Efficient Table Lines Segmentation with Asymmetric Convolutions

Efficient Table Lines Segmentation with Asymmetric Convolutions
Mohammad Minouei, Mohammad Reza Soheili, Didier Stricker
In: Wolfgang Osten; Dmitry Nikolaev; Jianhong Zhou (Hrsg.). Proceedings Volume 12084, Fourteenth International Conference on Machine Vision (ICMV 2021). International Conference on Machine Vision (ICMV-2021), November 8-12, Rome, Italy, Pages 1-7, Vol. 12084, SPIE, 3/2022.

Abstract:

Automatic table understanding in document images is one of the most challenging topics in the research commu- nity. This is owing to the fact that tables may appear in various structures and designs. However, a big majority of tables are designed with ruling lines. Recognizing these lines in images is mandatory in numerous table un- derstanding processes. Previous works have utilized hand-crafted features, merely applicable to distortion-free images. We present a compact CNN as an alternative solution. This method is capable of segmenting the ruling lines in challenging environments. In addition to the proposed architecture, a new dataset is generated for this task that contains 35K labeled samples. The reported results on this dataset show the effectiveness of this method. Our implementation and dataset are available online.