20,055 Hits in 3.7 sec

Learning Shape-Aware Embedding for Scene Text Detection

Zhuotao Tian, Michelle Shu, Pengyuan Lyu, Ruiyu Li, Chao Zhou, Xiaoyong Shen, Jiaya Jia
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
We address the problem of detecting scene text in arbitrary shapes, which is a challenging task due to the high variety and complexity of the scene.  ...  In addition, we introduce a shape-aware Loss to make training adaptively accommodate various aspect ratios of text instances and even the tiny gaps among them.  ...  To overcome these difficulties, we propose learning Shape-Aware Embedding for text instances that accommodate various aspect ratios and imprecise boundaries. Design.  ... 
doi:10.1109/cvpr.2019.00436 dblp:conf/cvpr/TianSLLZSJ19 fatcat:r46wgnrgqjadrdq4777pavwgfq

A Feasible Framework for Arbitrary-Shaped Scene Text Recognition [article]

Jinjin Zhang, Wei Wang, Di Huang, Qingjie Liu, Yunhong Wang
2019 arXiv   pre-print
In this paper, we propose a feasible framework for multi-lingual arbitrary-shaped STR, including instance segmentation based text detection and language model based attention mechanism for text recognition  ...  Deep learning based methods have achieved surprising progress in Scene Text Recognition (STR), one of classic problems in computer vision.  ...  Instead of individually concentrating on scene text detection or text recognition, we propose a feasible framework for multilingual arbitrary-shaped scene text spotting [5] .  ... 
arXiv:1912.04561v2 fatcat:5rtipn2hsjefjifv57ouizawoi

Geometry-Aware Scene Text Detection with Instance Transformation Network

Fangfang Wang, Liming Zhao, Xi Li, Xinchao Wang, Dacheng Tao
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
In this paper, we propose a geometry-aware modeling approach tailored for scene text representation with an end-to-end learning scheme.  ...  transformation embedding, resulting in a robust and elegant framework to detect words or text lines at one pass.  ...  for scene text. • We propose an end-to-end Instance Transformation Network for scene text detection with geometry-aware representation learning.  ... 
doi:10.1109/cvpr.2018.00150 dblp:conf/cvpr/WangZ0WT18 fatcat:z2ys5ri4ijhgdea3yrpaxpkode

Accurate Scene Text Detection via Scale-Aware Data Augmentation and Shape Similarity Constraint

Pengwen Dai, Yang Li, Hua Zhang, Jingzhi Li, Xiaochun Cao
2021 IEEE transactions on multimedia  
However, existing scene text detectors may overfit on the public datasets due to the limited training data, or generate inaccurate localization for arbitrary-shape scene texts.  ...  This paper presents an arbitrary-shape scene text detection method that can achieve better generalization ability and more accurate localization.  ...  Specifically, we first design a novel Scale-Aware Data Augmentation (SADA) strategy for the task of arbitrary-shape scene text detection.  ... 
doi:10.1109/tmm.2021.3073575 fatcat:r4rgthwbk5cw3boixvko3zbpoi

Mask is All You Need: Rethinking Mask R-CNN for Dense and Arbitrary-Shaped Scene Text Detection [article]

Xugong Qin, Yu Zhou, Youhui Guo, Dayan Wu, Zhihong Tian, Ning Jiang, Hongbin Wang, Weiping Wang
2021 arXiv   pre-print
Due to the large success in object detection and instance segmentation, Mask R-CNN attracts great attention and is widely adopted as a strong baseline for arbitrary-shaped scene text detection and spotting  ...  And we propose instance-aware mask learning in which the mask head learns to predict the shape of the whole instance rather than classify each pixel to text or non-text.  ...  Mask R-CNN, as one of the most powerful detectors for general object detection and instance segmentation, is widely adopted as a strong baseline for arbitrary-shaped scene text detection and spotting  ... 
arXiv:2109.03426v1 fatcat:oc7is6an6rdexmgwuyigea7bde

CORE-Text: Improving Scene Text Detection with Contrastive Relational Reasoning [article]

Jingyang Lin and Yingwei Pan and Rongfeng Lai and Xuehang Yang and Hongyang Chao and Ting Yao
2021 arXiv   pre-print
Such way naturally learns instance-aware representations of text proposals and thus facilitates scene text detection.  ...  Localizing text instances in natural scenes is regarded as a fundamental challenge in computer vision.  ...  The mask branch is then applied to the detection boxes, targeting for localizing the scene texts with arbitrary orientations and shapes.  ... 
arXiv:2112.07513v1 fatcat:qjn2mhmftretppstgz3hgwsreq

Scene Text Detection in Natural Images: A Review

Dongping Cao, Yong Zhong, Lishun Wang, Yilong He, Jiachen Dang
2020 Symmetry  
In this paper, we first introduce the history and progress of scene text detection and classify the traditional methods and deep learning-based methods in detail, pointing out the corresponding key issues  ...  Scene text detection is attracting more and more attention and has become an important topic in machine vision research.  ...  The boom of deep learning has also led to the development of successful techniques for scene text detection.  ... 
doi:10.3390/sym12121956 fatcat:3qd72rtd5vh5vds6ii57m37see

Lane detection with Position Embedding [article]

