In recent times, text detection in the wild has significantly raised its ability due to tremendous success of deep learning models. Applications of computer vision have emerged and got …
Detection and recognition of text in natural images are two main problems in the field of computer vision that have a wide variety of applications in analysis of sports videos …
Scene text detection methods based on deep learning have achieved remarkable results over the past years. However, due to the high diversity and complexity of natural scenes …
X Liu, G Meng, C Pan - International Journal on Document Analysis and …, 2019 - Springer
Scene text detection and recognition has become a very active research topic in recent several years. It can find many applications in reality ranging from navigation for vision …
J Tang, W Zhang, H Liu, MK Yang… - Proceedings of the …, 2022 - openaccess.thecvf.com
Recently, transformer-based methods have achieved promising progresses in object detection, as they can eliminate the post-processes like NMS and enrich the deep …
Y Zhu, C Yao, X Bai - Frontiers of Computer Science, 2016 - Springer
Text, as one of the most influential inventions of humanity, has played an important role in human life, so far from ancient times. The rich and precise information embodied in text is …
Scene text detection has attracted increasing concerns with the rapid development of deep neural networks in recent years. However, existing scene text detectors may overfit on the …
C Zhang, B Liang, Z Huang, M En… - Proceedings of the …, 2019 - openaccess.thecvf.com
Previous scene text detection methods have progressed substantially over the past years. However, limited by the receptive field of CNNs and the simple representations like …
S Tian, S Lu, C Li - … of the IEEE international conference on …, 2017 - openaccess.thecvf.com
The requiring of large amounts of annotated training data has become a common constraint on various deep learning systems. In this paper, we propose a weakly supervised scene text …