RSTC: A New Residual Swin Transformer for Offline Word-Level Writer Identification

Writer identification has steadily progressed in recent decades owing to its widespread application. Scenarios with extensive handwriting data such as page-level or sentence-level have achieved satisfactory accuracy; however, word-level offline writer identification is still challenging owing to the difficulty of learning good feature representations with scant handwriting data. This paper proposes a new Residual Swin Transformer Classifier (RSTC), which comprehensively aggregates local and global handwriting styles and yields robust feature representations with single-word images. The local information is modeled by the Transformer Block through interacting strokes and global information is featurized by holistic encoding using the Identity Branch and Global Block. Moreover, the pre-training technique is exploited to transfer reusable knowledge learned from a task similar to writer identification, strengthening RSTC’s representation of handwriting features. The proposed method is tested on the IAM and CVL benchmark datasets and achieves state-of-the-art performance, which demonstrates the superior modeling capability of RSTC for word-level writer identification.