111

autoCut.py

@@ -0,0 +1,209 @@
+import cv2
+import numpy as np
+import os
+from pathlib import Path
+
+# ========== 基础配置（只用填这几个，不用改其他） ==========
+INPUT_FOLDER  = "pages"
+OUTPUT_FOLDER = "chars_auto"
+
+# 第一个字中心点、最后一个字中心点
+CX0, CY0 = 1027, 1257
+CX1, CY1 = 4029, 5673
+
+CHAR_SIZE = 715
+ROWS = 5
+COLS = 5
+
+# 搜索范围扩展（像素）
+SEARCH_PAD = 150
+
+# 偏移修正最大幅度（像素）
+MAX_SHIFT = 100
+# ==========================================================
+
+Path(OUTPUT_FOLDER).mkdir(exist_ok=True)
+
+# 兼容中文路径读图
+def imread_unicode(path):
+    return cv2.imdecode(np.fromfile(path, dtype=np.uint8), cv2.IMREAD_COLOR)
+
+# 兼容中文路径存图
+def imwrite_unicode(path, img):
+    cv2.imencode('.png', img)[1].tofile(path)
+
+def get_char_center_from_bbox(
+    img_gray,
+    roi_x1,
+    roi_y1,
+    roi_x2,
+    roi_y2,
+    target_cx=None,
+    target_cy=None,
+    max_shift=MAX_SHIFT,
+):
+    """
+    在理论区域内，自动计算文字的真实边界框中心
+    返回：真实中心点 (cx, cy)
+    """
+    # 截取局部ROI
+    roi = img_gray[roi_y1:roi_y2, roi_x1:roi_x2]
+    roi_h, roi_w = roi.shape[:2]
+
+    blur = cv2.GaussianBlur(roi, (5, 5), 0)
+    _, binary = cv2.threshold(blur, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)
+
+    kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5, 5))
+    binary = cv2.morphologyEx(binary, cv2.MORPH_CLOSE, kernel, iterations=1)
+
+    num_labels, _, stats, centroids = cv2.connectedComponentsWithStats(binary, connectivity=8)
+    if num_labels <= 1:
+        if target_cx is not None and target_cy is not None:
+            return float(target_cx), float(target_cy)
+        cx = (roi_x1 + roi_x2) / 2.0
+        cy = (roi_y1 + roi_y2) / 2.0
+        return cx, cy
+
+    roi_area = float(roi_h * roi_w)
+    min_area = max(300.0, roi_area * 0.002)
+
+    if target_cx is None:
+        tx = roi_w / 2.0
+    else:
+        tx = float(target_cx - roi_x1)
+    if target_cy is None:
+        ty = roi_h / 2.0
+    else:
+        ty = float(target_cy - roi_y1)
+
+    gate = float(max(40.0, float(max_shift) + 20.0))
+
+    best_score = None
+    best_center = None
+    for i in range(1, num_labels):
+        x, y, w, h, area = stats[i]
+        area = float(area)
+        if area < min_area:
+            continue
+
+        box_area = float(w * h) if w > 0 and h > 0 else 1.0
+        fill = area / box_area
+
+        if (w > 0.85 * roi_w or h > 0.85 * roi_h) and fill < 0.08:
+            continue
+
+        aspect = float(w) / (float(h) + 1e-6)
+        if (aspect > 12.0 or aspect < (1.0 / 12.0)) and fill < 0.15:
+            continue
+
+        cx, cy = centroids[i]
+        if abs(float(cx) - tx) > gate or abs(float(cy) - ty) > gate:
+            continue
+        dx = (float(cx) - tx) / (roi_w + 1e-6)
+        dy = (float(cy) - ty) / (roi_h + 1e-6)
+        dist2 = dx * dx + dy * dy
+        score = area * (fill + 0.2) * np.exp(-16.0 * dist2)
+
+        if best_score is None or score > best_score:
+            best_score = score
+            best_center = (float(cx), float(cy))
+
+    if best_center is None:
+        min_area_relaxed = max(100.0, roi_area * 0.0005)
+        for i in range(1, num_labels):
+            x, y, w, h, area = stats[i]
+            area = float(area)
+            if area < min_area_relaxed:
+                continue
+
