JSTR: Judgment Improves Scene Text Recognition
This addresses the challenge of accurate text recognition in complex scenes for applications like document analysis or autonomous systems, representing an incremental improvement.
The paper tackles the problem of improving accuracy in scene text recognition by introducing a method that judges whether an image and text match, using misrecognition results to understand error tendencies, and it outperforms baseline and state-of-the-art methods on public datasets.
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 to misrecognize by predicting correct or incorrect between the image and text. The experimental results on publicly available datasets demonstrate that our proposed method outperforms the baseline and state-of-the-art methods in scene text recognition.