HWD: A Novel Evaluation Score for Styled Handwritten Text Generation
This provides a domain-specific tool for researchers in document analysis to better assess HTG models, though it is incremental as it adapts existing evaluation concepts to a niche task.
The paper tackles the challenge of evaluating Styled Handwritten Text Generation (HTG) models by proposing the Handwriting Distance (HWD), a novel evaluation score that uses a perceptual distance in a feature space to measure handwriting style quality, demonstrating its suitability across word-level and line-level datasets.
Styled Handwritten Text Generation (Styled HTG) is an important task in document analysis, aiming to generate text images with the handwriting of given reference images. In recent years, there has been significant progress in the development of deep learning models for tackling this task. Being able to measure the performance of HTG models via a meaningful and representative criterion is key for fostering the development of this research topic. However, despite the current adoption of scores for natural image generation evaluation, assessing the quality of generated handwriting remains challenging. In light of this, we devise the Handwriting Distance (HWD), tailored for HTG evaluation. In particular, it works in the feature space of a network specifically trained to extract handwriting style features from the variable-lenght input images and exploits a perceptual distance to compare the subtle geometric features of handwriting. Through extensive experimental evaluation on different word-level and line-level datasets of handwritten text images, we demonstrate the suitability of the proposed HWD as a score for Styled HTG. The pretrained model used as backbone will be released to ease the adoption of the score, aiming to provide a valuable tool for evaluating HTG models and thus contributing to advancing this important research area.