Arbitrary-Oriented Scene Text Detection via Rotation Proposals

@article{Ma2017ArbitraryOrientedST,
  title={Arbitrary-Oriented Scene Text Detection via Rotation Proposals},
  author={Jianqi Ma and Weiyuan Shao and Hao Ye and Li Wang and Hong Wang and Yingbin Zheng and X. Xue},
  journal={IEEE Transactions on Multimedia},
  year={2017},
  volume={20},
  pages={3111-3122}
}
This paper introduces a novel rotation-based framework for arbitrary-oriented text detection in natural scene images. We present the Rotation Region Proposal Networks, which are designed to generate inclined proposals with text orientation angle information. The angle information is then adapted for bounding box regression to make the proposals more accurately fit into the text region in terms of the orientation. The Rotation Region-of-Interest pooling layer is proposed to project arbitrary… 

ArbiText: Arbitrary-Oriented Text Detection in Unconstrained Scene

This paper proposes a novel method, namely Arbitrary-oriented Text (or ArbText for short) detector, for efficient text detection in unconstrained natural scene images, which first adopt the circle anchors rather than the rectangular ones to represent bounding boxes, which is more robust to orientation variations.

A novel method for fast arbitrary-oriented scene text detection

This proposed method is simple and effective which can predict word-level bounding boxes via a single fully convolutional network and can run at over 11 FPS on 704 × 1280 images, which is much faster than the previous works.

R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection

A novel method called Rotational Region CNN (R2CNN) for detecting arbitrary-oriented texts in natural scene images using the Region Proposal Network to generate axis-aligned bounding boxes that enclose the texts with different orientations.

Detecting Multi-Oriented Text with Corner-based Region Proposals

TextPolar: irregular scene text detection using polar representation

  • Jie ChenZ. Lian
  • Computer Science
    International Journal on Document Analysis and Recognition (IJDAR)
  • 2021
A segmentation-based method, TextPolar, for irregular scene text detection by using a novel text representation that predicts the text center line via pixel-level segmentation and adopts polar coordinates instead of Euclidean coordinates to precisely depict the contour of text regions.

Enhancement Spatial Transformer Networks for Text Classification

The localization networks within Spatial Transformer Networks (STN) are presented, which are designed to generate proposals with text orientation affine information including translation, scaling and rotation, which can lead to a better approximation for orientation.

Arbitrary-shaped scene text detection by predicting distance map

A novel natural scene text detector based on distance map that can detect arbitrary-shaped texts more flexibly and robustly by adjusting the width of the center line is proposed.

Total-Text: toward orientation robustness in scene text detection

A new scene text detection model is proposed as the baseline for Total-Text, namely Polygon-Faster-RCNN, and its ability to detect text of all orientations is demonstrated.

Multi-oriented Scene Text Detection via Corner Localization and Region Segmentation

This paper proposes to detect scene text by localizing corner points of text bounding boxes and segmenting text regions in relative positions and achieves better or comparable results in both accuracy and efficiency.

Arbitrary Shape Scene Text Detection With Adaptive Text Region Representation

Recurrent neural network based adaptive text region representation is proposed for text region refinement, where a pair of boundary points are predicted each time step until no new points are found, and text regions of arbitrary shapes are detected and represented with adaptive number of boundary Points.
...

References

SHOWING 1-10 OF 60 REFERENCES

A robust arbitrary text detection system for natural scene images

Orientation Robust Text Line Detection in Natural Images

This paper treats text line detection as a graph partitioning problem, where each vertex is represented by a Maximally Stable Extremal Region (MSER), and uses higher-order correlation clustering to partition the MSERs into text line candidates.

Scene Text Detection via Holistic, Multi-Channel Prediction

This work proposes to localize text in a holistic manner, by casting scene text detection as a semantic segmentation problem, and demonstrates that the proposed algorithm substantially outperforms previous state-of-the-art approaches.

Detecting texts of arbitrary orientations in natural images

  • C. YaoX. BaiWenyu LiuYi MaZ. Tu
  • Computer Science
    2012 IEEE Conference on Computer Vision and Pattern Recognition
  • 2012
A system which detects texts of arbitrary orientations in natural images using a two-level classification scheme and two sets of features specially designed for capturing both the intrinsic characteristics of texts to better evaluate its algorithm and compare it with other competing algorithms.

A New Technique for Multi-Oriented Scene Text Line Detection and Tracking in Video

A new technique for detecting and tracking video texts of any orientation by using spatial and temporal information, respectively, and multi-scale integration by a pyramid structure is proposed, which helps in extracting full text lines.

Scene Text Localization and Recognition with Oriented Stroke Detection

The method introduces a novel approach for character detection and recognition which combines the advantages of sliding-window and connected component methods and efficiently calculated a novel character representation efficiently calculated from the values obtained in the stroke detection phase.

Multi-oriented Text Detection with Fully Convolutional Networks

A novel approach for text detection in natural images that consistently achieves the state-of-the-art performance on three text detection benchmarks: MSRA-TD500, I CDAR2015 and ICDAR2013.

A Unified Framework for Multioriented Text Detection and Recognition

  • C. YaoX. BaiWenyu Liu
  • Computer Science
    IEEE Transactions on Image Processing
  • 2014
A unified framework for text detection and recognition in natural images using exactly the same features and classification scheme and a new dictionary search method is proposed, to correct the recognition errors usually caused by confusions among similar yet different characters.

Canny Text Detector: Fast and Robust Scene Text Localization Algorithm

A novel scene text detection algorithm, Canny Text Detector, which takes advantage of the similarity between image edge and text for effective text localization with improved recall rate and makes use of double threshold and hysteresis tracking to detect texts of low confidence.

Robust Text Detection in Natural Scene Images

An accurate and robust method for detecting texts in natural scene images using a fast and effective pruning algorithm to extract Maximally Stable Extremal Regions (MSERs) as character candidates using the strategy of minimizing regularized variations is proposed.
...