update

services/extract_service.py

@@ -5,95 +5,40 @@ import numpy as np
 import sys
 sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
 
-from utils.lbp_features import preprocess_face, FACE_SIZE
+from utils.lbp_features import FACE_SIZE
-
-BLUR_THRESHOLD = 30.0
-MIN_FACE_RATIO = 0.15
 
 face_cascade = cv2.CascadeClassifier(
     cv2.data.haarcascades + 'haarcascade_frontalface_default.xml'
 )
 
 
-def get_blur_score(img):
+def crop_wajah(gray):
-    return cv2.Laplacian(img, cv2.CV_64F).var()
+    """Crop wajah persis seperti notebook ablasi jalur 2."""
-
+    wajah = face_cascade.detectMultiScale(gray, 1.1, 5, minSize=(50, 50))
-
+    if len(wajah) == 0:
-def detect_frontal_face(gray_frame):
+        return None, None
-    h, w = gray_frame.shape
-    min_size = int(min(h, w) * MIN_FACE_RATIO)
-
-    faces = face_cascade.detectMultiScale(
-        gray_frame, scaleFactor=1.1, minNeighbors=5,
-        minSize=(min_size, min_size)
-    )
-
-    if len(faces) == 0:
-        faces = face_cascade.detectMultiScale(
-            gray_frame, scaleFactor=1.05, minNeighbors=4,
-            minSize=(min_size, min_size)
-        )
-
-    if len(faces) == 0:
-        return None
-
-    faces = sorted(faces, key=lambda f: f[2] * f[3], reverse=True)
-    return faces[0]
-
-
-def estimate_yaw_from_symmetry(gray_face):
-    h, w = gray_face.shape
-    mid = w // 2
-
-    left_half = gray_face[:, :mid].astype(np.float64)
-    right_half = cv2.flip(gray_face[:, mid:], 1).astype(np.float64)
-
-    min_w = min(left_half.shape[1], right_half.shape[1])
-    left_half = left_half[:, :min_w]
-    right_half = right_half[:, :min_w]
-
-    if left_half.size == 0 or right_half.size == 0:
-        return 999.0
-
-    left_mean = np.mean(left_half)
-    right_mean = np.mean(right_half)
-
-    diff = abs(left_mean - right_mean)
-    estimated_yaw = diff * 0.8
-
-    return estimated_yaw
-
-
-def process_frame(frame, gray_frame):
-    face_rect = detect_frontal_face(gray_frame)
-    if face_rect is None:
-        return None, None, "no_face", 0.0, 0.0
-
-    (x, y, w, h) = face_rect
 
+    (x, y, w, h) = max(wajah, key=lambda r: r[2] * r[3])
     sisi = max(w, h)
     cx, cy = x + w // 2, y + h // 2
     half = sisi // 2
     y1 = max(0, cy - half)
-    y2 = min(gray_frame.shape[0], cy + half)
+    y2 = min(gray.shape[0], cy + half)
     x1 = max(0, cx - half)
-    x2 = min(gray_frame.shape[1], cx + half)
+    x2 = min(gray.shape[1], cx + half)
 
-    face_crop_gray = gray_frame[y1:y2, x1:x2]
+    face_crop_gray = cv2.resize(gray[y1:y2, x1:x2], FACE_SIZE)
-    face_crop_color = frame[y1:y2, x1:x2]
+    face_crop_color = None
-
+    return face_crop_gray, (x1, y1, x2, y2)
-    face_resized = cv2.resize(face_crop_gray, FACE_SIZE, interpolation=cv2.INTER_AREA)
-
-    blur_score = get_blur_score(face_resized)
-    if blur_score < BLUR_THRESHOLD:
-        return None, None, f"blur ({round(blur_score, 1)})", blur_score, 0.0
-
-    yaw_estimate = estimate_yaw_from_symmetry(face_resized)
-
-    return face_resized, face_crop_color, "ok", blur_score, yaw_estimate
 
 
-def extract_frames(video_path, output_dir, target_frames=30):
+def extract_frames(video_path, output_dir, target_frames=200):
+    """
+    Ekstraksi frame sesuai ablasi jalur 2:
+    1. Baca SEMUA frame
+    2. Crop SEMUA frame (Haar Cascade)
+    3. Sampling merata (np.linspace) dari yang berhasil crop
+    """
     if not os.path.exists(video_path):
         raise Exception(f"Video tidak ditemukan: {video_path}")
 
@@ -114,11 +59,9 @@ def extract_frames(video_path, output_dir, target_frames=30):
     if total_frames <= 0:
         raise Exception("Video tidak valid (0 frame).")
 
