Faster R-CNN Based Table Detection Combining Corner Locating

Table detection in document images has achieved remarkable improvement. However, there is still a problem of inaccurate table boundary locating. This paper proposes Faster R-CNN based table detection combining corner locating method. Firstly, coarse table detection and corner locating are implemented through Faster R-CNN network. Secondly, those corners belonging to the same tables are grouped by coordinate matching. At the same time, unreliable corners are filtered. Finally, table boundaries are adjusted and refined by corresponding corner group. The proposed method improves the precision of table boundary locating at pixel-level. Experiment results show that our method effectively improves the precision of table detection. It achieves an F-measure of 94.9% on ICDAR2017 POD dataset. Compared with traditional Faster R-CNN method, our method increases by 2.8% in F-measure and 2.1% at pixellevel localization.

[1]  Mateu Sbert,et al.  Combining global and local global-illumination algorithms , 2003, SCCG '03.

[2]  Lars Petersson,et al.  DeNet: Scalable Real-Time Object Detection with Directed Sparse Sampling , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[3]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[4]  Francesca Cesarini,et al.  Trainable Table Location in Document Images , 2002, ICPR.

[5]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[6]  Shuicheng Yan,et al.  Multi-oriented Scene Text Detection via Corner Localization and Region Segmentation , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[7]  Zhi Tang,et al.  ICDAR2017 Competition on Page Object Detection , 2017, 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR).

[8]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Thomas Kieninger,et al.  Applying the T-Recs table recognition system to the business letter domain , 2001, Proceedings of Sixth International Conference on Document Analysis and Recognition.

[10]  Hei Law,et al.  CornerNet: Detecting Objects as Paired Keypoints , 2018, ECCV.

[11]  P. D. Sankhe,et al.  Deblurring of grayscale images using inverse and Wiener filter , 2011, ICWET.

[12]  Ioannis Pratikakis,et al.  Automatic Table Detection in Document Images , 2005, ICAPR.

[13]  Richard G. Baraniuk,et al.  Multiscale document segmentation using wavelet-domain hidden Markov models , 1999, Electronic Imaging.

[14]  Jia-Lin Chen.  A simplified approach to the HMM based texture analysis and its application to document segmentation , 1997, Pattern Recognit. Lett..

[15]  Jian Sun,et al.  Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Friedrich M. Wahl,et al.  Block segmentation and text extraction in mixed text/image documents , 1982, Comput. Graph. Image Process..

[17]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Wenyu Liu,et al.  Point Linking Network for Object Detection , 2017, ArXiv.

[19]  Thomas Kieninger,et al.  Table Recognition and Labeling Using Intrinsic Layout Features , 1999 .

[20]  Jianming Hu,et al.  Page segmentation of Chinese newspapers , 2002, Pattern Recognit..

[21]  Ross B. Girshick,et al.  Mask R-CNN , 2017, 1703.06870.

[22]  Sriram Subramanian,et al.  Tilt techniques: investigating the dexterity of wrist-based input , 2009, CHI.