Automated Image Content Analysis: An Introduction and Hands on Tutorial
John Wilkerson
9:00am – 5:00pm
This full day short course is a practicum on automated approaches to image analysis. It will be of particular interest to scholars studying social media or any domain where large numbers of images (e.g. tens of thousands or more) need to be labeled. The first part of the short course introduces Deep Learning and Convolutional Neural Networks (CNNs), the go-to methodologies for image labeling.
The second part is a hands-on tutorial using a Python software package developed by the instructors that they use in their own research. It will cover how to 1) use pre-trained CNNs to extract features of interest from an image (e.g. particular objects or text), and 2) how to train CNNs to classify images into user-determined categories using labeled examples. Working knowledge of Python is assumed.
Instructors: Andreu Casas (University of Washington, NYU); Nora Webb Williams, Wesley Zuidema, John Wilkerson (University of Washington).
**All Short Courses will take place on Wednesday, August 29 at the APSA 2018 Annual Meeting in Boston, MA.**