Updated textAnalyze(NLTK).py.py

videoAnalyzing(expressions).py

@@ -9,65 +9,107 @@ from keras.models import Sequential, load_model
 from keras.preprocessing.image import load_img
 from keras.preprocessing.image import img_to_array
 import matplotlib.pyplot as plt
+from skimage import io
+import os
+import cv2
+import numpy as np
 
-Savedmodel = tf.keras.models.load_model('./new model8.h5')
+Savedmodel = tf.keras.models.load_model('./emotion_lts.h5')
 Savedmodel.summary()
 
-objects = ('Angry', 'Disgust', 'Fear', 'Happy', 'Sad', 'Surprise', 'Neutral')
+objects = ('Angry', 'Happy', 'Sad', 'Neutral')
 vid = cv2.VideoCapture(0)
+#
+# def run():
+#     while True:
+#
+#         _, frame = vid.read()
+#         frame = imutils.resize(frame, width=500)
+#
+#         # result = api(frame)
+#
+#         cv2.imshow("frame",frame)
+#         # getPrediction(frame)
+#
+#         # cv.waitKey(0)
+#         if cv2.waitKey(20) & 0XFF == ord('q'):
+#             break
+#
+#     vid.release()
+#     cv2.destroyAllWindows()
+def emotion_analysis(emotions):
+    objects = ['Angry', 'Happy', 'Sad', 'Neutral']
+    y_pos = np.arange(len(objects))
+    plt.bar(y_pos, emotions, align='center', alpha=0.9)
+    plt.tick_params(axis='x', which='both', pad=10, width=4, length=10)
+    plt.xticks(y_pos, objects)
+    plt.ylabel('percentage')
+    plt.title('emotion')
 
-def run():
-    while True:
 
-        _, frame = vid.read()
-        frame = imutils.resize(frame, width=500)
 
-        # result = api(frame)
 
-        cv2.imshow("frame",frame)
-        # getPrediction(frame)
+# def getPrediction(img):
+#
+#     x = image.img_to_array(img)
+#     x = np.expand_dims(x, axis=0)
+#
+#     x /= 255
+#
+#     custom = Savedmodel.predict(x)
+#     # print(custom[0])
+#     emotion_analysis(custom[0])
+#
+#     x = np.array(x, 'float32')
+#     x = x.reshape([48, 48]);
+#
+#     plt.gray()
+#     plt.show()
+#
+#     m = 0.000000000000000000001
+#     a = custom[0]
+#     for i in range(0, len(a)):
+#         if a[i] > m:
+#             m = a[i]
+#             ind = i
+#
+#     print('Expression Prediction:', objects[ind])
 
-        # cv.waitKey(0)
-        if cv2.waitKey(20) & 0XFF == ord('q'):
-            break
+imgdir='./speechVideo'
+cap = cv2.VideoCapture('./speechVideo/speech.mp4')
 
-    vid.release()
-    cv2.destroyAllWindows()
+while(cap.isOpened()):
+  ret,frame=cap.read()
+  # img = image.load_img(frame,grayscale=True, target_size=(48, 48))
+  frame = cv2.resize(frame,(48,48))
+  frame = cv2.cvtColor(frame,cv2.COLOR_BGR2GRAY)
+  x = image.img_to_array(frame)
+  x = np.expand_dims(x, axis = 0)
 
-def getPrediction(img):
+  x /= 255
 
-    x = image.img_to_array(img)
-    x = np.expand_dims(x, axis=0)
+  custom = Savedmodel.predict(x)
+  #print(custom[0])
+  emotion_analysis(custom[0])
 
-    x /= 255
+  x = np.array(x, 'float32')
+  x = x.reshape([48, 48]);
 
-    custom = Savedmodel.predict(x)
-    # print(custom[0])
-    emotion_analysis(custom[0])
 
-    x = np.array(x, 'float32')
-    x = x.reshape([48, 48]);
+  m=0.000000000000000000001
+  a=custom[0]
+  for i in range(0,len(a)):
+      if a[i]>m:
+          m=a[i]
+          ind=i
 
-    # plt.gray()
-    # plt.show()
+  print('Expression Prediction:',objects[ind])
 
-    m = 0.000000000000000000001
-    a = custom[0]
-    for i in range(0, len(a)):
-        if a[i] > m:
-            m = a[i]
-            ind = i
+  if cv2.waitKey(20) & 0XFF == ord('q'):
+    break
 
-    print('Expression Prediction:', objects[ind])
 
+cap.release()
+cv2.destroyAllWindows()
 
-def emotion_analysis(emotions):
-    objects = ['Angry', 'Disgust', 'Fear', 'Happy', 'Sad', 'Surprise', 'Neutral']
-    y_pos = np.arange(len(objects))
-    plt.bar(y_pos, emotions, align='center', alpha=0.9)
-    plt.tick_params(axis='x', which='both', pad=10, width=4, length=10)
-    plt.xticks(y_pos, objects)
-    plt.ylabel('percentage')
-    plt.title('emotion')
 
-run()
\ No newline at end of file