.cvtColor(warped[y0:y1, x0:x1], cv2.COLOR_BGR2GRAY)
|
||
edges = cv2.Canny(roi, 60, 160)
|
||
density = float(np.count_nonzero(edges)) / float(edges.size)
|
||
return density > 0.006 or float(np.std(roi)) > 24
|
||
|
||
|
||
def main():
|
||
ap = argparse.ArgumentParser()
|
||
ap.add_argument('--src', default=DEFAULT_SRC)
|
||
ap.add_argument('--out', default=DEFAULT_OUT)
|
||
ap.add_argument('--seed', default=DEFAULT_SEED)
|
||
ap.add_argument('--preview', default=DEFAULT_PREVIEW)
|
||
ap.add_argument('--report', default=DEFAULT_REPORT)
|
||
ap.add_argument('--pad', type=int, default=2)
|
||
ap.add_argument('--width', type=int, default=440)
|
||
ap.add_argument('--dry-run', action='store_true')
|
||
args = ap.parse_args()
|
||
|
||
img = imread_u(args.src)
|
||
if img is None:
|
||
print('读取源照片失败:', args.src)
|
||
sys.exit(1)
|
||
seed = json.load(open(args.seed, encoding='utf-8'))
|
||
ids = [s['id'] for s in seed['shops']]
|
||
|
||
quad = detect_board_quad(img)
|
||
warped = warp_board(img, quad)
|
||
wh, ww = warped.shape[:2]
|
||
print('透视矫正完成: %dx%d' % (ww, wh))
|
||
|
||
blocks = detect_confident_blocks(warped)
|
||
print('置信照片块: %d 个' % len(blocks))
|
||
if len(blocks) < 20:
|
||
print('置信块太少，终止（避免误裁覆盖好图）')
|
||
sys.exit(2)
|
||
g = fit_grid(blocks)
|
||
print('网格拟合: 行=%s 行距=%.1f 照片=%.0fx%.0f' % (g['rows_found'], g['step'], g['pw'], g['ph']))
|
||
|
||
report = {'warped_size': [ww, wh], 'quad': np.round(quad).astype(int).tolist(),
|
||
'confident': len(blocks), 'detected': [], 'fallback': [], 'skipped': []}
|
||
os.makedirs(args.out, exist_ok=True)
|
||
crops = {}
|
||
half_w = g['pw'] / 2.0
|
||
for ri in range(ROWS):
|
||
for ci in range(COLS):
|
||
sid = 'r%dc%d' % (ri, ci)
|
||
b = g['grid'].get((ri, ci))
|
||
if b is not None:
|
||
x0 = max(0, b['x'] - args.pad)
|
||
y0 = max(0, b['y'] - args.pad)
|
||
x1 = min(ww, b['x'] + b['w'] + args.pad)
|
||
y1 = min(wh, b['y'] + b['h'] + args.pad)
|
||
report['detected'].append(sid)
|
||
else:
|
||
cx = g['col_center'][ci]
|
||
if cx is None:
|
||
report['skipped'].append(sid)
|
||
continue
|
||
x0 = int(max(0, cx - half_w - args.pad))
|
||
x1 = int(min(ww, cx + half_w + args.pad))
|
||
y0 = int(max(0, g['row_top'][ri] - args.pad))
|
||
y1 = int(min(wh, g['row_top'][ri] + g['ph'] + args.pad))
|
||
if not region_has_content(warped, x0, y0, x1 - x0, y1 - y0):
|
||
report['skipped'].append(sid)
|
||
continue
|
||
report['fallback'].append(sid)
|
||
crop = warped[y0:y1, x0:x1]
|
||
if crop.size == 0:
|
||
report['skipped'].append(sid)
|
||
continue
|
||
crop = trim_label(crop)
|
||
scale = args.width / float(crop.shape[1])
|
||
crop = cv2.resize(crop, (args.width, max(1, int(crop.shape[0] * scale))), interpolation=cv2.INTER_AREA)
|
||
crops[sid] = crop
|
||
if not args.dry_run:
|
||
imwrite_u(os.path.join(args.out, sid + '.jpg'), crop, [cv2.IMWRITE_JPEG_QUALITY, 88])
|
||
|
||
# 种子中存在但牌子上不存在的 id：清掉旧误裁图，前端显示占位符
|
||
if not args.dry_run:
|
||
for sid in ids:
|
||
if sid not in crops:
|
||
p = os.path.join(args.out, sid + '.jpg')
|
||
if os.path.exists(p):
|
||
os.remove(p)
|
||
print('清除旧误裁图:', sid)
|
||
|
||
# 拼版预览（11 列 x 7 行，带 id 标注）
|
||
cw, ch = 160, 118
|
||
lab_h = 18
|
||
sheet = np.full((ROWS * (ch + lab_h), COLS * cw, 3), 255, np.uint8)
|
||
for ri in range(ROWS):
|
||
for ci in range(COLS):
|
||
sid = 'r%dc%d' % (ri, ci)
|
||
x, y = ci * cw, ri * (ch + lab_h)
|
||
cv2.putText(sheet, sid, (x + 4, y + 13), cv2.FONT_HERSHEY_SIMPLEX, 0.42, (0, 0, 0), 1)
|
||
c = crops.get(sid)
|
||
if c is None:
|
||
cv2.putText(sheet, 'MISS', (x + 40, y + 70), cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 255), 2)
|
||
continue
|
||
sc = min((cw - 4) / float(c.shape[1]), (ch - 4) / float(c.shape[0]))
|
||
cc = cv2.resize(c, (max(1, int(c.shape[1] * sc)), max(1, int(c.shape[0] * sc))))
|
||
sheet[y + lab_h:y + lab_h + cc.shape[0], x + 2:x + 2 + cc.shape[1]] = cc
|
||
os.makedirs(os.path.dirname(args.preview), exist_ok=True)
|
||
imwrite_u(args.preview, sheet, [cv2.IMWRITE_JPEG_QUALITY, 90])
|
||
|
||
report['written'] = sorted(crops.keys())
|
||
os.makedirs(os.path.dirname(args.report), exist_ok=True)
|
||
json.dump(report, open(args.report, 'w', encoding='utf-8'), ensure_ascii=False, indent=1)
|
||
print('裁切完成: 直检 %d / 兜底 %d / 跳过 %d -> %s' % (
|
||
len(report['detected']), len(report['fallback']), len(report['skipped']), args.preview))
|
||
if report['fallback']:
|
||
print('兜底裁切:', report['fallback'])
|
||
if report['skipped']:
|
||
print('跳过(牌子上不存在):', report['skipped'])
|
||
|
||
|
||
if __name__ == '__main__':
|
||
main()
|