changers done

Emotion/emotions.txt

@@ -20,7 +20,9 @@
  'oppressed': 'Angry',
  'anguished': 'Sad',
  'animated': 'Happy',
+ 'happen': 'Sad',
  'annoyed': 'Angry',
+ 'simply': 'Angry',
  'appalled': 'Angry',
  'beatific': 'Happy',
  'bereaved': 'Sad',

Emotion/videoAnalyzing.py

-# from skimage import io
+#Import useful libraries
 import cv2
 import matplotlib.pyplot as plt
 import numpy as np
 import tensorflow as tf
 from keras.preprocessing import image
 
+#Load the trained model
 Saved_model = tf.keras.models.load_model('emotion_lts.h5')
 Saved_model.summary()
 
+#Prediction categories
 objects = ('Angry', 'Happy', 'Sad', 'Neutral')
 vid = cv2.VideoCapture(0)
 
@@ -21,16 +23,15 @@ def emotion_analysis(emotions):
     plt.ylabel('percentage')
     plt.title('emotion')
 
-
+#Predict facial expressions
 def get_emotions(filePath):
     cap = cv2.VideoCapture(filePath)
 
-    emotions = []
+    emotions = [] #Define emotion list
 
     while (cap.isOpened()):
         try:
             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)
@@ -39,12 +40,9 @@ def get_emotions(filePath):
             x /= 255
 
             custom = Saved_model.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)):

UI/application.js

@@ -53,6 +53,7 @@ app.controller('MainController', ['$scope', '$rootScope', '$location', '$route',
             });
         }
 
+//facial expression diagram
         $scope.selectVideoFile = function (e) {
             $scope.chartLabels = [];
             $scope.chartdata = [];
@@ -136,7 +137,7 @@ app.controller('MainController', ['$scope', '$rootScope', '$location', '$route',
                     console.log(error);
                 });
 
-            //emotion  graph
+//emotion  graph text analyzing
             MainFactory.emotionSentence({ text: $scope.audioText })
                 .then(function (response) {
                     console.log(response.data);
@@ -152,7 +153,6 @@ app.controller('MainController', ['$scope', '$rootScope', '$location', '$route',
 
                     $scope.chartdata = [];
                     for (let i = 0; i < $scope.emotions.length; i++) {
-                        // $scope.chartLabels.push(i+1);
                         if ($scope.emotions[i] == 'Angry') {
                             $scope.chartdata.push(1);
                             $scope.emotionScore += 0.25;
@@ -288,6 +288,8 @@ app.controller('MainController', ['$scope', '$rootScope', '$location', '$route',
                     console.log(error);
                 });
 
+//comparison between the expression prediction results and emotional moment results
+
             MainFactory.textAnalyzeEmotion({ text: $scope.audioText })
                 .then(function (response) {
                     console.log(response);