IntermediateTensorFlowFull notebook

Facial Emotion Recognition using MobileNetV2 Transfer Learning

Notebook-based emotion recognition tutorial using TensorFlow, MobileNetV2 transfer learning, seven emotion classes, Haar cascade face detection and realtime prediction logic.

Watch YouTube Video Download Notebook / Source Code

This download currently contains the uploaded notebook FaceEmotionTransferLearning_Final_Code_duringVideo.ipynb. Replace it later with your final cleaned code ZIP if required.

Facial Emotion Recognition using MobileNetV2 Transfer Learning

Overview

This tutorial is based on your uploaded FaceEmotionTransferLearning_Final_Code_duringVideo.ipynb notebook. It includes training-data preparation, seven emotion classes, MobileNetV2 transfer learning, model compilation/training, prediction on a face ROI and realtime webcam/video inference code. All notebook code cells and available outputs are included for later editing.

Editing tip: This page is controlled from data/tutorials.ts. Change the title, text, images, Python code, YouTube link, and download link there.

What you will learn

Prepare seven-class facial emotion training data
Resize and normalize image tensors
Use MobileNetV2 for transfer learning
Detect face ROI with Haar cascades
Predict emotion class on still images and webcam frames

Suggested tutorial flow

01

Dataset and emotion classes

Load training data from seven emotion-class folders.

02

Preprocessing

Resize images to 224 x 224 and normalize data.

03

MobileNetV2 transfer learning

Add new dense layers and softmax classifier.

04

Face ROI prediction

Detect face, crop ROI and predict emotion.

05

Realtime video demo

Run prediction on live frames and overlay emotion labels.

Text explanation template

Notebook-based tutorial material

This tutorial is based on your uploaded FaceEmotionTransferLearning_Final_Code_duringVideo.ipynb notebook. It includes training-data preparation, seven emotion classes, MobileNetV2 transfer learning, model compilation/training, prediction on a face ROI and realtime webcam/video inference code. All notebook code cells and available outputs are included for later editing.

How this page is organized

The page shows the full notebook workflow as tutorial sections. Each code cell is rendered as a separate Python code block. If the notebook cell produced an image, graph, screenshot or display output, it is shown under the matching code block and also in the results gallery.

How to edit this later

Open data/tutorials.ts and edit the object with this tutorial slug. Replace resultImages with your final screenshots, update codeBlocks with cleaned code, change videoUrl to the exact YouTube link, and replace the download URL with your final source-code ZIP or GitHub link.

Images, screenshots and results

Add your result screenshots, graphs, model outputs, detected objects, confusion matrices, or interface snapshots here.

face-emotion-recognition-tensorflow notebook output cell 4 — Notebook output from cell 4: plt.imshow(img_array) ## BGR

face-emotion-recognition-tensorflow notebook output cell 7 — Notebook output from cell 7: for category in Classes:

face-emotion-recognition-tensorflow notebook output cell 8 — Notebook output from cell 8: img_size= 224 ## ImageNet => 224 x 224

face-emotion-recognition-tensorflow notebook output cell 42 — Notebook output from cell 42: plt.imshow(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))

face-emotion-recognition-tensorflow notebook output cell 48 — Notebook output from cell 48: plt.imshow(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))

face-emotion-recognition-tensorflow notebook output cell 49 — Notebook output from cell 49: plt.imshow(cv2.cvtColor(face_roi, cv2.COLOR_BGR2RGB))

Python code explanation

Use one or more code blocks. After each block, explain what the code does in simple teaching language.

