Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
119 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

A Survey on Figure Classification Techniques in Scientific Documents (2307.05694v1)

Published 9 Jul 2023 in cs.IR, cs.CV, and cs.LG

Abstract: Figures visually represent an essential piece of information and provide an effective means to communicate scientific facts. Recently there have been many efforts toward extracting data directly from figures, specifically from tables, diagrams, and plots, using different Artificial Intelligence and Machine Learning techniques. This is because removing information from figures could lead to deeper insights into the concepts highlighted in the scientific documents. In this survey paper, we systematically categorize figures into five classes - tables, photos, diagrams, maps, and plots, and subsequently present a critical review of the existing methodologies and data sets that address the problem of figure classification. Finally, we identify the current research gaps and provide possible directions for further research on figure classification.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (33)
  1. L. Cai, J. Gao, and D. Zhao, “A review of the application of deep learning in medical image classification and segmentation,” Annals of Translational Medicine, vol. 8, no. 11, 2020.
  2. S. Rani.B.R, “Classification of vehicles using image processing techniques,” International journal of engineering research and technology, vol. 3, 2018.
  3. L. Liu, Z. Wang, T. Qiu, Q. Chen, Y. Lu, and C. Y. Suen, “Document image classification: Progress over two decades,” Neurocomputing, vol. 453, pp. 223–240, 2021.
  4. M. Kumar, M. Kamble, S. Pawar, P. Patil, and N. Bonde, “Survey on techniques for plant leaf classification,” 2011.
  5. K. Davila, S. Setlur, D. Doermann, B. U. Kota, and V. Govindaraju, “Chart Mining: A Survey of Methods for Automated Chart Analysis,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 43, pp. 3799–3819, Nov. 2021. Conference Name: IEEE Transactions on Pattern Analysis and Machine Intelligence.
  6. N. Siegel, Z. Horvitz, R. Levin, S. Divvala, and A. Farhadi, “FigureSeer: Parsing Result-Figures in Research Papers,” in ECCV, 2016.
  7. P.-S. Lee, J. D. West, and B. Howe, “Viziometrics: Analyzing Visual Information in the Scientific Literature,” IEEE Transactions on Big Data, vol. 4, pp. 117–129, Mar. 2018. Conference Name: IEEE Transactions on Big Data.
  8. D. Morris, E. Müller-Budack, and R. Ewerth, “SlideImages: A Dataset for Educational Image Classification,” arXiv:2001.06823 [cs], Jan. 2020. arXiv: 2001.06823.
  9. J. kv, A. Mondal, and C. Jawahar, “DocFigure: A Dataset for Scientific Document Figure Classification,” pp. 74–79, Sept. 2019.
  10. V. Andrearczyk and H. Müller, “Deep Multimodal Classification of Image Types in Biomedical Journal Figures,” in CLEF, 2018.
  11. I. Almakky, V. Palade, Y.-L. Hedley, and J. Yang, “A stacked deep autoencoder model for biomedical figure classification,” in 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), pp. 1134–1138, Apr. 2018. ISSN: 1945-8452.
  12. X. Lu, S. Kataria, W. J. Brouwer, J. Z. Wang, P. Mitra, and C. L. Giles, “Automated analysis of images in documents for intelligent document search,” International Journal on Document Analysis and Recognition (IJDAR), vol. 12, pp. 65–81, July 2009.
  13. B. Cheng, R. Stanley, S. Antani, and G. Thoma, “Graphical Figure Classification Using Data Fusion for Integrating Text and Image Features,” Proceedings of the International Conference on Document Analysis and Recognition, ICDAR, Aug. 2013.
  14. A. Lagopoulos, N. Kapraras, V. Amanatiadis, A. Fachantidis, and G. Tsoumakas, “Classifying Biomedical Figures by Modality via Multi-Label Learning,” IEEE Journal of Biomedical and Health Informatics, vol. 23, pp. 2230–2237, Nov. 2019. Conference Name: IEEE Journal of Biomedical and Health Informatics.
