Update app.py

app.py

@@ -4,15 +4,13 @@ import numpy as np
 import cv2 
 import requests
 from keras.models import model_from_json
-
 import face_recognition
 import os
 from datetime import datetime
 
-#the following are to do with this interactive notebook code
-from matplotlib import pyplot as plt # this lets you draw inline pictures in the notebooks
-import pylab # this allows you to control figure size 
-pylab.rcParams['figure.figsize'] = (10.0, 8.0) # this controls figure size in the notebook
+from keras.models import model_from_json
+from keras.preprocessing.image import img_to_array
+from PIL import Image
 
 import io
 import streamlit as st
@@ -29,16 +27,22 @@ for cls in myList:
         classnames.append(os.path.splitext(cls)[0])
 st.write(classnames)
 
-
-json_file = open("facialemotionmodel.json", "r")
-model_json = json_file.read()
+# load model
+emotion_dict = {0:'angry', 1 :'happy', 2: 'neutral', 3:'sad', 4: 'surprise'}
+# load json and create model
+json_file = open('emotion_model1.json', 'r')
+loaded_model_json = json_file.read()
 json_file.close()
-model = model_from_json(model_json)
+classifier = model_from_json(loaded_model_json)
 
-model.load_weights("facialemotionmodel.h5")
-haar_file=cv2.data.haarcascades + 'haarcascade_frontalface_default.xml'
-face_cascade=cv2.CascadeClassifier(haar_file)
+# load weights into new model
+classifier.load_weights("emotion_model1.h5")
 
+#load face
+try:
+    face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
+except Exception:
+    st.write("Error loading cascade classifiers")
 
 def findEncodings(Images):
     encodeList = []
@@ -53,7 +57,6 @@ def extract_features(image):
     feature = feature.reshape(1,48,48,1)
     return feature/255.0
 
-labels = {0 : 'angry', 1 : 'disgust', 2 : 'fear', 3 : 'happy', 4 : 'neutral', 5 : 'sad', 6 : 'surprise'}
 
 encodeListknown = findEncodings(Images)
 st.write('Encoding Complete')
@@ -64,23 +67,48 @@ if img_file_buffer is not None:
     test_image = Image.open(img_file_buffer)
     image1 = Image.open(img_file_buffer)
     st.image(test_image, use_column_width=True)
-    image = np.asarray(image1)
-    image1 = np.asarray(test_image)
-    image1 = cv2.cvtColor(image1, cv2.COLOR_BGR2GRAY)
-    
+    image = np.asarray(test_image)
     
+    img = np.asarray(image1)
+    img = cv2.resize(img,(0,0),None,0.25,0.25)
+    st.write("1")
+
+    #image gray
+    img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
+    faces = face_cascade.detectMultiScale(
+        image=img_gray, scaleFactor=1.3, minNeighbors=5)
+    st.write("2")
+    for (x, y, w, h) in faces:
+        cv2.rectangle(img=img, pt1=(x, y), pt2=(
+            x + w, y + h), color=(255, 0, 0), thickness=2)
+        roi_gray = img_gray[y:y + h, x:x + w]
+        roi_gray = cv2.resize(roi_gray, (48, 48), interpolation=cv2.INTER_AREA)
+        if np.sum([roi_gray]) != 0:
+            roi = roi_gray.astype('float') / 255.0
+            roi = img_to_array(roi)
+            roi = np.expand_dims(roi, axis=0)
+            prediction = classifier.predict(roi)[0]
+            maxindex = int(np.argmax(prediction))
+            finalout = emotion_dict[maxindex]
+            output = str(finalout)
+            st.write("3")
+        label_position = (x, y)
+        img = cv2.putText(img, output, label_position, cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
+        st.image(img, use_column_width=True)
+        st.write("4")
+
     #########################
     imgS = cv2.resize(image,(0,0),None,0.25,0.25)
     imgS = cv2.cvtColor(imgS, cv2.COLOR_BGR2RGB)
     facesCurFrame = face_recognition.face_locations(imgS)
     encodesCurFrame = face_recognition.face_encodings(imgS,facesCurFrame)
-
+    st.write("5")
     for encodeFace,faceLoc in zip(encodesCurFrame,facesCurFrame):
         matches = face_recognition.compare_faces(encodeListknown,encodeFace)
         faceDis = face_recognition.face_distance(encodeListknown,encodeFace)
         #print(faceDis)
         matchIndex = np.argmin(faceDis)
-        st.write("start")
+        st.write("6")
         if matches[matchIndex]:
             name = classnames[matchIndex]
             st.write(name)
@@ -89,28 +117,19 @@ if img_file_buffer is not None:
             cv2.rectangle(image,(x1,y1),(x2,y2),(0,255,0),2)
             cv2.rectangle(image,(x1,y2-35),(x2,y2),(0,255,0),cv2.FILLED)
             cv2.putText(image,name,(x1+6,y2-6),cv2.FONT_HERSHEY_COMPLEX,1,(255, 255, 255),2)
-
-            faces=face_cascade.detectMultiScale(image1,1.3,5)
-            for (p,q,r,s) in faces:
-                image = image1[q:q+s,p:p+r]
-                cv2.rectangle(image1,(p,q),(p+r,q+s),(255,0,0),2)
-                image = cv2.resize(image,(48,48))
-                img = extract_features(image)
-                pred = model.predict(img)
-                prediction_label = labels[pred.argmax()]
-                st.write("Predicted Output:", prediction_label)
-                # cv2.putText(im,prediction_label)
-                img = cv2.putText(image1, '% s' %(prediction_label), (p-10, q-10),cv2.FONT_HERSHEY_COMPLEX_SMALL,2, (0,0,255))
-                st.image(img, use_column_width=True)
+            st.write("7")
+            ##############
+            if name:
+                if output=='happy':
+                    url = "https://kiwi-whispering-plier.glitch.me/update" 
+                    
+                    data = {
+                        'name': name,
+                    }
+                    else:
+                        st.write("Please smile")
         else:
             st.write("FAiled")
              
            
-            # ##############
-            # url = "https://kiwi-whispering-plier.glitch.me/update" 
-            
-            # data = {
-            #     'name': name,
-            # }
-            # else:
-            #     st.write("Please smile")
+