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
This commit is contained in:
Warren
@@ -0,0 +1,291 @@
|
||||
#!/opt/homebrew/bin/python3.11
|
||||
"""
|
||||
Smart Stamp Score v2 - Pure OpenCV but with better stamp signatures
|
||||
Key insight: stamps have BORDER + CENTER pattern with different colors
|
||||
"""
|
||||
|
||||
import os
|
||||
import cv2
|
||||
import json
|
||||
import time
|
||||
import numpy as np
|
||||
|
||||
UUID = "384b0ff44aaaa1f1"
|
||||
VIDEO_PATH = f"output/{UUID}/{UUID}.mp4"
|
||||
OUTPUT_DIR = f"output/{UUID}/smart_stamp_v2"
|
||||
os.makedirs(OUTPUT_DIR, exist_ok=True)
|
||||
CROPS_DIR = os.path.join(OUTPUT_DIR, "crops")
|
||||
os.makedirs(CROPS_DIR, exist_ok=True)
|
||||
|
||||
FRAME_INTERVAL = 5
|
||||
print("=" * 60)
|
||||
print("🔍 Smart Stamp Search v2 - Better Scoring")
|
||||
print("=" * 60)
|
||||
|
||||
cap = cv2.VideoCapture(VIDEO_PATH)
|
||||
fps = cap.get(cv2.CAP_PROP_FPS)
|
||||
total_sec = int(cap.get(cv2.CAP_PROP_FRAME_COUNT) / fps)
|
||||
print(f"📹 Video: {total_sec}s")
|
||||
|
||||
|
||||
def compute_stamp_score(roi, frame):
|
||||
"""
|
||||
Compute how likely a region is a stamp.
|
||||
Stamps have:
|
||||
1. Border pattern (edge density high around perimeter)
|
||||
2. Color diversity (multiple hues)
|
||||
3. Moderate texture (not solid, not pure noise)
|
||||
4. Rectangular shape
|
||||
"""
|
||||
h, w = roi.shape[:2]
|
||||
if h < 10 or w < 10 or h > 200 or w > 200:
|
||||
return 0.0
|
||||
|
||||
aspect = w / h
|
||||
if not (0.3 < aspect < 3.0):
|
||||
return 0.0
|
||||
|
||||
score = 0.0
|
||||
|
||||
# 1. Color diversity (hues)
|
||||
hsv = cv2.cvtColor(roi, cv2.COLOR_BGR2HSV)
|
||||
hue = hsv[:, :, 0]
|
||||
sat = hsv[:, :, 1]
|
||||
val = hsv[:, :, 2]
|
||||
|
||||
# Count significant hues (sat > 30 to ignore grays)
|
||||
mask_color = sat > 30
|
||||
if np.sum(mask_color) < h * w * 0.1:
|
||||
return 0.0 # Too gray/white
|
||||
|
||||
unique_hues = len(np.unique(hue[mask_color]))
|
||||
hue_score = min(1.0, unique_hues / 40)
|
||||
score += hue_score * 0.3
|
||||
|
||||
# 2. Edge density (stamps have patterns/lines)
|
||||
gray = cv2.cvtColor(roi, cv2.COLOR_BGR2GRAY)
|
||||
edges = cv2.Canny(gray, 30, 100)
|
||||
edge_ratio = np.sum(edges > 0) / (h * w)
|
||||
edge_score = min(1.0, edge_ratio / 0.15)
|
||||
score += edge_score * 0.2
|
||||
|
||||
# 3. Border vs center contrast (stamps have borders)
|
||||
border_thickness = max(2, min(h, w) // 6)
|
||||
border = np.ones((h, w), dtype=np.uint8) * 255
|
||||
border[border_thickness:-border_thickness, border_thickness:-border_thickness] = 0
|
||||
center = 255 - border
|
||||
|
||||
border_mean = np.mean(gray[border > 0])
|
||||
center_mean = np.mean(gray[center > 0])
|
||||
border_center_diff = abs(border_mean - center_mean)
|
||||
contrast_score = min(1.0, border_center_diff / 40)
|
||||
score += contrast_score * 0.2
|
||||
|
||||
# 4. Hue variance between border and center
|
||||
border_hue = hue[border > 0][mask_color[border > 0]]
|
||||
center_hue = hue[center > 0][mask_color[center > 0]]
|
||||
