Deep Learning is just an incredible concept of what machines can do, and it is so powerful that engineers and business pioneers all focus on it. This extraordinary sort of calculation has far outperformed any past benchmarks for grouping pictures, text, and voice.

Deep learning is based on neural networks, similar to human brain cells. Earlier deep learning was not due to less processing power and a high need for data. But now, we are capable of power efficiency and more extensive data.

Neural networks work in the same way as human brain cells, which means we can recognize objects in the same way our human mind recognizes them. Which helps identify objects using Machines.

Our project is based on object detection using deep learning. It is based on multi-class classification for chess pieces using "CNN".

A Convolutional Neural Network (ConvNet/CNN) is a Deep Learning algorithm that can take in an input image, as-sign importance (learnable weights and biases) to various aspects/objects in the picture, and differentiate one from the other class.

CNNs, like neural networks, are made up of neurons with learning weights and biases. Each neuron gets several in-puts, converts them to a weighted total, runs it through an activation fu²nction, and returns with an output.