Notebook cell 0: import tensorflow as tf ## pip install tensorflow-gpu

pythonexample

import tensorflow as tf  ## pip install tensorflow-gpu
import cv2 ###  pip install opencv-python
 ## pip install opencv-contrib-python   fullpackage 
import os
import matplotlib.pyplot as plt  ## pip install matlplotlib
import numpy as np ## pip install numpy ## shift + enter

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 1: img_array = cv2.imread("Training/0/Training_314.jpg")

pythonexample

img_array = cv2.imread("Training/0/Training_314.jpg")

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 2: img_array.shape # rgb

pythonexample

img_array.shape # rgb

Notebook output

(48, 48, 3)

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 3: print (img_array)

pythonexample

print (img_array)

Notebook output

[[[153 153 153]
  [166 166 166]
  [167 167 167]
  ...
  [253 253 253]
  [253 253 253]
  [253 253 253]]

 [[142 142 142]
  [158 158 158]
  [170 170 170]
  ...
  [254 254 254]
  [254 254 254]
  [254 254 254]]

 [[146 146 146]
  [156 156 156]
  [173 173 173]
  ...
  [254 254 254]
  [254 254 254]
  [254 254 254]]

 ...

 [[222 222 222]
  [212 212 212]
  [209 209 209]
  ...
  [255 255 255]
  [254 254 254]
  [254 254 254]]

 [[210 210 210]
  [207 207 207]
  [201 201 201]
  ...
  [254 254 254]
  [253 253 253]
  [255 255 255]]

 [[209 209 209]
  [200 200 200]
  [191 191 191]
  ...
  [255 255 255]
  [255 255 255]
  [251 251 251]]]

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 4: plt.imshow(img_array) ## BGR

pythonexample

plt.imshow(img_array) ## BGR

Notebook output

<matplotlib.image.AxesImage at 0x25198bbb488>

face-emotion-recognition-tensorflow notebook output cell 4 — Notebook output from cell 4: plt.imshow(img_array) ## BGR

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 5: Datadirectory = "Training/" ## training dataset

pythonexample

Datadirectory = "Training/"  ## training dataset

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 6: Classes = ["0","1","2","3","4","5","6"] ## list of classes = > exact name of your fol...

pythonexample

Classes = ["0","1","2","3","4","5","6"] ## list of classes = > exact name of your folders

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 7: for category in Classes:

pythonexample

for category in Classes:
    path = os.path.join(Datadirectory, category)  ## //
    for img in os.listdir(path):
        img_array = cv2.imread(os.path.join(path,img))
        #backtorgb = cv2.cvtColor(img_array,cv2.COLOR_GRAY2RGB)
        plt.imshow(cv2.cvtColor(img_array, cv2.COLOR_BGR2RGB))
        plt.show()
        break
    break

face-emotion-recognition-tensorflow notebook output cell 7 — Notebook output from cell 7: for category in Classes:

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 8: img_size= 224 ## ImageNet => 224 x 224

pythonexample

img_size= 224 ## ImageNet => 224 x 224
new_array= cv2.resize(img_array, (img_size,img_size))
plt.imshow(cv2.cvtColor(new_array, cv2.COLOR_BGR2RGB))
plt.show()

face-emotion-recognition-tensorflow notebook output cell 8 — Notebook output from cell 8: img_size= 224 ## ImageNet => 224 x 224

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 9: new_array.shape

pythonexample

new_array.shape

Notebook output

(224, 224, 3)

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 11: training_Data = [] ## data array

pythonexample

training_Data = [] ## data array 

def create_training_Data():
    for category in Classes:
        path = os.path.join(Datadirectory, category)
        class_num = Classes.index(category) ## 0 1,  ## Label
        for img in os.listdir(path):
            try:
                img_array = cv2.imread(os.path.join(path,img))
                new_array= cv2.resize(img_array, (img_size,img_size)) 
                training_Data.append([new_array,class_num])
            except Exception as e:
                pass

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 12: create_training_Data()

pythonexample

create_training_Data()

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 13: print(len(training_Data))

pythonexample

print(len(training_Data))

Notebook output

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 14: temp = np.array(training_Data)

pythonexample

temp = np.array(training_Data)

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 15: temp.shape

pythonexample

temp.shape

Notebook output

(11568, 2)

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 16: import random

pythonexample

import random

random.shuffle(training_Data)

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 17: X = [] ## data /feature

pythonexample

X = []  ## data /feature
y = []  ## label

for features,label in training_Data:
    X.append(features)
    y.append(label)


X = np.array(X).reshape(-1, img_size, img_size, 3) ## converting it to 4 dimension

