Image recognition of selfie images

Implementation of Image Recognition techniques There are lots of open source libraries available for the image recognition and classification. You can make use of the "TensorFlow" library for image recognition and can be integrated with your android application.

I'd go transfer learning way. The idea is to take the net, that's already been trained on large data set and has developed a number of conv filters, which can be reused. There's few of them available in tensorflow. You take net pretrained on ImageNet, chop off last layers responsible for classifying those filters and substitute it with your own. That way you don't really need to have that much data to reach seminal scores.

Check these links:

• https://machinelearningmastery.com/transfer-learning-for-deep-learning/
• https://towardsdatascience.com/a-comprehensive-hands-on-guide-to-transfer-learning-with-real-world-applications-in-deep-learning-212bf3b2f27a
• https://www.pyimagesearch.com/2019/05/20/transfer-learning-with-keras-and-deep-learning/
• https://www.pyimagesearch.com/2019/06/24/change-input-shape-dimensions-for-fine-tuning-with-keras/
• https://www.pyimagesearch.com/2019/06/03/fine-tuning-with-keras-and-deep-learning/
• https://www.tensorflow.org/api_docs/python/tf/keras/applications

You can also provide your own top layer to change input shape.

base_model = MobileNetV2(
    weights="imagenet",
    include_top=False,
    input_shape=(HEIGTH, WIDTH, DEPTH)
)

You can choose whether to retrain the net.

base_model.trainable = False

Now just instantiate new model with base model and add your final layers.

model = Sequential(base_model)

model.add(Flatten())

model.add(Dense(units=1024))
model.add(Activation('relu'))
model.add(BatchNormalization())
model.add(Dropout(rate=0.25))

model.add(Dense(units=1024))
model.add(Activation('relu'))
model.add(BatchNormalization())
model.add(Dropout(rate=0.25))

model.add(Dense(units=len(encoder.classes_)))
model.add(Activation('softmax'))

Then compile the model as usual.

model.compile(
    loss='categorical_crossentropy',
    optimizer=Adam(
        learning_rate=0.0001
    ),
    metrics=['accuracy']
)

Please note, that you have to choose the right number of final dense layers and their shape. You still need to fine tune it: which activation function to use, should you do weight decay, at which rate, what optimizer, what learning rate etc.