+            box_area = float(w * h) if w > 0 and h > 0 else 1.0
+            fill = area / box_area
+            if (w > 0.90 * roi_w or h > 0.90 * roi_h) and fill < 0.06:
+                continue
+
+            cx, cy = centroids[i]
+            if abs(float(cx) - tx) > gate or abs(float(cy) - ty) > gate:
+                continue
+            score = area * (fill + 0.2)
+            if best_score is None or score > best_score:
+                best_score = score
+                best_center = (float(cx), float(cy))
+
+    if best_center is None:
+        if target_cx is not None and target_cy is not None:
+            return float(target_cx), float(target_cy)
+        cx = (roi_x1 + roi_x2) / 2.0
+        cy = (roi_y1 + roi_y2) / 2.0
+        return cx, cy
+
+    return roi_x1 + best_center[0], roi_y1 + best_center[1]
+
+def process_page(img_path, page_idx):
+    img = imread_unicode(str(img_path))
+    if img is None:
+        print(f"跳过无法读取：{img_path.name}")
+        return
+    h, w = img.shape[:2]
+    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
+
+    # 生成理论网格行列间隔
+    step_x = (CX1 - CX0) / (COLS - 1)
+    step_y = (CY1 - CY0) / (ROWS - 1)
+
+    for row in range(ROWS):
+        for col in range(COLS):
+            # 理论中心点
+            theo_cx = CX0 + col * step_x
+            theo_cy = CY0 + row * step_y
+
+            # 理论区域ROI范围
+            r_x1 = int(theo_cx - CHAR_SIZE // 2 - SEARCH_PAD)
+            r_y1 = int(theo_cy - CHAR_SIZE // 2 - SEARCH_PAD)
+            r_x2 = int(theo_cx + CHAR_SIZE // 2 + SEARCH_PAD)
+            r_y2 = int(theo_cy + CHAR_SIZE // 2 + SEARCH_PAD)
+
+            # 边界保护
+            r_x1 = max(0, r_x1)
+            r_y1 = max(0, r_y1)
+            r_x2 = min(w, r_x2)
+            r_y2 = min(h, r_y2)
+
+            # 自动获取真实文字边界框中心（只允许小幅修正）
+            detect_cx, detect_cy = get_char_center_from_bbox(
+                gray, r_x1, r_y1, r_x2, r_y2, theo_cx, theo_cy, max_shift=MAX_SHIFT
+            )
+            dx = float(detect_cx - theo_cx)
+            dy = float(detect_cy - theo_cy)
+            dx = float(np.clip(dx, -MAX_SHIFT, MAX_SHIFT))
+            dy = float(np.clip(dy, -MAX_SHIFT, MAX_SHIFT))
+            real_cx = float(theo_cx + dx)
+            real_cy = float(theo_cy + dy)
+
+            # 用真实中心裁切 715x715
+            x1 = int(round(real_cx - CHAR_SIZE / 2.0))
+            y1 = int(round(real_cy - CHAR_SIZE / 2.0))
+            x2 = x1 + CHAR_SIZE
+            y2 = y1 + CHAR_SIZE
+
+            canvas = np.full((CHAR_SIZE, CHAR_SIZE, 3), 255, dtype=np.uint8)
+            sx1 = max(0, x1)
+            sy1 = max(0, y1)
+            sx2 = min(w, x2)
+            sy2 = min(h, y2)
+            src = img[sy1:sy2, sx1:sx2]
+
+            dx = max(0, -x1)
+            dy = max(0, -y1)
+            canvas[dy:dy + src.shape[0], dx:dx + src.shape[1]] = src
+            crop = canvas
+            fname = f"page{page_idx}_r{row}_c{col}.png"
+            save_path = os.path.join(OUTPUT_FOLDER, fname)
+            imwrite_unicode(save_path, crop)
+
+if __name__ == "__main__":
+    print("开始 5×5 逐字自动边界检测中心定位切割...")
+    img_list = sorted(Path(INPUT_FOLDER).glob("*.png"))
+    for idx, f in enumerate(img_list):
+        process_page(f, idx + 1)
+        print(f"已完成：{f.name}")
+    print("✅ 全部自动切割+自动边界检测定位完成！")