TrueType Transformer: Character and Font Style Recognition in Outline Format

TL;DR

The paper introduces TrueType Transformer (T3), a neural network model that directly processes outline font data for character and style recognition, achieving resolution independence and leveraging local control point structures.

Contribution

The novel T3 model directly accepts outline data using Transformer architecture, enabling resolution-independent font and character style recognition without image conversion.

Findings

T3 effectively recognizes characters and font styles from outline data.

Control points significantly influence classification accuracy.

T3 demonstrates resolution-independent recognition capabilities.

Abstract

We propose TrueType Transformer (T3), which can perform character and font style recognition in an outline format. The outline format, such as TrueType, represents each character as a sequence of control points of stroke contours and is frequently used in born-digital documents. T3 is organized by a deep neural network, so-called Transformer. Transformer is originally proposed for sequential data, such as text, and therefore appropriate for handling the outline data. In other words, T3 directly accepts the outline data without converting it into a bitmap image. Consequently, T3 realizes a resolution-independent classification. Moreover, since the locations of the control points represent the fine and local structures of the font style, T3 is suitable for font style classification, where such structures are very important. In this paper, we experimentally show the applicability of T3 in character and font style recognition tasks, while observing how the individual control points contribute to classification results.