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 18: X.shape

pythonexample

X.shape

Notebook output

(11568, 224, 224, 3)

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 19: # normalize the data

pythonexample

# normalize the data
X= X/255.0; ## we are normalizing it

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 20: type(y)

pythonexample

type(y)

Notebook output

list

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 21: y[0]

pythonexample

y[0]

Notebook output

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 22: Y= np.array(y)

pythonexample

Y= np.array(y)

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 23: Y.shape

pythonexample

Y.shape

Notebook output

(11568,)

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 25: import tensorflow as tf

pythonexample

import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 26: model = tf.keras.applications.MobileNetV2() ## Pre-trained Model

pythonexample

model  = tf.keras.applications.MobileNetV2() ## Pre-trained Model

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 27: model.summary()

pythonexample

model.summary()

Notebook output

Model: "mobilenetv2_1.00_224"
__________________________________________________________________________________________________
Layer (type)                    Output Shape         Param #     Connected to                     
==================================================================================================
input_1 (InputLayer)            [(None, 224, 224, 3) 0                                            
__________________________________________________________________________________________________
Conv1_pad (ZeroPadding2D)       (None, 225, 225, 3)  0           input_1[0][0]                    
__________________________________________________________________________________________________
Conv1 (Conv2D)                  (None, 112, 112, 32) 864         Conv1_pad[0][0]                  
__________________________________________________________________________________________________
bn_Conv1 (BatchNormalization)   (None, 112, 112, 32) 128         Conv1[0][0]                      
__________________________________________________________________________________________________
Conv1_relu (ReLU)               (None, 112, 112, 32) 0           bn_Conv1[0][0]                   
__________________________________________________________________________________________________
expanded_conv_depthwise (Depthw (None, 112, 112, 32) 288         Conv1_relu[0][0]                 
__________________________________________________________________________________________________
expanded_conv_depthwise_BN (Bat (None, 112, 112, 32) 128         expanded_conv_depthwise[0][0]    
__________________________________________________________________________________________________
expanded_conv_depthwise_relu (R (None, 112, 112, 32) 0           expanded_conv_depthwise_BN[0][0] 
__________________________________________________________________________________________________
expanded_conv_project (Conv2D)  (None, 112, 112, 16) 512         expanded_conv_depthwise_relu[0][0
__________________________________________________________________________________________________
expanded_conv_project_BN (Batch (None, 112, 112, 16) 64          expanded_conv_project[0][0]      
__________________________________________________________________________________________________
block_1_expand (Conv2D)         (None, 112, 112, 96) 1536        expanded_conv_project_BN[0][0]   
______________________________________________________________________________________________
... [output shortened for website readability]

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 29: base_input = model.layers[0].input ## input

pythonexample

base_input = model.layers[0].input ## input

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 30: base_output = model.layers[-2].output

pythonexample

base_output = model.layers[-2].output

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 31: base_ouput

pythonexample

base_ouput

Notebook output

<tf.Tensor 'global_average_pooling2d/Identity:0' shape=(None, 1280) dtype=float32>

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 32: final_output = layers.Dense(128)(base_output) ## adding new layer, after the output o...

pythonexample

final_output = layers.Dense(128)(base_output) ## adding new layer, after the output of global pooling layer
final_ouput = layers.Activation('relu')(final_output) ## activation function 
final_output = layers.Dense(64)(final_ouput) 
final_ouput = layers.Activation('relu')(final_output)
final_output = layers.Dense(7,activation='softmax')(final_ouput) ## my classes are 07, classification layer

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 33: final_output ## ouput

pythonexample

final_output ## ouput

Notebook output

<tf.Tensor 'dense_2/Identity:0' shape=(None, 7) dtype=float32>

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 34: new_model = keras.Model(inputs = base_input, outputs= final_output)

pythonexample

new_model = keras.Model(inputs = base_input, outputs= final_output)

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 35: new_model.summary()

pythonexample

new_model.summary()

