"""方法A2：蒙版 CCOEFF_NORMED 多尺度匹配 + 跨尺度峰显著度。 修正方法A的两个问题： 1. CCORR_NORMED 不减均值 → 换 CCOEFF_NORMED（有蒙版），区分度更高 2. 跨尺度直接比分数不公平（小模板占便宜）→ 每尺度算峰显著度 (max-median)/std 输出： - 每对：1.0 尺度参考、最优显著度尺度、该尺度 top-3 峰（NMS）→ 验证干扰结构 - 可视化：mark | top-3 峰局部裁剪 并排图 → try/out/A2/ - 汇总表 → try/out/A2/summary.txt """ from pathlib import Path import cv2 import numpy as np ROOT = Path(__file__).resolve().parent.parent CAP = ROOT / "captchas" OUT = ROOT / "try" / "out" / "A2" OUT.mkdir(parents=True, exist_ok=True) SCALES = np.arange(0.50, 1.51, 0.05) TOP_K = 3 def load_mark(path): """返回 (BGR float32, alpha float32 0~1) 或 (None, None)。""" try: m = cv2.imread(str(path), cv2.IMREAD_UNCHANGED) if m is None or m.ndim < 2: return None, None if m.ndim == 3 and m.shape[2] == 4: return m[..., :3].astype(np.float32), m[..., 3].astype(np.float32) / 255.0 return m.astype(np.float32), np.ones(m.shape[:2], np.float32) except Exception as e: print(f" mark 读取失败: {e}") return None, None def match_ccoeff(big, tpl_f, mask_f): """蒙版 CCOEFF_NORMED。返回响应图或 None。""" try: res = cv2.matchTemplate(big, tpl_f, cv2.TM_CCOEFF_NORMED, mask=mask_f) return np.nan_to_num(res, nan=-1.0, posinf=-1.0, neginf=-1.0).astype(np.float32) except cv2.error as e: print(f" 匹配失败: {e}") return None def scale_response(big, bgr_f, alpha_f, scale): """单尺度匹配，返回 (响应图, 模板宽, 模板高)；失败返回 (None, 0, 0)。""" try: if abs(scale - 1.0) < 1e-9: tpl, mask = bgr_f, alpha_f else: w = max(12, round(bgr_f.shape[1] * scale)) h = max(12, round(bgr_f.shape[0] * scale)) if w >= big.shape[1] or h >= big.shape[0]: return None, 0, 0 tpl = cv2.resize(bgr_f, (w, h), interpolation=cv2.INTER_AREA).astype(np.float32) mask = cv2.resize(alpha_f, (w, h), interpolation=cv2.INTER_AREA).astype(np.float32) res = match_ccoeff(big, tpl, mask) if res is None: return None, 0, 0 return res, int(mask.shape[1]), int(mask.shape[0]) except cv2.error as e: print(f" 尺度失败(scale={scale}): {e}") return None, 0, 0 def prominence(res): """峰显著度：峰高相对响应图整体的突出程度，跨尺度可比。""" try: mx = float(res.max()) med = float(np.median(res)) sd = float(res.std()) return (mx - med) / sd if sd > 1e-6 else 0.0 except Exception: return 0.0 def topk_peaks(res, tpl_w, tpl_h, k=TOP_K): """NMS 取前 k 个峰：返回 [(score, (x, y)), ...]。""" try: r = res.copy() peaks = [] for _ in range(k): _, score, _, loc = cv2.minMaxLoc(r) if score <= -1.0: break peaks.append((float(score), loc)) x0 = max(0, loc[0] - int(tpl_w * 0.7)) y0 = max(0, loc[1] - int(tpl_h * 0.7)) x1 = min(r.shape[1], loc[0] + int(tpl_w * 0.7)) y1 = min(r.shape[0], loc[1] + int(tpl_h * 0.7)) r[y0:y1, x0:x1] = -1.0 return peaks except Exception as e: print(f" 峰提取失败: {e}") return [] def side_by_side(name, mark_bgr, big, peaks, tpl_w, tpl_h): """mark | top-k 