編集履歴

質問編集履歴

コードを修正しました。

2020/07/01 01:30

投稿

YYJP

スコア23

test CHANGED Viewed

File without changes

test CHANGED Viewed

@@ -130,115 +130,127 @@
     frame = imutils.resize(frame,width=300)
-    gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
+    ####
-    faces = face_detection.detectMultiScale(gray,scaleFactor=1.1,minNeighbors=5,minSize=(30,30),flags=cv2.CASCADE_SCALE_IMAGE)
-    canvas = np.zeros((250, 300, 3), dtype="uint8")
-    frameClone = frame.copy()
+    prev_time = time.time()
+    while True:
+        curr_time = time.time()
-    if len(faces) > 0:
+        if curr_time - prev_time >= 0.1:
-        faces = sorted(faces, reverse=True,
-        key=lambda x: (x[2] - x[0]) * (x[3] - x[1]))[0]
-        (fX, fY, fW, fH) = faces
-                    # Extract the ROI of the face from the grayscale image, resize it to a fixed 28x28 pixels, and then prepare
-            # the ROI for classification via the CNN
-        roi = gray[fY:fY + fH, fX:fX + fW]
-        roi = cv2.resize(roi, (64, 64))
-        roi = roi.astype("float") / 255.0
-        roi = img_to_array(roi)
-        roi = np.expand_dims(roi, axis=0)
+            gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
+            faces = face_detection.detectMultiScale(gray,scaleFactor=1.1,minNeighbors=5,minSize=(30,30),flags=cv2.CASCADE_SCALE_IMAGE)
+            canvas = np.zeros((250, 300, 3), dtype="uint8")
+            frameClone = frame.copy()
+            if len(faces) > 0:
-        preds = emotion_classifier.predict(roi)[0]
+                faces = sorted(faces, reverse=True,
-        with open(filenameTXT, 'a') as f:
+                key=lambda x: (x[2] - x[0]) * (x[3] - x[1]))[0]
-################この処理が、動画に対し0.1秒刻みでなされるようにしたい##################
-            print(preds, file=f)
+                (fX, fY, fW, fH) = faces
-####################################################################################
-        emotion_probability = np.max(preds)
-        label = EMOTIONS[preds.argmax()]
-        ###
-        time.sleep(1)
-        ###
-    else: continue
-    for (i, (emotion, prob)) in enumerate(zip(EMOTIONS, preds)):
+                            # Extract the ROI of the face from the grayscale image, resize it to a fixed 28x28 pixels, and then prepare
-                # construct the label text
-                text = "{}: {:.2f}%".format(emotion, prob * 100)
-                # draw the label + probability bar on the canvas
+                    # the ROI for classification via the CNN
+                roi = gray[fY:fY + fH, fX:fX + fW]
+                roi = cv2.resize(roi, (64, 64))
+                roi = roi.astype("float") / 255.0
+                roi = img_to_array(roi)
-               # emoji_face = feelings_faces[np.argmax(preds)]
+                roi = np.expand_dims(roi, axis=0)
+                preds = emotion_classifier.predict(roi)[0]
+                with open(filenameTXT, 'a') as f:
+                #print(preds)
+                    print(preds, file=f)
+                emotion_probability = np.max(preds)
+                label = EMOTIONS[preds.argmax()]
+                ###
+                time.sleep(1)
+                ###
+            else: continue
+            for (i, (emotion, prob)) in enumerate(zip(EMOTIONS, preds)):
+                        # construct the label text
+                        text = "{}: {:.2f}%".format(emotion, prob * 100)
+                        # draw the label + probability bar on the canvas
+                       # emoji_face = feelings_faces[np.argmax(preds)]
-                w = int(prob * 300)
+                        w = int(prob * 300)
-                cv2.rectangle(canvas, (7, (i * 35) + 5),
+                        cv2.rectangle(canvas, (7, (i * 35) + 5),
-                (w, (i * 35) + 35), (0, 0, 255), -1)
+                        (w, (i * 35) + 35), (0, 0, 255), -1)
-                cv2.putText(canvas, text, (10, (i * 35) + 23),
+                        cv2.putText(canvas, text, (10, (i * 35) + 23),
-                cv2.FONT_HERSHEY_SIMPLEX, 0.45,
+                        cv2.FONT_HERSHEY_SIMPLEX, 0.45,
-                (255, 255, 255), 2)
+                        (255, 255, 255), 2)
-                cv2.putText(frameClone, label, (fX, fY - 10),
+                        cv2.putText(frameClone, label, (fX, fY - 10),
-                cv2.FONT_HERSHEY_SIMPLEX, 0.45, (0, 0, 255), 2)
+                        cv2.FONT_HERSHEY_SIMPLEX, 0.45, (0, 0, 255), 2)
-                cv2.rectangle(frameClone, (fX, fY), (fX + fW, fY + fH),
+                        cv2.rectangle(frameClone, (fX, fY), (fX + fW, fY + fH),
-                              (0, 0, 255), 2)
+                                      (0, 0, 255), 2)
-#    for c in range(0, 3):
+        #    for c in range(0, 3):
-#        frame[200:320, 10:130, c] = emoji_face[:, :, c] * \
+        #        frame[200:320, 10:130, c] = emoji_face[:, :, c] * \
-#        (emoji_face[:, :, 3] / 255.0) + frame[200:320,
+        #        (emoji_face[:, :, 3] / 255.0) + frame[200:320,
-#        10:130, c] * (1.0 - emoji_face[:, :, 3] / 255.0)
+        #        10:130, c] * (1.0 - emoji_face[:, :, 3] / 255.0)
+        prev_time = curr_time
+    ####
     cv2.imshow('your_face', frameClone)

タイトルを修正しました。

2020/07/01 01:30

投稿

YYJP

スコア23

test CHANGED Viewed

	@@ -1 +1 @@
1	- 動画を0.1秒刻みで解析したい
1	+ 表情認識AIで、動画内の表情を0.1秒刻みで解析したい

test CHANGED Viewed

@@ -40,6 +40,12 @@
+下記見づらいコードですが、
+何卒、よろしくお願いいたします。
 ### 該当のソースコード