scholarly journals An Algorithm for Scene Text Detection Using Multibox and Semantic Segmentation

2019 ◽  
Vol 9 (6) ◽  
pp. 1054 ◽  
Author(s):  
Hongbo Qin ◽  
Haodi Zhang ◽  
Hai Wang ◽  
Yujin Yan ◽  
Min Zhang ◽  
...  
Keyword(s):  
Semantic Segmentation ◽  
Text Detection ◽  
Experimental Results ◽  
Natural Scene ◽  
Maximum Increase ◽  
Correction Process ◽  
Bounding Box ◽  
Scene Text Detection ◽  
Scene Text ◽  
F Measure

An outside mutual correction (OMC) algorithm for natural scene text detection using multibox and semantic segmentation was developed. In the OMC algorithm, semantic segmentation and multibox were processed in parallel, and the text detection results were mutually corrected. The mutual correction process was divided into two steps: (1) The semantic segmentation results were employed in the bounding box enhancement module (BEM) to correct the multibox results. (2) The semantic bounding box module (SBM) was used to optimize the adhesion text boundary of the semantic segmentation results. Non-maximum suppression (NMS) was adopted to merge the SBM and BEM results. Our algorithm was evaluated on the ICDAR2013 and SVT datasets. The experimental results show that the developed algorithm had a maximum increase of 13.62% in the F-measure score and the highest F-measure score was 81.38%.

Natural scene text detection with MC–MR candidate extraction and coarse-to-fine filtering

2017 ◽  
Vol 260 ◽  
pp. 112-122 ◽  
Author(s):  
Chunna Tian ◽  
Yong Xia ◽  
Xiangnan Zhang ◽  
Xinbo Gao
Keyword(s):  
Text Detection ◽  
Natural Scene ◽  
Scene Text Detection ◽  
Scene Text ◽  
Coarse To Fine

scholarly journals A Scene Text Detector for Text with Arbitrary Shapes

2020 ◽  
Vol 2020 ◽  
pp. 1-11
Author(s):  
Weijia Wu ◽  
Jici Xing ◽  
Cheng Yang ◽  
Yuxing Wang ◽  
Hong Zhou
Keyword(s):  
State Of The Art ◽  
Recognition Task ◽  
Text Detection ◽  
Supplementary Information ◽  
Complex Environment ◽  
Irregular Shapes ◽  
Scene Text Detection ◽  
Scene Text ◽  
F Measure ◽  
Instance Segmentation

The performance of text detection is crucial for the subsequent recognition task. Currently, the accuracy of the text detector still needs further improvement, particularly those with irregular shapes in a complex environment. We propose a pixel-wise method based on instance segmentation for scene text detection. Specifically, a text instance is split into five components: a Text Skeleton and four Directional Pixel Regions, then restoring itself based on these elements and receiving supplementary information from other areas when one fails. Besides, a Confidence Scoring Mechanism is designed to filter characters similar to text instances. Experiments on several challenging benchmarks demonstrate that our method achieves state-of-the-art results in scene text detection with an F-measure of 84.6% on Total-Text and 86.3% on CTW1500.

Multilingual Scene Text Detection Using Gradient Morphology

2020 ◽  
Vol 10 (3) ◽  
pp. 31-43 ◽  
Author(s):  
Dibyajyoti Dhar ◽  
Neelotpal Chakraborty ◽  
Sayan Choudhury ◽  
Ashis Paul ◽  
Ayatullah Faruk Mollah ◽  
...  
Keyword(s):  
State Of The Art ◽  
High Sensitivity ◽  
Text Detection ◽  
Interesting Problem ◽  
Natural Scene ◽  
The Past ◽  
Scene Text Detection ◽  
Scene Text ◽  
Multiple Languages ◽  
Natural Scene Images

Text detection in natural scene images is an interesting problem in the field of information retrieval. Several methods have been proposed over the past few decades for scene text detection. However, the robustness and efficiency of these methods are downgraded due to high sensitivity towards various complexities of an image. Also, in multi-lingual environment where texts may occur in multiple languages, a method may not be suitable for detecting scene texts in certain languages. To counter these challenges, a gradient morphology-based method is proposed in this paper that proves to be robust against image complexities and efficiently detects scene texts irrespective of their languages. The method is validated using low quality images from standard multi-lingual datasets like MSRA-TD500 and MLe2e. The performance of the method is compared with that of some state-of-the-art methods, and comparably better results are observed.

scholarly journals Natural Scene Text Detection Based On Multi-level Fusion Proposal Network

2020 ◽  
Vol 790 ◽  
pp. 012051
Author(s):  
Tong Li ◽  
Wanggen Li ◽  
Nannan Zhu ◽  
Xuecheng Gong ◽  
Jiajia Chen
Keyword(s):  
Text Detection ◽  
Natural Scene ◽  
Scene Text Detection ◽  
Scene Text ◽  
Multi Level ◽  
Level Fusion

scholarly journals Arbitrary Shape Natural Scene Text Detection Method Based on Soft Attention Mechanism and Dilated Convolution

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 122685-122694
Author(s):  
Xiao Qin ◽  
Jianhui Jiang ◽  
Chang-An Yuan ◽  
Shaojie Qiao ◽  
Wei Fan
Keyword(s):  
Arbitrary Shape ◽  
Detection Method ◽  
Text Detection ◽  
Attention Mechanism ◽  
Natural Scene ◽  
Dilated Convolution ◽  
Scene Text Detection ◽  
Scene Text

PRPN: Progressive region prediction network for natural scene text detection

2021 ◽  
pp. 107767
Author(s):  
Yuanhong Zhong ◽  
Xinyu Cheng ◽  
Tao Chen ◽  
Jing Zhang ◽  
Zhaokun Zhou ◽  
...  
Keyword(s):  
Text Detection ◽  
Natural Scene ◽  
Scene Text Detection ◽  
Scene Text
Sign in / Sign up

Export Citation Format

Share Document