Notebook output

Model: "model"
__________________________________________________________________________________________________
Layer (type)                    Output Shape         Param #     Connected to                     
==================================================================================================
input_1 (InputLayer)            [(None, 224, 224, 3) 0                                            
__________________________________________________________________________________________________
Conv1_pad (ZeroPadding2D)       (None, 225, 225, 3)  0           input_1[0][0]                    
__________________________________________________________________________________________________
Conv1 (Conv2D)                  (None, 112, 112, 32) 864         Conv1_pad[0][0]                  
__________________________________________________________________________________________________
bn_Conv1 (BatchNormalization)   (None, 112, 112, 32) 128         Conv1[0][0]                      
__________________________________________________________________________________________________
Conv1_relu (ReLU)               (None, 112, 112, 32) 0           bn_Conv1[0][0]                   
__________________________________________________________________________________________________
expanded_conv_depthwise (Depthw (None, 112, 112, 32) 288         Conv1_relu[0][0]                 
__________________________________________________________________________________________________
expanded_conv_depthwise_BN (Bat (None, 112, 112, 32) 128         expanded_conv_depthwise[0][0]    
__________________________________________________________________________________________________
expanded_conv_depthwise_relu (R (None, 112, 112, 32) 0           expanded_conv_depthwise_BN[0][0] 
__________________________________________________________________________________________________
expanded_conv_project (Conv2D)  (None, 112, 112, 16) 512         expanded_conv_depthwise_relu[0][0
__________________________________________________________________________________________________
expanded_conv_project_BN (Batch (None, 112, 112, 16) 64          expanded_conv_project[0][0]      
__________________________________________________________________________________________________
block_1_expand (Conv2D)         (None, 112, 112, 96) 1536        expanded_conv_project_BN[0][0]   
__________________________________________________________________________________________________
block_1_ex
... [output shortened for website readability]

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 36: new_model.compile(loss="sparse_categorical_crossentropy", optimizer = "adam", metrics...

pythonexample

new_model.compile(loss="sparse_categorical_crossentropy", optimizer = "adam", metrics = ["accuracy"])

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 37: new_model.fit(X,Y, epochs = 25) ## training

pythonexample

new_model.fit(X,Y, epochs = 25) ## training

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 38: new_model.save('Final_model_95p07.h5')

pythonexample

new_model.save('Final_model_95p07.h5')

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 39: new_model = tf.keras.models.load_model('Final_model_95p07.h5')

pythonexample

new_model = tf.keras.models.load_model('Final_model_95p07.h5')

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 40: frame = cv2.imread("surprised_man.jpg")

pythonexample

frame = cv2.imread("surprised_man.jpg")

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 41: frame.shape

pythonexample

frame.shape

Notebook output

(410, 820, 3)

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 42: plt.imshow(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))

pythonexample

plt.imshow(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))

Notebook output

<matplotlib.image.AxesImage at 0x1cf8c66f888>

face-emotion-recognition-tensorflow notebook output cell 42 — Notebook output from cell 42: plt.imshow(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 43: # we need face detection algorihtm (gray image )

pythonexample

# we need face detection algorihtm (gray image )

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 44: faceCascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalface_...

pythonexample

faceCascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalface_default.xml')

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 45: gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)

pythonexample

gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 46: gray.shape

pythonexample

gray.shape

Notebook output

(410, 820)

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 47: faces = faceCascade.detectMultiScale(gray,1.1,4)

pythonexample

faces = faceCascade.detectMultiScale(gray,1.1,4)
for x,y,w,h in faces:
    roi_gray = gray[y:y+h, x:x+w]
    roi_color = frame[y:y+h, x:x+w]
    cv2.rectangle(frame, (x, y), (x+w, y+h), (0, 255, 0), 2) # BGR
    facess = faceCascade.detectMultiScale(roi_gray)   
    if len(facess) == 0:
        print("Face  not detected")
    else:
        for (ex,ey,ew,eh) in facess:
            face_roi = roi_color[ey: ey+eh, ex:ex + ew]

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 48: plt.imshow(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))

pythonexample

plt.imshow(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))

