%0 Generic %1 citeulike:14532106 %A xxx, %D 2018 %K detection keypoints ocr %T TextBoxes++: A Single-Shot Oriented Scene Text Detector %U http://arxiv.org/abs/1801.02765 %X Scene text detection is an important step of scene text recognition system and also a challenging problem. Different from general object detection, the main challenges of scene text detection lie on arbitrary orientations, small sizes, and significantly variant aspect ratios of text in natural images. In this paper, we present an end-to-end trainable fast scene text detector, named TextBoxes++, which detects arbitrary-oriented scene text with both high accuracy and efficiency in a single network forward pass. No post-processing other than an efficient non-maximum suppression is involved. We have evaluated the proposed TextBoxes++ on four public datasets. In all experiments, TextBoxes++ outperforms competing methods in terms of text localization accuracy and runtime. More specifically, TextBoxes++ achieves an f-measure of 0.817 at 11.6fps for \$1024 1024\$ ICDAR 2015 Incidental text images, and an f-measure of 0.5591 at 19.8fps for \$768 768\$ COCO-Text images. Furthermore, combined with a text recognizer, TextBoxes++ significantly outperforms the state-of-the-art approaches for word spotting and end-to-end text recognition tasks on popular benchmarks.

@misc{citeulike:14532106, abstract = {{Scene text detection is an important step of scene text recognition system and also a challenging problem. Different from general object detection, the main challenges of scene text detection lie on arbitrary orientations, small sizes, and significantly variant aspect ratios of text in natural images. In this paper, we present an end-to-end trainable fast scene text detector, named TextBoxes++, which detects arbitrary-oriented scene text with both high accuracy and efficiency in a single network forward pass. No post-processing other than an efficient non-maximum suppression is involved. We have evaluated the proposed TextBoxes++ on four public datasets. In all experiments, TextBoxes++ outperforms competing methods in terms of text localization accuracy and runtime. More specifically, TextBoxes++ achieves an f-measure of 0.817 at 11.6fps for \$1024 \times 1024\$ ICDAR 2015 Incidental text images, and an f-measure of 0.5591 at 19.8fps for \$768 \times 768\$ COCO-Text images. Furthermore, combined with a text recognizer, TextBoxes++ significantly outperforms the state-of-the-art approaches for word spotting and end-to-end text recognition tasks on popular benchmarks.}}, added-at = {2019-02-27T22:23:29.000+0100}, archiveprefix = {arXiv}, author = {xxx}, biburl = {https://www.bibsonomy.org/bibtex/2ca90912e2802f936d3677902e9d856e5/nmatsuk}, citeulike-article-id = {14532106}, citeulike-linkout-0 = {http://arxiv.org/abs/1801.02765}, citeulike-linkout-1 = {http://arxiv.org/pdf/1801.02765}, day = 9, eprint = {1801.02765}, interhash = {2863b3d510c73ce99e1e82dbc105db1a}, intrahash = {ca90912e2802f936d3677902e9d856e5}, keywords = {detection keypoints ocr}, month = jan, posted-at = {2018-02-09 08:47:21}, priority = {0}, timestamp = {2019-02-27T22:23:29.000+0100}, title = {{TextBoxes++: A Single-Shot Oriented Scene Text Detector}}, url = {http://arxiv.org/abs/1801.02765}, year = 2018 }