click to
look inside
Look inside

Deep Neural Networks for Image Segmentation in Fine Art

prerequisites
intermediate Python • intermediate NumPy • basics of PyTorch • intermediate deep learning (CNNs)
skills learned
image transformation • build an image classifier-based convolutional neural networks • apply transfer learning for image classification and segmentation • perform image semantic segmentation to increase accuracy of art paintings identification
David Stork and Max Dehaut
5 weeks · 5-7 hours per week · INTERMEDIATE
filed under

placing your order...

Don't refresh or navigate away from the page.
liveProject liveProjects give you the opportunity to learn new skills by completing real-world challenges in your local development environment. Solve practical problems, write working code, and analyze real data—with liveProject, you learn by doing. These self-paced projects also come with full liveBook access to select books for 90 days plus permanent access to other select Manning products. $34.99 $49.99 you save: $15 (30%)
try it! first milestone FREE
Deep Neural Networks for Image Segmentation in Fine Art (liveProject) added to cart
continue shopping
go to cart
Look inside
In this liveProject, you’ve taken on the challenge of digitizing the collection of the World Painting Museum, and the head curator wants you to use your machine learning skills to create an index of the art. Your challenges will include classifying your training data, considering pretrained models to help aid categorization, implementing a customized CNN that can identify genre, and applying image semantic segmentation in order to facilitate the classification by identifying the elements present on the art painting.
This project is designed for learning purposes and is not a complete, production-ready application or solution.

book resources

When you start your liveProject, you get full access to the following books for 90 days.

project authors

David Stork
Dr. David G. Stork is widely considered a pioneer in the application of rigorous computer vision, image analysis and artificial intelligence to problems in the history and interpretation of fine art. He is a graduate of MIT and the University of Maryland, and has published 200+ scholarly papers and eight books, including Pattern classification (2nd ed.) by Duda, Hart, and Stork, and the forthcoming Pixels & paintings: Foundations of computer-assisted connoisseurship (Wiley). He has held faculty appointments in eight disciplines, and is currently a visiting lecturer at Stanford University.
Maxime DEHAUT
Max Dehaut is a tech lead for Codit Luxembourg (Proximus Group), overseeing all technical aspects within the local region of Codit. He helps to define and implement the technological strategy with a focus on decision management, IoT and machine learning. In addition, Max has worked on several academic R&D projects related to machine learning in the UK, and has frequently been an invited speaker at machine learning related conferences. Prior to FICO, Max undertook a programme management role for Safe Triage, an organization providing fully automated triage solutions for the emergency (civilian and military) services. He also worked for NATO as an IT manager for the Air/Ground-based Defense Programme.

prerequisites

This liveProject is for intermediate Python programmers with some deep learning experience. To begin this liveProject, you will need to be familiar with:

TOOLS
  • Intermediate Python
  • Intermediate NumPy
  • Basics of PIL
  • Basics of Matplotlib
  • Basics of PyTorch
TECHNIQUES
  • Classification as a machine learning task
  • Intermediate deep learning (including convolutional neural networks)

you will learn

In this liveProject, you’ll overcome common problems faced in a deep learning project such as dataset relevance and model accuracy. You’ll master a diverse toolbox of data science and machine learning tools that can be applied to almost any project.

  • Building a training dataset of images with ZipFile and the request library
  • Elaborating on convolutional neural networks with PyTorch
  • Implementing pretrained models
  • Image segmentation

features

Self-paced
You choose the schedule and decide how much time to invest as you build your project.
Project roadmap
Each project is divided into several achievable steps.
Get Help
While within the liveProject platform, get help from other participants and our expert mentors.
Compare with others
For each step, compare your deliverable to the solutions by the author and other participants.
book resources
Get full access to select books for 90 days. Permanent access to excerpts from Manning products are also included, as well as references to other resources.
RECENTLY VIEWED