45 papers with code • 4 benchmarks • 6 datasets
Text Spotting is the combination of Scene Text Detection and Scene Text Recognition in an end-to-end manner. It is the ability to read natural text in the wild.
Our contributions are three-fold: 1) For the first time, we adaptively fit arbitrarily-shaped text by a parameterized Bezier curve.
Incidental scene text spotting is considered one of the most difficult and valuable challenges in the document analysis community.
We propose a post-processing approach to improve scene text recognition accuracy by using occurrence probabilities of words (unigram language model), and the semantic correlation between scene and text.
Most existing video text spotting benchmarks focus on evaluating a single language and scenario with limited data.
To this end, we introduce a new model named Explicit Synergy-based Text Spotting Transformer framework (ESTextSpotter), which achieves explicit synergy by modeling discriminative and interactive features for text detection and recognition within a single decoder.
Deep learning based methods have achieved surprising progress in Scene Text Recognition (STR), one of classic problems in computer vision.
Unlike previous works that merely employed visual features for text detection, this work proposes a novel text spotter, named Ambiguity Eliminating Text Spotter (AE TextSpotter), which learns both visual and linguistic features to significantly reduce ambiguity in text detection.