Facial Recognition in Historical Photographs with Artificial Intelligence in Python

This lesson is meant as an introductory exercise in applying computer vision machine learning to historical photos. You’ll learn computer vision and machine learning principles for object recognition, and how to apply these principles using Python to recognize and classify smiling faces in historical photographs. This lesson will also serve as an introduction to some of the ethical issues posed by the use of AI in the study of photographs, particularly those implicating race and gender.

Scholars from two broad perspectives may find this tutorial of interest. First, historians engaging with large visual corpora in their research may find computer vision and object recognition valuable. Second, this tutorial is meant to provide an introductory lesson in how computational analysis of large visual collections can aid in curating and organizing large digital collections.

#Reviewed by:

• Steven Verstockt
• Daniel van Strien

#Learning outcomes

After completing this lesson, you will be able to:

• Understand the basics of computer vision machine learning
• Understand how a computer ‘views’ an image
• Extract pictures of human faces from historical documents digitized in the PDF format using Python, and how to organize them for further analysis
• Apply a pre-trained computer vision model to a historical dataset