Layout Segmentation and Description of Tibetan Document Images Based on Adaptive Run Length Smoothing Algorithm

Yuanyuan Chen; Weilan Wang; Huaming Liu; Zhengqi Cai; Penghai Zhao

doi:10.3788/LOP202158.1410006

[1] Li Y X, Zou Y J, Ma J W. DeepLayout: a semantic segmentation approach to page layout analysis[M]. //Huang D S, Gromiha M M, Han K, et al. Intelligent computing methodologies. Lecture notes in computer science, 10956, 266-277(2018).

[2] Oliveira S A, Seguin B, Kaplan F. dhSegment: a generic deep-learning approach for document segmentation[C]. //2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR), August 5-8, 2018, Niagara Falls, NY, USA, 7-12(2018).

[3] Chen K, Seuret M, Hennebert J et al. Convolutional neural networks for page segmentation of historical document images[C]. //2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), November 9-15, 2017, Kyoto, Japan., 965-970(2017).

[4] Zulfiqar A, Ul-Hasan A, Shafait F. Logical layout analysis using deep learning[C]. //2019 Digital Image Computing: Techniques and Applications (DICTA), December 2-4, 2019, Perth, WA, Australia, 1-5(2019).

[5] Wang Y W. Research and implementation of layout analysis and post-processing for Mongolian document images[D](2017).

[6] Chen X, He J J, Li H J et al. Manchu document layout analysis based on mask R-CNN[J]. Journal of Dalian Minzu University, 21, 240-245(2019).

[7] Ma L L, Long C J, Duan L J et al. Segmentation and recognition for historical Tibetan document images[J]. IEEE Access, 8, 52641-52651(2020).

[8] Liu H M, Bi X H, Wang W L. Layout analysis of historical Tibetan documents[C]. //2019 2nd International Conference on Artificial Intelligence and Big Data (ICAIBD), May 25-28, 2019, Chengdu, China., 74-78(2019).

[9] Zhang X Q, Ma L L, Duan L J et al. Layout analysis for historical Tibetan documents based on convolutional denoising autoencoder[J]. Journal of Chinese Information Processing, 32, 67-73, 81(2018).

[10] Zhang X Q. Research on layout segmentation method for historical Tibetan documents[D](2018).

[11] Zhang X Q, Duan L J, Ma L L et al. Text extraction for historical Tibetan document images based on connected component analysis and corner point detection[M]. //Yang J F, Hu Q H, Cheng M M, et al. Communications in computer and information science. Communications in computer and information science, 772, 545-555(2017).

[12] Duan L J, Zhang X Q, Ma L L et al. Text extraction method for historical Tibetan document images based on block projections[J]. Optoelectronics Letters, 13, 457-461(2017).

[13] Rais M, Goussies N A, Mejail M. Using adaptive run length smoothing algorithm for accurate text localization in images[M]. //Martin C S, Kim S W. Progress in pattern recognition, image analysis, computer vision, and applications. Lecture notes in computer science, 7042, 149-156(2011).

[14] Papamarkos N, Tzortzakis J, Gatos B. Determination of run-length smoothing values for document segmentation[C]. //Proceedings of Third International Conference on Electronics, Circuits, and Systems, October 16, 1996, Rhodes, Greece., 684-687(1996).

[15] Zhang L, Zhu Y, Wu G W. English document segmentation based on run-length smearing algorithm[J]. Acta Electronica Sinica, 27, 102-104(1999).

[16] Chen Y. Design and implementation of printed Tibetan recognition software on android platform[D](2020).