Scene Text Detection for Augmented Reality -- Character Bigram Approach to reduce False Positive Rate
This work provides an incremental improvement for augmented reality developers by reducing false positives in scene text detection.
This paper tackles the problem of false positives in scene text detection for augmented reality applications. By using a character bigram approach with an efficient convolutional neural network, the proposed detector reduces the false positive rate by 28.16% on the ICDAR 2015 dataset.
Natural scene text detection is an important aspect of scene understanding and could be a useful tool in building engaging augmented reality applications. In this work, we address the problem of false positives in text spotting. We propose improving the performace of sliding window text spotters by looking for character pairs (bigrams) rather than single characters. An efficient convolutional neural network is designed and trained to detect bigrams. The proposed detector reduces false positive rate by 28.16% on the ICDAR 2015 dataset. We demonstrate that detecting bigrams is a computationally inexpensive way to improve sliding window text spotters.