|
||||
if len(border_hue) > 5 and len(center_hue) > 5:
|
||||
border_hue_mean = np.mean(border_hue)
|
||||
center_hue_mean = np.mean(center_hue)
|
||||
hue_diff = min(
|
||||
abs(border_hue_mean - center_hue_mean),
|
||||
180 - abs(border_hue_mean - center_hue_mean),
|
||||
)
|
||||
hue_diff_score = min(1.0, hue_diff / 60)
|
||||
score += hue_diff_score * 0.3
|
||||
else:
|
||||
score += 0.1
|
||||
|
||||
return min(1.0, score)
|
||||
|
||||
|
||||
all_results = []
|
||||
start_time = time.time()
|
||||
|
||||
for sec in range(0, total_sec, FRAME_INTERVAL):
|
||||
cap.set(cv2.CAP_PROP_POS_MSEC, sec * 1000)
|
||||
ret, frame = cap.read()
|
||||
if not ret:
|
||||
continue
|
||||
|
||||
elapsed = time.time() - start_time
|
||||
progress = sec / total_sec * 100
|
||||
|
||||
h, w = frame.shape[:2]
|
||||
frame_results = []
|
||||
|
||||
# Collect candidate regions (hands + paper)
|
||||
candidates = []
|
||||
|
||||
# Skin/hand
|
||||
hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)
|
||||
skin = cv2.inRange(hsv, np.array([0, 20, 60]), np.array([25, 180, 255]))
|
||||
skin += cv2.inRange(hsv, np.array([160, 20, 60]), np.array([179, 180, 255]))
|
||||
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (9, 9))
|
||||
skin = cv2.morphologyEx(skin, cv2.MORPH_CLOSE, kernel)
|
||||
skin = cv2.morphologyEx(skin, cv2.MORPH_OPEN, kernel)
|
||||
|
||||
contours, _ = cv2.findContours(skin, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
|
||||
for cnt in contours:
|
||||
area = cv2.contourArea(cnt)
|
||||
if 1500 < area < h * w * 0.35:
|
||||
x, y, cw, ch = cv2.boundingRect(cnt)
|
||||
margin = 50
|
||||
candidates.append(
|
||||
{
|
||||
"type": "hand",
|
||||
"bbox": [
|
||||
max(0, x - margin),
|
||||
max(0, y - margin),
|
||||
min(w, x + cw + margin),
|
||||
min(h, y + ch + margin),
|
||||
],
|
||||
}
|
||||
)
|
||||
|
||||
# Paper/envelope
|
||||
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
|
||||
_, bright = cv2.threshold(gray, 175, 255, cv2.THRESH_BINARY)
|
||||
bright = cv2.morphologyEx(
|
||||
bright, cv2.MORPH_CLOSE, cv2.getStructuringElement(cv2.MORPH_RECT, (5, 5))
|
||||
)
|
||||
contours, _ = cv2.findContours(bright, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
|
||||
for cnt in contours:
|
||||
area = cv2.contourArea(cnt)
|
||||
if 3000 < area < h * w * 0.5:
|
||||
x, y, cw, ch = cv2.boundingRect(cnt)
|
||||
aspect = cw / ch if ch > 0 else 0
|
||||
if 0.2 < aspect < 4.0:
|
||||
margin = 40
|
||||
candidates.append(
|
||||
{
|
||||
"type": "paper",
|
||||
"bbox": [
|
||||
max(0, x - margin),
|
||||
max(0, y - margin),
|
||||
min(w, x + cw + margin),
|
||||
min(h, y + ch + margin),
|
||||
],
|
||||
}
|
||||
)
|
||||
|
||||
# In each candidate, find small stamp-like regions
|
||||
for container in candidates:
|
||||
cx1, cy1, cx2, cy2 = container["bbox"]
|
||||
region = frame[cy1:cy2, cx1:cx2]
|
||||
|
||||
if region.size == 0:
|
||||
continue
|
||||
|
||||
rh, rw = region.shape[:2]
|
||||
region_gray = cv2.cvtColor(region, cv2.COLOR_BGR2GRAY)
|
||||
|
||||
# Find small rectangular shapes via edges
|