峰裁剪 并排图。""" try: mark_u8 = np.clip(mark_bgr, 0, 255).astype(np.uint8) mark_u8 = cv2.copyMakeBorder(mark_u8, 2, 2, 2, 2, cv2.BORDER_CONSTANT, value=(255, 255, 255)) tiles = [cv2.resize(mark_u8, (tpl_w, tpl_h))] for score, (x, y) in peaks: x0, y0 = max(0, x), max(0, y) x1, y1 = min(big.shape[1], x + tpl_w), min(big.shape[0], y + tpl_h) crop = big[y0:y1, x0:x1].copy() if crop.shape[0] != tpl_h or crop.shape[1] != tpl_w: crop = cv2.copyMakeBorder(crop, 0, tpl_h - crop.shape[0], 0, tpl_w - crop.shape[1], cv2.BORDER_CONSTANT, value=(128, 128, 128)) cv2.putText(crop, f"{score:.3f}", (2, 12), cv2.FONT_HERSHEY_SIMPLEX, 0.4, (0, 0, 255), 1) tiles.append(crop) sep = np.full((tpl_h, 4, 3), 255, np.uint8) row = tiles[0] for t in tiles[1:]: row = np.hstack([row, sep, t]) cv2.imwrite(str(OUT / f"{name[:12]}-crops.png"), row) except Exception as e: print(f" 可视化失败: {e}") def process_pair(name, lines): try: big = cv2.imread(str(CAP / f"{name}.jpeg"), cv2.IMREAD_COLOR) if big is None: lines.append(f"{name} SKIP 大图读取失败") return big_f = big.astype(np.float32) bgr_f, alpha_f = load_mark(CAP / f"{name}-mark.png") if bgr_f is None: lines.append(f"{name} SKIP mark 读取失败") return # 参考：1.0 尺度 res10, _, _ = scale_response(big_f, bgr_f, alpha_f, 1.0) if res10 is not None: _, _, _, loc10 = cv2.minMaxLoc(res10) ref = f"1.0尺度峰={float(res10.max()):.3f}@{loc10}" else: ref = "1.0尺度N/A" # 扫尺度，选显著度最高者 best = None # (显著度, 尺度, 响应图, 模板宽, 模板高) curve = [] for sc in SCALES: res, tw_, th_ = scale_response(big_f, bgr_f, alpha_f, float(sc)) if res is None: curve.append(0.0) continue p = prominence(res) curve.append(p) if best is None or p > best[0]: best = (p, float(sc), res, tw_, th_) curve = np.array(curve) if best is None: lines.append(f"{name} SKIP 无有效尺度") return p, sc, res, tw, th = best peaks = topk_peaks(res, tw, th) top = " ".join(f"#{i+1}:{s:.3f}@{loc}" for i, (s, loc) in enumerate(peaks)) print(f"{name[:12]} {ref} 最优尺度={sc:.2f} 显著度={p:.2f} {top}") lines.append(f"{name[:12]}\t{ref}\t尺度={sc:.2f}\t显著度={p:.2f}\t{top}") side_by_side(name, bgr_f, big, peaks, tw, th) # 大图上画 top-3 框 vis = big.copy() colors = [(0, 0, 255), (0, 165, 255), (255, 0, 0)] for i, (s, (x, y)) in enumerate(peaks): cv2.rectangle(vis, (x, y), (x + tw, y + th), colors[i % 3], 2) cv2.imwrite(str(OUT / f"{name[:12]}-match.png"), vis) except Exception as e: print(f"{name[:12]} 处理失败: {e}") lines.append(f"{name[:12]} ERROR {e}") def main(): lines = [] pairs = sorted({p.name.replace("-mark.png", "") for p in CAP.glob("*-mark.png")}) for name in pairs: process_pair(name, lines) (OUT / "summary.txt").write_text("\n".join(lines) + "\n", encoding="utf-8") print(f"\n结果与 summary 已写入 {OUT}/") if __name__ == "__main__": main()