CDeC-Net: Composite Deformable Cascade Network for Table Detection in Document Images

• Published in: 2020 25th International Conference on Pattern Recognition (ICPR) pp. 9491 - 9498
• Main Authors: Agarwal, Madhav, Mondal, Ajoy, Jawahar, C. V.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 10.01.2021
• Subjects: Benchmark testing; Cascade Mask R-CNN; Convolution; Convolutional codes; Data mining; deformable convolution; Mathematical model; Page object; Protocols; Reproducibility of results; single model; table detection
• DOI: 10.1109/ICPR48806.2021.9411922

Localizing page elements/objects such as tables, figures, equations, etc. is the primary step in extracting information from document images. We propose a novel end-to-end trainable deep network, (cnec-xet) for detecting tables present in the documents. The proposed network consists of a multistage extension of Mask R-CNN with a dual backbone having deformable convolution for detecting tables varying in scale with high detection accuracy at higher IoU threshold. We empirically evaluate CDeC-Net on the publicly available benchmark datasets with extensive experiments. Our solution has three important properties: (i) a single trained model CDeC-Net ‡ that performs well across all the popular benchmark datasets; (ii) we report excellent performances across multiple, including higher, thresholds of IoU; (iii) by following the same protocol of the recent papers for each of the benchmarks, we consistently demonstrate the superior quantitative performance. Our code and models are publicly available at https://github.com/mdv3101/CDeCNet for enabling reproducibility of the results.