JSTR: Judgment Improves Scene Text Recognition

arXiv:2404.05967v1 Announce Type: cross
Abstract: In this paper, we present a method for enhancing the accuracy of scene text recognition tasks by judging whether the image and text match each other. While previous studies focused on generating the recognition results from input images, our approach also considers the model's misrecognition results to understand its error tendencies, thus improving the text recognition pipeline. This method boosts text recognition accuracy by providing explicit feedback on the data that the model is likely …

abstract accuracy arxiv cs.ai cs.cl cs.cv cs.lg image images judgment match paper recognition results studies tasks text type