-    candidates = []
+    semua_crop = []
-    frame_idx = 0
     skipped_no_face = 0
-    skipped_blur = 0
+    frame_idx = 0
-    skipped_side = 0
 
     while True:
         ret, frame = cap.read()
@@ -126,54 +69,42 @@ def extract_frames(video_path, output_dir, target_frames=30):
             break
 
         gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
-        face_img, face_color, status, blur_score, yaw = process_frame(frame, gray)
+        face_gray, bbox = crop_wajah(gray)
 
-        if face_img is None:
+        if face_gray is None:
-            if "blur" in status:
+            skipped_no_face += 1
-                skipped_blur += 1
-            else:
-                skipped_no_face += 1
             frame_idx += 1
             continue
 
-        candidates.append({
+        (x1, y1, x2, y2) = bbox
+        face_color = frame[y1:y2, x1:x2]
+
+        semua_crop.append({
             'frame_idx': frame_idx,
-            'face_gray': face_img,
+            'face_gray': face_gray,
             'face_color': face_color,
-            'blur_score': blur_score,
-            'yaw': yaw
         })
 
         frame_idx += 1
 
     cap.release()
 
-    if len(candidates) == 0:
+    total_crop = len(semua_crop)
+
+    if total_crop == 0:
         raise Exception(
-            "Tidak ada frame wajah frontal berkualitas yang berhasil diekstrak. "
+            "Tidak ada frame wajah yang berhasil diekstrak. "
-            "Pastikan wajah menghadap depan dengan pencahayaan cukup."
+            "Pastikan wajah terlihat jelas di video."
         )
 
-    candidates.sort(key=lambda c: c['blur_score'], reverse=True)
+    if total_crop <= target_frames:
-
+        hasil = semua_crop
-    if len(candidates) > target_frames:
+    else:
-        candidates_by_idx = sorted(candidates, key=lambda c: c['frame_idx'])
+        indices = np.linspace(0, total_crop - 1, target_frames, dtype=int)
-
+        hasil = [semua_crop[i] for i in indices]
-        chunk_size = len(candidates_by_idx) // target_frames
-        selected = []
-
-        for i in range(target_frames):
-            start = i * chunk_size
-            end = min(start + chunk_size, len(candidates_by_idx))
-            chunk = candidates_by_idx[start:end]
-
-            best_in_chunk = max(chunk, key=lambda c: c['blur_score'])
-            selected.append(best_in_chunk)
-
-        candidates = sorted(selected, key=lambda c: c['frame_idx'])
 
     saved_count = 0
-    for cand in candidates:
+    for cand in hasil:
         filename = f"frame_{saved_count:03d}.jpg"
         filename_raw = f"raw_frame_{saved_count:03d}.jpg"
         cv2.imwrite(
@@ -184,14 +115,15 @@ def extract_frames(video_path, output_dir, target_frames=30):
         cv2.imwrite(os.path.join(output_dir, filename_raw), cand['face_color'])
         saved_count += 1
 
+    interval = total_crop / saved_count if saved_count > 0 else 0
+
     return {
         "total_video_frames": total_frames,
         "video_fps": round(fps, 1),
-        "total_candidates": len(candidates),
+        "total_crop_detected": total_crop,
         "total_extracted": saved_count,
         "target_frames": target_frames,
         "skipped_no_face": skipped_no_face,
-        "skipped_blur": skipped_blur,
+        "sampling_interval": round(interval, 1),
-        "skipped_side_face": skipped_side,
         "output_dir": output_dir
     }