Using Robust Regression to Find Font Usage Trends

TL;DR

This paper employs robust regression with a CNN to analyze font usage trends over time using movie posters, revealing historical shifts in font popularity through a novel hybrid training approach.

Contribution

It introduces a hybrid MSE and Tukey's biweight loss training method for font trend analysis using CNNs on movie poster images, addressing the challenge of estimating release years from font images.

Findings

Identified distinct font usage trends across different time periods.

Demonstrated the effectiveness of robust regression with hybrid loss in font trend estimation.

Provided insights into the evolution of font styles in movie posters.

Abstract

Fonts have had trends throughout their history, not only in when they were invented but also in their usage and popularity. In this paper, we attempt to specifically find the trends in font usage using robust regression on a large collection of text images. We utilize movie posters as the source of fonts for this task because movie posters can represent time periods by using their release date. In addition, movie posters are documents that are carefully designed and represent a wide range of fonts. To understand the relationship between the fonts of movie posters and time, we use a regression Convolutional Neural Network (CNN) to estimate the release year of a movie using an isolated title text image. Due to the difficulty of the task, we propose to use of a hybrid training regimen that uses a combination of Mean Squared Error (MSE) and Tukey's biweight loss. Furthermore, we perform a thorough analysis on the trends of fonts through time.