Jun Xie, Jiacheng Han, Dezhen Qi, Feng Chen, Kaer Huang, Jianwei Shuai
2022 arXiv   pre-print
For Tusimple dataset, there is not too complicated scene and lane has more prominent spatial features.  ...  On the basis of RESA, we introduce the method of position embedding to enhance the spatial features.  ...  transformer for scene text recognition.  ... 
arXiv:2203.12301v1 fatcat:qd4lf3nvczdb5fxtqn3xzeu7je

Deep Relational Reasoning Graph Network for Arbitrary Shape Text Detection [article]

Shi-Xue Zhang, Xiaobin Zhu, Jie-Bo Hou, Chang Liu, Chun Yang, Hongfa Wang, Xu-Cheng Yin
2020 arXiv   pre-print
Arbitrary shape text detection is a challenging task due to the high variety and complexity of scenes texts.  ...  In this paper, we propose a novel unified relational reasoning graph network for arbitrary shape text detection.  ...  arbitrary shape text detection.  ... 
arXiv:2003.07493v2 fatcat:2moizmnexjekzocota3jmethuq

RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition [article]

Xiaoyu Yue, Zhanghui Kuang, Chenhao Lin, Hongbin Sun, Wayne Zhang
2020 arXiv   pre-print
The attention-based encoder-decoder framework has recently achieved impressive results for scene text recognition, and many variants have emerged with improvements in recognition quality.  ...  To suppress such side-effect, we propose a novel position enhancement branch, and dynamically fuse its outputs with those of the decoder attention module for scene text recognition.  ...  Related Work Most of traditional methods for scene text recognition [48, 49, 33, 23, 34] adopt the bottom-up approach in which individual character is first detected by sliding window, and then integrated  ... 
arXiv:2007.07542v2 fatcat:nruhhk2fszhcnap3vgqul3ex2m

ContourNet: Taking a Further Step toward Accurate Arbitrary-shaped Scene Text Detection [article]

Yuxin Wang, Hongtao Xie, Zhengjun Zha, Mengting Xing, Zilong Fu, Yongdong Zhang
2020 arXiv   pre-print
Scene text detection has witnessed rapid development in recent years.  ...  However, there still exists two main challenges: 1) many methods suffer from false positives in their text representations; 2) the large scale variance of scene texts makes it hard for network to learn  ...  variance in scene text detection.  ... 
arXiv:2004.04940v1 fatcat:zk4lgp6xffcf7nzlhmuumhz5wu

Cluttered TextSpotter: An End-to-End Trainable Light- weight Scene Text Spotter for Cluttered Environment

Randheer Bagi, Tanima Dutta, Hari Prabhat Gupta
2020 IEEE Access  
Scene text detection and recognition approaches have received immense attention in computer vision research community.  ...  Scene text spotting aims at simultaneously localizing and recognizing text instances, symbols, and logos in natural scene images.  ...  The authors in [47] use text frontier learning and a tightness prior that refine pixel-wise mask prediction and assign polygonal boundary to each text region for arbitrary shaped text detection.  ... 
doi:10.1109/access.2020.3002808 fatcat:x4kbcajahrc5vgtuxsc6oyyjsa

Exploring Font-independent Features for Scene Text Recognition [article]

Yizhi Wang, Zhouhui Lian
2020 arXiv   pre-print
Specifically, we introduce trainable font embeddings to shape the font styles of generated glyphs, with the image feature of scene text only representing its essential patterns.  ...  Many recently-proposed methods are specially designed to accommodate the arbitrary shape, layout and orientation of scene texts, but ignoring that various font (or writing) styles also pose severe challenges  ...  CONCLUSION In this paper, we proposed the attentional glyph generation with trainable font embeddings for improving the feature learning of scene text recognition.  ... 
arXiv:2009.07447v1 fatcat:uiql56bx6bdippff3axacpxyru

Geometry-Aware Recurrent Neural Networks for Active Visual Recognition [article]

Ricson Cheng, Ziyan Wang, Katerina Fragkiadaki
2018 arXiv   pre-print
The proposed models are equipped with differentiable egomotion-aware feature warping and (learned) depth-aware unprojection operations to achieve geometrically consistent mapping between the features in  ...  We present recurrent geometry-aware neural networks that integrate visual information across multiple views of a scene into 3D latent feature tensors, while maintaining an one-to-one mapping between 3D  ...  We train for object instance segmentation by learning voxel segmentation embeddings [13] .  ... 
arXiv:1811.01292v2 fatcat:3caf2xhu7ngyzbvh5jwdqw2ooe

Multimodal Detection of Unknown Objects on Roads for Autonomous Driving [article]

Daniel Bogdoll and Enrico Eisen and Maximilian Nitsche and Christin Scheib and J. Marius Zöllner
2022 arXiv   pre-print
Tremendous progress in deep learning over the last years has led towards a future with autonomous vehicles on our roads.  ...  In this paper, we propose a novel pipeline to detect unknown objects.  ...  While the former detects the anchors of known classes, the latter learns instance-aware point embeddings and prototypes of the unknown classes.  ... 
arXiv:2205.01414v1 fatcat:4tachsjdlrfhtnenayf6lzhxwq
« Previous Showing results 1 — 15 out of 20,055 results