Notebook output

<matplotlib.image.AxesImage at 0x1d026451708>

face-emotion-recognition-tensorflow notebook output cell 48 — Notebook output from cell 48: plt.imshow(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 49: plt.imshow(cv2.cvtColor(face_roi, cv2.COLOR_BGR2RGB))

pythonexample

plt.imshow(cv2.cvtColor(face_roi, cv2.COLOR_BGR2RGB))

Notebook output

<matplotlib.image.AxesImage at 0x1d025dff2c8>

face-emotion-recognition-tensorflow notebook output cell 49 — Notebook output from cell 49: plt.imshow(cv2.cvtColor(face_roi, cv2.COLOR_BGR2RGB))

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 50: final_image =cv2.resize(face_roi, (224,224)) ##

pythonexample

final_image =cv2.resize(face_roi, (224,224)) ##
final_image =  np.expand_dims(final_image,axis =0)  ## need fourth dimension  
final_image=final_image/255.0 ## normalizing

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 51: Predictions =new_model.predict(final_image)

pythonexample

Predictions =new_model.predict(final_image)

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 52: Predictions[0]

pythonexample

Predictions[0]

Notebook output

array([2.2529088e-05, 9.1614591e-09, 2.7516992e-06, 3.3497886e-07,
       1.9450944e-07, 9.9997175e-01, 2.3757423e-06], dtype=float32)

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 53: np.argmax(Predictions)

pythonexample

np.argmax(Predictions)

Notebook output

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Notebook cell 55: import cv2 ### pip install opencv-python

pythonexample

import cv2 ###  pip install opencv-python
 ## pip install opencv-contrib-python   fullpackage 
#from deepface import DeepFace  ## pip install deepface
path = "haarcascade_frontalface_default.xml"
font_scale = 1.5
font = cv2.FONT_HERSHEY_PLAIN

# set the rectangle background to white
rectangle_bgr = (255, 255, 255)
# make a black image
img = np.zeros((500, 500))
# set some text
text = "Some text in a box!"
# get the width and height of the text box
(text_width, text_height) = cv2.getTextSize(text, font, fontScale=font_scale, thickness=1)[0]
# set the text start position
text_offset_x = 10
text_offset_y = img.shape[0] - 25
# make the coords of the box with a small padding of two pixels
box_coords = ((text_offset_x, text_offset_y), (text_offset_x + text_width + 2, text_offset_y - text_height - 2))
cv2.rectangle(img, box_coords[0], box_coords[1], rectangle_bgr, cv2.FILLED)
cv2.putText(img, text, (text_offset_x, text_offset_y), font, fontScale=font_scale, color=(0, 0, 0), thickness=1)

cap = cv2.VideoCapture(1)
# Check if the webcam is opened correctly
if not cap.isOpened():
    cap = cv2.VideoCapture(0)
if not cap.isOpened():
    raise IOError("Cannot open webcam")

while True:
    ret,frame = cap.read()
    #eye_cascade = cv2.CascadeClassifier(cv2.data.haarcascades +'haarcascade_eye.xml')
    faceCascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalface_default.xml')
    gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
    #print(faceCascade.empty())
    faces = faceCascade.detectMultiScale(gray,1.1,4)
    for x,y,w,h in faces:
        roi_gray = gray[y:y+h, x:x+w]
        roi_color = frame[y:y+h, x:x+w]
        cv2.rectangle(frame, (x, y), (x+w, y+h), (255, 0, 0), 2)
        facess = faceCascade.detectMultiScale(roi_gray)   
        if len(facess) == 0:
            print("Face  not detected")
        else:
            for (ex,ey,ew,eh) in facess:
                face_roi = roi_color[ey: ey+eh, ex:ex + ew] ## cropping the face
    
    final_image =cv2.resize(face_roi, (224,224))
    final_image =  np.expand_dims(final_image,axis =0)  ## need fourth dimension  
    final_image=final_image/255.0
    
    font = cv2.FONT_HERSHEY_SIMPLEX 
    
    Predictions = new_model.predict(final_image)
    
    font_scale = 1.5
    font = cv2.FONT_HERSHEY_PLAIN

 
    if (np.argmax(Predictions)==0):
        status = "Angry"
        
