bernardo-cruz/DLV03_Project

Deep Learning in Vision

DLV03_Project

Deep Learning in Vision course | HSLU

Introduction

The objective of this project is to recognize arabic letters using a CNN model and create artistic pictures with a Neural Style Transfer Model. The predicted arabic letter indicates which style is used (i.e. Picasso, Van Gogh etc.) to create a picture with the Neural Style Transfer Model.

Arabic Character Classification

Arabic Handwritten Characters Dataset

Models

• CNN
  A Convolutional Neural Network (ConvNet/CNN) is a Deep Learning algorithm which can take in an input image, assign importance (learnable weights and biases) to various aspects/objects in the image and be able to differentiate one from the other. (Source: https://towardsdatascience.com/a-comprehensive-guide-to-convolutional-neural-networks-the-eli5-way-3bd2b1164a53)

• Neural Style Transfer
  Neural style transfer is an optimization technique used to take two images—a content image and a style reference image (such as an artwork by a famous painter)—and blend them together so the output image looks like the content image, but “painted” in the style of the style reference image. (Source: https://www.tensorflow.org/tutorials/generative/style_transfer)

Important Links

• Arabic Handwritten Characters Dataset
• Learning Rate Finder
• Data Augmentation
• CNN
• CNN ELI5
• A Neural Algorithm of Artistic Style