- Trending Categories
Data Structure
Networking
RDBMS
Operating System
Java
MS Excel
iOS
HTML
CSS
Android
Python
C Programming
C++
C#
MongoDB
MySQL
Javascript
PHP
Physics
Chemistry
Biology
Mathematics
English
Economics
Psychology
Social Studies
Fashion Studies
Legal Studies
- Selected Reading
- UPSC IAS Exams Notes
- Developer's Best Practices
- Questions and Answers
- Effective Resume Writing
- HR Interview Questions
- Computer Glossary
- Who is Who
Handwritten Digit Recognition using Neural Network
Introduction
Handwritten Digit Recognition is a part of image recognition widely used in Computer Vision in Deep learning. Image recognition is one of the very basic and preliminary stages of every image or video−related task in Deep Learning. This article lets an overview of Handwritten Digit Recognition and how Image recognition can be extended to multiclass classification.
Before going ahead let us understand the difference between Binary and Multiclass image classification
Binary Image Classification
In Binary image classification, the model has two classes to predict from. For example in the classification of cats and dogs.
Multiclass Image Classification
In Multiclass Image Classification, the model has more than two classes to predict from. For example, in the classification of FasnionMNIST or Handwritten Digit Recognition, we have 10 classes to predict from.
Handwritten Digit Recognition
This task is a case of Multiclass image classification where the model predicts one of the digits from 0 to 9 to which the input image belongs.
In the MNIST digit recognition task, we use a CNN network to develop a model to recognize the handwritten digit. We would download the MNIST dataset which consists of a training set of 60000 images and 10000 images for testing. Each image is cropped into 28x28 pixels and handwritten digits are from 0 to 9.
Implementation using Python
Example
## Digit Recognition import keras from keras.layers import Conv2D, MaxPooling2D from keras.models import Sequential from keras import backend as K from keras.datasets import mnist from keras.utils import to_categorical from keras.layers import Dense, Dropout, Flatten import matplotlib.pyplot as plt %matplotlib inline fig = plt.figure n_classes = 10 input_shape = (28, 28, 1) batch_size = 128 num_classes = 10 epochs = 10 (X_train, Y_train), (X_test, Y_test) = mnist.load_data() print("Training data shape {} , test data shape {}".format(X_train.shape, Y_train.shape)) img = X_train[1] plt.imshow(img, cmap='gray') plt.show() X_train = X_train.reshape(X_train.shape[0], 28, 28, 1) X_test = X_test.reshape(X_test.shape[0], 28, 28, 1) Y_train = to_categorical(Y_train, n_classes) Y_test = to_categorical(Y_test, n_classes) X_train = X_train.astype('float32') X_test = X_test.astype('float32') X_train /= 255 X_test /= 255 print('x_train shape:', X_train.shape) print('train samples ',X_train.shape[0],) print('test samples',X_test.shape[0]) model = Sequential() model.add(Conv2D(32, kernel_size=(3, 3),activation='relu',input_shape=input_shape)) model.add(Conv2D(64, (3, 3), activation='relu')) model.add(MaxPooling2D(pool_size=(2, 2))) model.add(Dropout(0.25)) model.add(Flatten()) model.add(Dense(256, activation='relu')) model.add(Dropout(0.5)) model.add(Dense(num_classes, activation='softmax')) model.compile(loss=keras.losses.categorical_crossentropy,optimizer=keras.optimizers.Adadelta(),metrics=['accuracy']) history = model.fit(X_train, Y_train,batch_size=batch_size,epochs=epochs,verbose=1,validation_data=(X_test, Y_test)) output_score = model.evaluate(X_test, Y_test, verbose=0) print('Testing loss:', output_score[0]) print('Testing accuracy:', output_score[1])
Output
Training data shape (60000, 28, 28) , test data shape (60000,)x_train shape: (60000, 28, 28, 1) train samples 60000 test samples 10000 Epoch 1/10 469/469 [==============================] - 13s 10ms/step - loss: 2.2877 - accuracy: 0.1372 - val_loss: 2.2598 - val_accuracy: 0.2177 Epoch 2/10 469/469 [==============================] - 4s 9ms/step - loss: 2.2428 - accuracy: 0.2251 - val_loss: 2.2058 - val_accuracy: 0.3345 Epoch 3/10 469/469 [==============================] - 5s 10ms/step - loss: 2.1863 - accuracy: 0.3062 - val_loss: 2.1340 - val_accuracy: 0.4703 Epoch 4/10 469/469 [==============================] - 5s 10ms/step - loss: 2.1071 - accuracy: 0.3943 - val_loss: 2.0314 - val_accuracy: 0.5834 Epoch 5/10 469/469 [==============================] - 4s 9ms/step - loss: 1.9948 - accuracy: 0.4911 - val_loss: 1.8849 - val_accuracy: 0.6767 Epoch 6/10 469/469 [==============================] - 4s 10ms/step - loss: 1.8385 - accuracy: 0.5744 - val_loss: 1.6841 - val_accuracy: 0.7461 Epoch 7/10 469/469 [==============================] - 4s 10ms/step - loss: 1.6389 - accuracy: 0.6316 - val_loss: 1.4405 - val_accuracy: 0.7825 Epoch 8/10 469/469 [==============================] - 5s 10ms/step - loss: 1.4230 - accuracy: 0.6694 - val_loss: 1.1946 - val_accuracy: 0.8078 Epoch 9/10 469/469 [==============================] - 5s 10ms/step - loss: 1.2229 - accuracy: 0.6956 - val_loss: 0.9875 - val_accuracy: 0.8234 Epoch 10/10 469/469 [==============================] - 5s 11ms/step - loss: 1.0670 - accuracy: 0.7168 - val_loss: 0.8342 - val_accuracy: 0.8353 Testing loss: 0.8342439532279968 Testing accuracy: 0.8353000283241272
Conclusion
In this article, we have studied how we perform recognition of Handwritten Digit using a Neural Network.
627 Views
