Progressive rectification network for irregular text recognition

Abstract

Scene text recognition has received increasing attention in the research community. Text in the wild often possesses irregular arrangements, which typically include perspective, curved, and oriented texts. Most of the existing methods do not work well for irregular text, especially for severely distorted text. In this paper, we propose a novel progressive rectification network (PRN) for irregular scene text recognition. Our PRN progressively rectifies the irregular text to a front-horizontal view and further boosts the recognition performance. The distortions are removed step by step by leveraging the observation that the intermediate rectified result provides good guidance for subsequent higher quality rectification. Additionally, by decomposing the rectification process into multiple procedures, the difficulty of each step is considerably mitigated. First, we specifically perform a rough rectification, and then adopt iterative refinement to gradually achieve optimal rectification. Additionally, to avoid the boundary damage problem in direct iterations, we design an envelope-refinement structure to maintain the integrity of the text during the iterative process. Instead of the rectified images, the text line envelope is tracked and continually refined, which implicitly models the transformation information. Then, the original input image is consistently utilized for transformation based on the refined envelope. In this manner, the original character information is preserved until the final transformation. These designs lead to optimal rectification to boost the performance of succeeding recognition. Extensive experiments on eight challenging datasets demonstrate the superiority of our method, especially on irregular benchmarks.

Natural scene text recognition based on artificial intelligence machine learning

“…Compared with traditional image recognition technology, natural scene images have important characteristics, and the complexity of the environment determines the difficulty of this technology [12]. The complexity of text recognition in physical scenes largely depends on the complexity of the image.…”

Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition

“…Existing STR methods for recognizing texts of arbitrary shapes can be divided into two main categories, i.e., rectificationbased methods and segmentation-based methods. The former methods (Gao et al 2018;Yang et al 2017;Cheng et al 2018) use the spatial transformer network (Jaderberg et al 2015) to normalize text images into the canonical shape, i.e., horizontally aligned characters of uniform heights and widths. These methods, however, are limited by the predefined text transformation set and hard to generalize to real-world examples.…”

Progressive Scene Text Erasing with Self-Supervision

“…Progressive processing is a popular strategy that is frequently employed in various tasks, such as scene text detection [24], scene text recognition [25], [26], RGB-D salient object detection [27], and image super-resolution [28]. PSENet [24] generates the different scale of kernels for each text instance and gradually expands the minimal scale kernel to the text instance with the complete shape.…”