Upload api.py

api.py

@@ -220,16 +220,22 @@ def process_video_job(job_id: str):
             crops_meta: list[dict] = []
 
             saved_count = 0
+            frames_processed = 0
+            frames_with_faces = 0
             for frame_idx in frame_indices:
                 cap.set(cv2.CAP_PROP_POS_FRAMES, int(frame_idx))
                 ret2, frame = cap.read()
                 if not ret2:
                     continue
+                frames_processed += 1
                 rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
 
                 if _use_fr and face_recognition is not None:
                     boxes = face_recognition.face_locations(rgb, model="hog")  # CPU HOG
                     encs = face_recognition.face_encodings(rgb, boxes)
+                    if boxes:
+                        frames_with_faces += 1
+                        print(f"[{job_id}] Frame {frame_idx}: {len(boxes)} cara(s) detectada(s) con face_recognition")
                     for (top, right, bottom, left), e in zip(boxes, encs):
                         crop = frame[top:bottom, left:right]
                         if crop.size == 0:
@@ -260,10 +266,32 @@ def process_video_job(job_id: str):
                                 face_cascade = None
                             boxes_haar = []
                             if face_cascade is not None and not face_cascade.empty():
-                                faces_haar = face_cascade.detectMultiScale(gray, scaleFactor=1.1, minNeighbors=5, minSize=(40, 40))
+                                faces_haar = face_cascade.detectMultiScale(gray, scaleFactor=1.05, minNeighbors=3, minSize=(30, 30))
                                 for (x, y, w, h) in faces_haar:
                                     top, left, bottom, right = max(0, y), max(0, x), min(frame.shape[0], y+h), min(frame.shape[1], x+w)
                                     boxes_haar.append((top, right, bottom, left))
+                            
+                            # Si Haar no detecta nada, intentar con DeepFace directamente
+                            if not boxes_haar:
+                                try:
+                                    tmp_detect = faces_root / f"detect_{frame_idx:06d}.jpg"
+                                    cv2.imwrite(str(tmp_detect), frame)
+                                    detect_result = DeepFace.extract_faces(img_path=str(tmp_detect), detector_backend='opencv', enforce_detection=False)
+                                    for det in detect_result:
+                                        facial_area = det.get('facial_area', {})
+                                        if facial_area:
+                                            x, y, w, h = facial_area.get('x', 0), facial_area.get('y', 0), facial_area.get('w', 0), facial_area.get('h', 0)
+                                            if w > 20 and h > 20:
+                                                top, left, bottom, right = max(0, y), max(0, x), min(frame.shape[0], y+h), min(frame.shape[1], x+w)
+                                                boxes_haar.append((top, right, bottom, left))
+                                    tmp_detect.unlink(missing_ok=True)
+                                except Exception as _e_detect:
+                                    print(f"[{job_id}] Frame {frame_idx}: DeepFace extract_faces error: {_e_detect}")
+                            
+                            if boxes_haar:
+                                frames_with_faces += 1
+                                print(f"[{job_id}] Frame {frame_idx}: {len(boxes_haar)} cara(s) detectada(s) con Haar/DeepFace")
+                            
                             for (top, right, bottom, left) in boxes_haar:
                                 crop = frame[top:bottom, left:right]
                                 if crop.size == 0:
@@ -289,6 +317,8 @@ def process_video_job(job_id: str):
                             print(f"[{job_id}] DeepFace fallback error: {_e_df}")
             cap.release()
 
+            print(f"[{job_id}] ✓ Frames procesados: {frames_processed}/{len(frame_indices)}")
+            print(f"[{job_id}] ✓ Frames con caras: {frames_with_faces}")
             print(f"[{job_id}] ✓ Caras detectadas (embeddings): {len(embeddings)}")
 
             # Clustering DBSCAN de caras como en 'originales'