Feature extraction methods

1. Very Deep Convolutional Networks for Large-Scale Image Recognition(VGG-16) The VGG-16 is one of the most popular pre-trained models for image classification. Introduced in the famous ILSVRC 2014 Conference, it was and remains THE model to beat even today.

The most common linear methods for feature extraction are Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) . PCA uses an orthogonal transformation to convert data into a lower-dimensional space while maximizing the variance of the data.

Automated feature extraction methods Autoencoders, wavelet scattering, and deep neural networks are commonly used to extract features and reduce dimensionality of the data.

CNN provides better image recognition when its neural network feature extraction becomes deeper (contains more layers), at the cost of the learning method complexities that had made CNN inefficient and neglected for some time.

Feature Selection: Select a subset of input features from the dataset.