Images Classification Recipe

Images Classification

Convolutional Neural Networks (CNN) and Transfer Learning for Heritage Images Classification

This recipe exposes an image classification scenario, aiming to deduce the technique or genre of images (picture, drawing, map...) using a Convolutional Neural Networks trained model (supervised approach with transfer learning).

This recipe may have various library use cases, particularly for cataloguing and information retrieval systems.

This recipe is based on BnF materials

Goals

This recipes includes a basic introduction to neural networks and deep learning (formal neuron model, neural networks, convolutional neural networks, transfer learning) and a hands-on session:

1. Creation of an images dataset for training
2. Training of a classification model with commercial APIs or open source IA frameworks
3. Application of the model to the heritage images to be classified

The IIIF standard API is leveraged to extract images from digital repositories, but raw files may also be used.

Educational resources

Introduction to the core technology used

For the theory, see the BnF github for a 45 mn introduction course (FR and EN versions, direct link).

Implementation notes

Images classification using AI SaaS

_Prerequisites: IBM Watson Studio account or Google Cloud AutoML account (see the setup document)

1. Use case definition: choice of the source images and the model classes

A 4 classes scenario dataset (picture/drawing/map/noise) can be downloaded here, but it's up to you to build your own use case.

2. Choice of the SaaS platform

IBM Watson Studio and Google Cloud AutoML

Images classification using AI frameworks

_Prerequisites: basic scripting and command line skills (Python scripts are used)

Other resources

...