Abstract
Recognizing text from natural images is a hot research
topic in computer vision due to its various applications.
Despite the enduring research of several decades on optical character recognition (OCR), recognizing texts from
natural images is still a challenging task. This is because
scene texts are often in irregular (e.g. curved, arbitrarilyoriented or seriously distorted) arrangements, which have
not yet been well addressed in the literature. Existing methods on text recognition mainly work with regular (horizontal and frontal) texts and cannot be trivially generalized to
handle irregular texts. In this paper, we develop the arbitrary orientation network (AON) to directly capture the
deep features of irregular texts, which are combined into
an attention-based decoder to generate character sequence.
The whole network can be trained end-to-end by using only images and word-level annotations. Extensive experiments on various benchmarks, including the CUTE80, SVTPerspective, IIIT5k, SVT and ICDAR datasets, show that
the proposed AON-based method achieves the-state-of-theart performance in irregular datasets, and is comparable to
major existing methods in regular datasets.