        x1,y1,w1,h1 = 0,0,175,75
        # Draw black background rectangle
        cv2.rectangle(frame, (x1, x1), (x1 + w1, y1 + h1), (0,0,0), -1)
        # Add text
        cv2.putText(frame, status, (x1 + int(w1/10),y1 + int(h1/2)), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0,0,255), 2)
        
        cv2.putText(frame,status,(100, 150),font, 3,(0, 0, 255),2,cv2.LINE_4)
       
        cv2.rectangle(frame, (x, y), (x+w, y+h), (0, 0, 255))
    
    elif (np.argmax(Predictions)==1):
        status = "Disgust"
        
        x1,y1,w1,h1 = 0,0,175,75
        # Draw black background rectangle
        cv2.rectangle(frame, (x1, x1), (x1 + w1, y1 + h1), (0,0,0), -1)
        # Add text
        cv2.putText(frame, status, (x1 + int(w1/10),y1 + int(h1/2)), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0,0,255), 2)
        
        cv2.putText(frame,status,(100, 150),font, 3,(0, 0, 255),2,cv2.LINE_4)
       
        cv2.rectangle(frame, (x, y), (x+w, y+h), (0, 0, 255))
        
    elif (np.argmax(Predictions)==2):
        status = "Fear"
        
        x1,y1,w1,h1 = 0,0,175,75
        # Draw black background rectangle
        cv2.rectangle(frame, (x1, x1), (x1 + w1, y1 + h1), (0,0,0), -1)
        # Add text
        cv2.putText(frame, status, (x1 + int(w1/10),y1 + int(h1/2)), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0,0,255), 2)
        
        cv2.putText(frame,status,(100, 150),font, 3,(0, 0, 255),2,cv2.LINE_4)
       
        cv2.rectangle(frame, (x, y), (x+w, y+h), (0, 0, 255))
        
    elif (np.argmax(Predictions)==3):
        status = "Happy"
        
        x1,y1,w1,h1 = 0,0,175,75
        # Draw black background rectangle
        cv2.rectangle(frame, (x1, x1), (x1 + w1, y1 + h1), (0,0,0), -1)
        # Add text
        cv2.putText(frame, status, (x1 + int(w1/10),y1 + int(h1/2)), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0,0,255), 2)
        
        cv2.putText(frame,status,(100, 150),font, 3,(0, 0, 255),2,cv2.LINE_4)
       
        cv2.rectangle(frame, (x, y), (x+w, y+h), (0, 0, 255))
        
    elif (np.argmax(Predictions)==4):
        status = "Sad"
        
        x1,y1,w1,h1 = 0,0,175,75
        # Draw black background rectangle
        cv2.rectangle(frame, (x1, x1), (x1 + w1, y1 + h1), (0,0,0), -1)
        # Add text
        cv2.putText(frame, status, (x1 + int(w1/10),y1 + int(h1/2)), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0,0,255), 2)
        
        cv2.putText(frame,status,(100, 150),font, 3,(0, 0, 255),2,cv2.LINE_4)
       
        cv2.rectangle(frame, (x, y), (x+w, y+h), (0, 0, 255))
        
    elif (np.argmax(Predictions)==5):
        status = "Surprise"
        
        x1,y1,w1,h1 = 0,0,175,75
        # Draw black background rectangle
        cv2.rectangle(frame, (x1, x1), (x1 + w1, y1 + h1), (0,0,0), -1)
        # Add text
        cv2.putText(frame, status, (x1 + int(w1/10),y1 + int(h1/2)), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0,0,255), 2)
        
        cv2.putText(frame,status,(100, 150),font, 3,(0, 0, 255),2,cv2.LINE_4)
       
        cv2.rectangle(frame, (x, y), (x+w, y+h), (0, 0, 255))
    else:
        status = "Neutral"
        
        x1,y1,w1,h1 = 0,0,175,75
        # Draw black background rectangle
        cv2.rectangle(frame, (x1, x1), (x1 + w1, y1 + h1), (0,0,0), -1)
        # Add text
        cv2.putText(frame, status, (x1 + int(w1/10),y1 + int(h1/2)), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0,255,0), 2)
        cv2.putText(frame,status,(100, 150),font, 3,(0, 255,0),2,cv2.LINE_4)
        cv2.rectangle(frame, (x, y), (x+w, y+h), (0, 255,0))
    
