Skip to Main Content

Digital Humanities and Digital Scholarship: Images

Digital humanities services, tools, and selected bibliography from WSU librarians

Getting Started

Google Vision API

API from Google that performs image classification, optical character recognition (OCR), and other functions.  Free within certain daily usage limits.

Clarifai

Clarifai is an online tool / API for image classification.  Free within certain usage limits.  You can see a demonstration here.

Contact the library- we can help

Examples and Inspiration

Image Processing or Image Analysis, terms often used for quantitative analysis of images, is a quickly growing part of Digital Humanities.  One example area includes "Image Classification", the process of using machine learning to extract objects from an image (e.g. hat, apple, dog, boat).  However, Image Processing is not limited to classification, but might also include analysis and visualization of image metadata, or Optical Character Recognition (OCR).

Google Vision APIImage credit: blog post about Google Vision API, [link]

Photogrammer Project

From the project website, "Photogrammar is a web-based platform for organizing, searching, and visualizing the 170,000 photographs from 1935 to 1945 created by the United States Farm Security Administration and Office of War Information (FSA-OWI)".

 

Articles and Information

"Visualizing MNIST: An Exploration of Dimensionality Reduction", Olah

  • excellent introduction to image recognition, focusing on the freely available MNIST dataset

Learning More

Google TensorFlow - Image Recognition

TensorFlow is a cross-platform library from Google that facilitates machine and training models.  TensorFlow supports Image Recognition, and has some tutorials available.