Arbitrary Shape Text Detection via Boundary Transformer. (arXiv:2205.05320v1 [cs.CV])

Web: http://arxiv.org/abs/2205.05320

Arbitrary shape text detection is a challenging task due to its complexity
and variety, e.g, various scales, random rotations, and curve shapes. In this
paper, we propose an arbitrary shape text detector with a boundary transformer,
which can accurately and directly locate text boundaries without any
post-processing. Our method mainly consists of a boundary proposal module and
an iteratively optimized boundary transformer module. The boundary proposal
module consisting of multi-layer dilated convolutions will compute important
prior information (including classification map, …

arxiv cv detection text transformer