Generative Shape Models: Joint Text Recognition and Segmentation with Very Little Training Data
This addresses the problem of limited training data for scene text recognition and segmentation, offering a more efficient solution for computer vision applications.
The paper tackled scene text recognition and segmentation by using a generative shape model, achieving state-of-the-art results with significantly fewer training images than discriminative methods, and demonstrated improved robustness to affine and non-affine deformations.
We demonstrate that a generative model for object shapes can achieve state of the art results on challenging scene text recognition tasks, and with orders of magnitude fewer training images than required for competing discriminative methods. In addition to transcribing text from challenging images, our method performs fine-grained instance segmentation of characters. We show that our model is more robust to both affine transformations and non-affine deformations compared to previous approaches.