feat: update Python processors and add utility scripts

- Update ASR, face, OCR, pose processors - Add release pre-flight check script - Add synonym generation, chunk processing scripts - Add face recognition, stamp search utilities
2026-04-30 15:07:49 +08:00
parent f4697396e4
commit 8f05a7c188
256 changed files with 60505 additions and 299 deletions
--- a/scripts/crop_stamp_closeup.py
+++ b/scripts/crop_stamp_closeup.py
@@ -0,0 +1,80 @@
+#!/opt/homebrew/bin/python3.11
+"""
+Crop stamp from magnifying glass scene at highest quality
+"""
+
+import cv2
+import os
+
+BASE_DIR = "output/384b0ff44aaaa1f1/stamp_closeup"
+OUTPUT_DIR = "output/384b0ff44aaaa1f1/stamp_closeup/cropped"
+os.makedirs(OUTPUT_DIR, exist_ok=True)
+
+# Bounding boxes from OWL-ViT detection
+# Format: [x1, y1, x2, y2]
+DETECTIONS = {
+    "5733": [519, 147, 1383, 931],  # Best frame
+    "5734": [516, 147, 1384, 936],
+    "5735": [528, 151, 1381, 936],
+}
+
+# Also extract a wider area to see context
+WIDER_MARGIN = 100
+
+for sec, bbox in DETECTIONS.items():
+    frame_path = os.path.join(BASE_DIR, f"frame_{sec}s.jpg")
+    img = cv2.imread(frame_path)
+    if img is None:
+        continue
+
+    x1, y1, x2, y2 = bbox
+
+    # 1. Crop exact detection area
+    crop = img[y1:y2, x1:x2]
+    if crop.size > 0:
+        cv2.imwrite(os.path.join(OUTPUT_DIR, f"stamp_{sec}s_crop.jpg"), crop)
+        print(f"  📍 {sec}s: Saved crop ({crop.shape[1]}x{crop.shape[0]})")
+
+    # 2. Crop wider area with margin
+    wx1 = max(0, x1 - WIDER_MARGIN)
+    wy1 = max(0, y1 - WIDER_MARGIN)
+    wx2 = min(img.shape[1], x2 + WIDER_MARGIN)
+    wy2 = min(img.shape[0], y2 + WIDER_MARGIN)
+    wide_crop = img[wy1:wy2, wx1:wx2]
+    if wide_crop.size > 0:
+        cv2.imwrite(os.path.join(OUTPUT_DIR, f"stamp_{sec}s_wide.jpg"), wide_crop)
+        print(
+            f"  📍 {sec}s: Saved wide crop ({wide_crop.shape[1]}x{wide_crop.shape[0]})"
+        )
+
+    # 3. Annotate full frame with green box
+    annotated = img.copy()
+    cv2.rectangle(annotated, (x1, y1), (x2, y2), (0, 255, 0), 4)
+    cv2.putText(
+        annotated,
+        "STAMP AREA",
+        (x1, y1 - 15),
+        cv2.FONT_HERSHEY_SIMPLEX,
+        1.0,
+        (0, 255, 0),
+        3,
+    )
+    cv2.imwrite(os.path.join(OUTPUT_DIR, f"annotated_{sec}s.jpg"), annotated)
+
+    # 4. Draw on the original HQ frame too
+    hq_path = os.path.join(BASE_DIR, f"frame_{sec}s.jpg")
+    hq_img = cv2.imread(hq_path)
+    if hq_img is not None:
+        cv2.rectangle(hq_img, (x1, y1), (x2, y2), (0, 255, 0), 4)
+        cv2.putText(
+            hq_img,
+            "STAMP",
+            (x1, y1 - 15),
+            cv2.FONT_HERSHEY_SIMPLEX,
+            1.0,
+            (0, 255, 0),
+            3,
+        )
+        cv2.imwrite(os.path.join(OUTPUT_DIR, f"full_annotated_{sec}s.jpg"), hq_img)
+
+print(f"\n🏁 Done. Check {OUTPUT_DIR}")