||||
edges = cv2.Canny(region_gray, 30, 100)
|
||||
contours_s, _ = cv2.findContours(
|
||||
edges, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE
|
||||
)
|
||||
|
||||
for cnt in contours_s:
|
||||
area = cv2.contourArea(cnt)
|
||||
if 150 < area < 20000:
|
||||
x, y, sw, sh = cv2.boundingRect(cnt)
|
||||
if not (15 < sw < 150 and 15 < sh < 150):
|
||||
continue
|
||||
|
||||
aspect = sw / sh if sh > 0 else 0
|
||||
if not (0.3 < aspect < 3.0):
|
||||
continue
|
||||
|
||||
roi = region[y : y + sh, x : x + sw]
|
||||
if roi.size == 0:
|
||||
continue
|
||||
|
||||
stamp_score = compute_stamp_score(roi, frame)
|
||||
|
||||
if stamp_score > 0.4:
|
||||
ox1 = cx1 + x
|
||||
oy1 = cy1 + y
|
||||
ox2 = cx1 + x + sw
|
||||
oy2 = cy1 + y + sh
|
||||
|
||||
crop = frame[oy1:oy2, ox1:ox2]
|
||||
if crop.size == 0:
|
||||
continue
|
||||
|
||||
frame_results.append(
|
||||
{
|
||||
"timestamp": sec,
|
||||
"container": container["type"],
|
||||
"score": stamp_score,
|
||||
"bbox": [ox1, oy1, ox2, oy2],
|
||||
"size": [sw, sh],
|
||||
"crop": crop,
|
||||
}
|
||||
)
|
||||
|
||||
if frame_results:
|
||||
frame_results.sort(key=lambda x: x["score"], reverse=True)
|
||||
# Keep top 3 per frame
|
||||
top = frame_results[:3]
|
||||
all_results.extend(top)
|
||||
|
||||
print(
|
||||
f" [{sec}s | {progress:.0f}%] Found {len(top)} candidates (top score: {top[0]['score']:.2f})"
|
||||
)
|
||||
|
||||
# Save top crops
|
||||
for r in top:
|
||||
crop_name = f"stamp_{sec}s_{r['container']}_{r['score']:.2f}.jpg"
|
||||
cv2.imwrite(os.path.join(CROPS_DIR, crop_name), r["crop"])
|
||||
|
||||
# Annotate
|
||||
cv2.rectangle(
|
||||
frame,
|
||||
(r["bbox"][0], r["bbox"][1]),
|
||||
(r["bbox"][2], r["bbox"][3]),
|
||||
(0, 255, 0),
|
||||
2,
|
||||
)
|
||||
cv2.putText(
|
||||
frame,
|
||||
f"{r['score']:.2f}",
|
||||
(r["bbox"][0], r["bbox"][1] - 5),
|
||||
cv2.FONT_HERSHEY_SIMPLEX,
|
||||
0.5,
|
||||
(0, 255, 0),
|
||||
1,
|
||||
)
|
||||
|
||||
ann_path = os.path.join(OUTPUT_DIR, f"annotated_{sec}s.jpg")
|
||||
cv2.imwrite(ann_path, frame)
|
||||
else:
|
||||
if sec % 120 == 0:
|
||||
print(f" [{sec // 60}min | {progress:.0f}%] Scanning...")
|
||||
|
||||
cap.release()
|
||||
|
||||
# Sort and deduplicate
|
||||
all_results.sort(key=lambda x: x["score"], reverse=True)
|
||||
seen = set()
|
||||
unique = []
|
||||
for r in all_results:
|
||||
ts = r["timestamp"]
|
||||
if ts not in seen:
|
||||
seen.add(ts)
|
||||
# Remove crop from serializable result
|
||||
result_out = {k: v for k, v in r.items() if k != "crop"}
|
||||
unique.append(result_out)
|
||||
|
||||
print(f"\n{'=' * 60}")
|
||||
print(f"📊 Found {len(unique)} stamp candidates (score > 0.4)")
|
||||
for r in unique:
|
||||
print(
|
||||
f" 🎯 {r['timestamp']}s | {r['container']} | score:{r['score']:.2f} | {r['size'][0]}x{r['size'][1]}px"
|
||||
)
|
||||
|
||||
with open(os.path.join(OUTPUT_DIR, "results.json"), "w") as f:
|
||||
json.dump(unique, f, indent=2)
|
||||
|
||||
print(f"\n🏁 Done. Crops: {CROPS_DIR}")
|
||||
Reference in New Issue
Block a user