douyin-captcha/try/method_f_contour.py

"""方法F：轮廓候选匹配。

适用于 mark 的 RGB 颜色与大图目标不同、但 alpha 轮廓保持一致的样本。
流程：
1. 从大图生成边缘并提取外部轮廓；
2. 对 mark alpha 轮廓做缩放/旋转模板；
3. 用轮廓形状相似度 + 面积/边界覆盖率筛选候选。

输出：try/out/F/{*-match.png,summary.txt}
"""
from pathlib import Path
import math
import cv2
import numpy as np

ROOT = Path(__file__).resolve().parent.parent
CAP = ROOT / "captchas"
OUT = ROOT / "try" / "out" / "F"
OUT.mkdir(parents=True, exist_ok=True)

SCALES = np.arange(0.35, 1.31, 0.05)
ANGLES = np.arange(-180.0, 180.0, 15.0)
TOP_K = 5


def files_for(prefix):
    bigs = [p for p in CAP.glob(f"{prefix}*.jpeg") if "-mark" not in p.stem]
    if not bigs:
        return None, None
    big = bigs[0]
    return big, CAP / f"{big.stem}-mark.png"


def read_shapes(mark_path, big_path):
    try:
        mark = cv2.imread(str(mark_path), cv2.IMREAD_UNCHANGED)
        big = cv2.imread(str(big_path), cv2.IMREAD_COLOR)
        if mark is None or big is None:
            return None
        alpha = mark[..., 3] if mark.ndim == 3 and mark.shape[2] == 4 else np.full(mark.shape[:2], 255, np.uint8)
        mask = (alpha > 128).astype(np.uint8) * 255
        contours, _ = cv2.findContours(mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
        if not contours:
            return None
        mark_contour = max(contours, key=cv2.contourArea)
        gray = cv2.cvtColor(big, cv2.COLOR_BGR2GRAY)
        # 目标通常与局部背景有明显亮度差；保留边缘并闭合轮廓。
        edges = cv2.Canny(gray, 40, 120)
        edges = cv2.morphologyEx(edges, cv2.MORPH_CLOSE, np.ones((3, 3), np.uint8), iterations=2)
        return big, mark_contour, edges
    except Exception as e:
        print(f"  读取失败: {e}")
        return None


def transform_contour(contour, scale, angle):
    try:
        pts = contour.reshape(-1, 2).astype(np.float32)
        center = pts.mean(axis=0)
        pts = (pts - center) * scale
        theta = math.radians(angle)
        rot = np.array([[math.cos(theta), -math.sin(theta)],
                        [math.sin(theta), math.cos(theta)]], dtype=np.float32)
        return (pts @ rot.T).astype(np.float32)
    except Exception:
        return None


def contour_score(mark_contour, candidate):
    try:
        # matchShapes 对平移/尺度基本不敏感，旋转也较稳定；用于形状初筛。
        return float(cv2.matchShapes(mark_contour, candidate, cv2.CONTOURS_MATCH_I1, 0.0))
    except cv2.error:
        return 1e9


def process(prefix, lines):
    try:
        big_path, mark_path = files_for(prefix)
        if big_path is None:
            lines.append(f"{prefix}\tSKIP\t文件缺失")
            return
        loaded = read_shapes(mark_path, big_path)
        if loaded is None:
            lines.append(f"{prefix}\tSKIP\t读取失败")
            return
        big, mark_contour, edges = loaded
        contours, _ = cv2.findContours(edges, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
        mark_area = max(cv2.contourArea(mark_contour), 1.0)
        candidates = []
        for contour in contours:
            area = cv2.contourArea(contour)
            if area < mark_area * 0.08 or area > mark_area * 20:
                continue
            score = contour_score(mark_contour, contour)
            x, y, w, h = cv2.boundingRect(contour)
            candidates.append((score, area, x, y, w, h))
        candidates.sort(key=lambda item: item[0])
        kept = []
        for item in candidates:
            _, _, x, y, w, h = item
            cx, cy = x + w / 2.0, y + h / 2.0
            if all(math.hypot(cx - (q[2] + q[4] / 2), cy - (q[3] + q[5] / 2)) > 0.5 * max(w, h)
                   for q in kept):
                kept.append(item)
            if len(kept) >= TOP_K:
                break
        if not kept:
            lines.append(f"{prefix}\tSKIP\t无轮廓候选")
            return
        best = kept[0]
        score, area, x, y, w, h = best
        print(f"{prefix}  shape={score:.4f} area={area:.0f} offset=({x},{y}) size=({w},{h}) top={len(kept)}")
        lines.append(f"{prefix}\tshape={score:.4f}\tarea={area:.0f}\toffset=({x},{y})\t"
                     f"size=({w},{h})\ttop={len(kept)}")
        vis = big.copy()
        for i, item in enumerate(kept):
            _, _, px, py, pw, ph = item
            color = (0, 0, 255) if i == 0 else (255, 0, 0)
            cv2.rectangle(vis, (px, py), (px + pw, py + ph), color, 2)
            cv2.putText(vis, str(i + 1), (px + 2, py + 16), cv2.FONT_HERSHEY_SIMPLEX,
                        0.55, color, 2)
        cv2.imwrite(str(OUT / f"{prefix}-match.png"), vis)
    except Exception as e:
        print(f"{prefix}  处理失败: {e}")
        lines.append(f"{prefix}\tERROR\t{e}")


def main():
    lines = []
    prefixes = sorted({p.name.split("~", 1)[0] for p in CAP.glob("*.jpeg")
                       if "-mark" not in p.stem})
    for prefix in prefixes:
        process(prefix, lines)
    (OUT / "summary.txt").write_text("\n".join(lines) + "\n", encoding="utf-8")
    print(f"\n结果已写入 {OUT}/")


if __name__ == "__main__":
    main()