… rectification network for scene text recognition, whose advantages are three-fold. 1) The
novel rectification network is more precise and robust, due to the elaborate description of text …

… scene text recognition network via iterative rectification (ESIR). The ESIR employs an
innovative rectification network that corrects perspective and curvature distortions of scene texts …

… transformer network (STN) and a sequence recognition network (SRN). The STN transforms
an input image to a rectified image, while the SRN recognizes text. The two networks are …

… to recognize irregular scene text. The framework contains a multi-object rectification
network (MORN) and an attention-based sequence recognition network (ASRN). The image …

… We propose a rectification-based text recognition network whose vision model improves the
prediction from a two-dimensional perspective. It exploits low-level and high-level raw visual …

… In this paper, we proposed a two-level rectification attention network for scene text recognition.
The two-level rectification network combined geometry-level and pixel-level methods, …

… network model that comprises a rectification network and a … to the problem of scene text
recognition and extend it with a … text detectors using ASTER’s abilities in text rectification and …

… models are further employed to translate text instances into sequences … process and this
paper focuses on scene text recognition. … networks for natural scene text recognition,” Workshop …

… semantic reasoning network (SRN) for accurate scene text recognition, which integrates
not … rectification network based on the rich local attributes to generate better rectification results. …

… rectification network (PRN) for irregular scene text … rectification network that progressively
rectifies irregular text to a … view, leading to optimal rectification and easier recognition. As our …