    #gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
    #print(faceCascade.empty())
    #faces = faceCascade.detectMultiScale(gray,1.1,4)

    # Draw a rectangle around the faces
    #for(x, y, w, h) in faces:
      #  cv2.rectangle(frame, (x, y), (x+w, y+h), (0, 255, 0), 2)
 
   
    
  
    # Use putText() method for 
    # inserting text on video 
  
    cv2.imshow('Face Emotion Recognition',frame)

    if cv2.waitKey(2) & 0xFF == ord('q'):
        break

cap.release()
cv2.destroyAllWindows()

Notebook output

Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not detected
Face  not d
... [output shortened for website readability]

KeyboardInterrupt: 
[1;31m---------------------------------------------------------------------------
[1;31mKeyboardInterrupt                         Traceback (most recent call last)
[1;32m<ipython-input-18-495b00b848aa> in <module>[1;34m
     53     font [1;33m= cv2[1;33m.FONT_HERSHEY_SIMPLEX[1;33m[1;33m
     54 [1;33m
[1;32m---> 55[1;33m     Predictions [1;33m= new_model[1;33m.predict[1;33m(final_image[1;33m)[1;33m[1;33m
     56 [1;33m
     57     font_scale [1;33m= [1;36m1.5[1;33m[1;33m

[1;32mC:\ProgramData\Anaconda3\lib\site-packages\tensorflow_core\python\keras\engine\training.py in predict[1;34m(self, x, batch_size, verbose, steps, callbacks, max_queue_size, workers, use_multiprocessing)
    907         max_queue_size[1;33m=max_queue_size[1;33m,[1;33m[1;33m
    908         workers[1;33m=workers[1;33m,[1;33m[1;33m
[1;32m--> 909[1;33m         use_multiprocessing=use_multiprocessing)
    910 [1;33m
    911   [1;32mdef reset_metrics[1;33m(self[1;33m)[1;33m:[1;33m[1;33m

[1;32mC:\ProgramData\Anaconda3\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py in predict[1;34m(self, model, x, batch_size, verbose, steps, callbacks, **kwargs)
    460     return self._model_iteration(
    461         model[1;33m, ModeKeys[1;33m.PREDICT[1;33m, x[1;33m=x[1;33m, batch_size[1;33m=batch_size[1;33m, verbose[1;33m=verbose[1;33m,[1;33m[1;33m
[1;32m--> 462[1;33m         steps=steps, callbacks=callbacks, **kwargs)
    463 [1;33m
    464 [1;33m

[1;32mC:\ProgramData\Anaconda3\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py in _model_iteration[1;34m(self, model, mode, x, y, batch_size, verbose, sample_weight, steps, callbacks, **kwargs)
    442               mode[1;33m=mode[1;33m,[1;33m[1;
... [output shortened for website readability]

This code block is extracted from the uploaded Jupyter notebook. Replace or rewrite the explanation later with your final teaching notes for this step.

Download source code

Use this area to provide the complete source code, GitHub repository, Google Drive ZIP, notebook, dataset, or premium download link.

Download Notebook / Source Code

Related Tutorials

Keep learning

Image Recognition using MobileNetV2

Deep Learning45 min

Image Recognition using MobileNetV2

Actual notebook-based tutorial for loading images in Python, preprocessing for MobileNetV2 and decoding ImageNet predictions.

Read tutorial Watch video

Facial Emotion Recognition using DeepFace and OpenCV

Computer Vision50 min

Facial Emotion Recognition using DeepFace and OpenCV

Actual notebook-based tutorial for detecting faces, analyzing emotions with DeepFace and drawing emotion labels using OpenCV.

Read tutorial Watch video

Driver Identification Using Deep Learning

Research Project45 min

Driver Identification Using Deep Learning

Driver identification pipeline using deep learning for recognizing driver identity from image/video input.

Read tutorial Watch video