In this project, a category classification was carry on the MNIST database performed by a fully connected multilayer network of the perceptron type (MLP) .
The objective of this project is the same as seen in Multilayer Perceptron (MLP) & MNIST but with a difference in the use of operations called image convolutions. These networks are trained with images to extract features through convolutions in order to classify the numbers from the MNIST database.
Transfer learning is a machine learning technique in which a model trained on one task is used as a starting point for a model on a second, related task. It is particularly useful when tagged data is scarce or expensive to obtain.
Regularizers are techniques by which you affect the gradient descent equation to improve its behavior or correct errors of a CNN.
Object detection is a task in computer vision that involves identifying and locating objects in an image or video. It is a challenging problem that requires not only recognizing the presence of an object but also determining its position and extent in the scene.
The segmentation of an image is the one that makes groups of objects to assign them some class, this assignment is done pixel by pixel giving it a value or class and representing it in some color.
Image segmentation is generally used to find regions of interest in order to perform tasks such as detection