  15. T. Giannakopoulos, Y. Foufoulas, E. Stamatogiannakis, H. Dimitropoulos, N. Manola, and Y. Ioannidis, “Visual-Based Classification of Figures from Scientific Literature,” pp. 1059–1060, May 2015.
  16. K. A. Hashmi, M. Liwicki, D. Stricker, M. A. Afzal, M. A. Afzal, and M. Z. Afzal, “Current Status and Performance Analysis of Table Recognition in Document Images with Deep Neural Networks,” arXiv:2104.14272 [cs], May 2021. arXiv: 2104.14272.
  17. M. Savva, N. Kong, A. Chhajta, L. Fei-Fei, M. Agrawala, and J. Heer, “ReVision: automated classification, analysis and redesign of chart images,” in Proceedings of the 24th annual ACM symposium on User interface software and technology, UIST ’11, (New York, NY, USA), pp. 393–402, Association for Computing Machinery, Oct. 2011.
  18. J. Gao, Y. Zhou, and K. E. Barner, “View: Visual Information Extraction Widget for improving chart images accessibility,” in 2012 19th IEEE International Conference on Image Processing, pp. 2865–2868, Sept. 2012. ISSN: 2381-8549.
  19. V. Karthikeyani and S. Nagarajan, “Machine Learning Classification Algorithms to Recognize Chart Types in Portable Document Format (PDF) Files,” International Journal of Computer Applications, vol. 39, pp. 1–5, Feb. 2012.
  20. X. Liu, B. Tang, Z. Wang, X. Xu, S. Pu, D. Tao, and M. Song, “Chart classification by combining deep convolutional networks and deep belief networks,” in 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 801–805, Aug. 2015.
  21. J. Amara, P. Kaur, M. Owonibi, and B. Bouaziz, “Convolutional Neural Network Based Chart Image Classification,” May 2017.
  22. D. Jung, W. Kim, H. Song, J. Hwang, B. Lee, B. H. Kim, and J. Seo, “ChartSense: Interactive Data Extraction from Chart Images,” CHI, 2017.
  23. M. Sanderson and P. Clough, “Imageclef—the clef cross language image retrieval track— imageclef/lifeclef—multimedia retrieval in clef,” 2019.
  24. A. Balaji, T. Ramanathan, and V. Sonathi, “Chart-Text: A Fully Automated Chart Image Descriptor,” Dec. 2018. arXiv:1812.10636 [cs].
  25. P. Chagas, R. Akiyama, A. Meiguins, C. Santos, F. Saraiva, B. Meiguins, and J. Morais, “Evaluation of Convolutional Neural Network Architectures for Chart Image Classification,” in 2018 International Joint Conference on Neural Networks (IJCNN), pp. 1–8, July 2018. ISSN: 2161-4407.
  26. W. Dai, M. Wang, Z. Niu, and J. Zhang, “Chart decoder: Generating textual and numeric information from chart images automatically,” Journal of Visual Languages & Computing, vol. 48, pp. 101–109, Oct. 2018.
  27. X. Liu, D. Klabjan, and P. NBless, “Data Extraction from Charts via Single Deep Neural Network,” June 2019. arXiv:1906.11906 [cs].
  28. K. Davila, B. U. Kota, S. Setlur, V. Govindaraju, C. Tensmeyer, S. Shekhar, and R. Chaudhry, “ICDAR 2019 Competition on Harvesting Raw Tables from Infographics (CHART-Infographics),” in 2019 International Conference on Document Analysis and Recognition (ICDAR), (Sydney, Australia), pp. 1594–1599, IEEE, Sept. 2019.
  29. F. Bajić, J. Job, and K. Nenadić, “Data Visualization Classification Using Simple Convolutional Neural Network Model,” International Journal of Electrical and Computer Engineering Systems (IJECES), vol. 11, no. 1, pp. 43–51, 2020.
  30. T. Araújo, P. Chagas, J. Alves, C. Santos, B. Sousa Santos, and B. Serique Meiguins, “A Real-World Approach on the Problem of Chart Recognition Using Classification, Detection and Perspective Correction,” Sensors, vol. 20, p. 4370, Jan. 2020. Number: 16 Publisher: Multidisciplinary Digital Publishing Institute.
  31. J. Luo, Z. Li, J. Wang, and C.-Y. Lin, “ChartOCR: Data Extraction from Charts Images via a Deep Hybrid Framework,” in 2021 IEEE Winter Conference on Applications of Computer Vision (WACV), (Waikoloa, HI, USA), pp. 1916–1924, IEEE, Jan. 2021.
  32. K. Davila, C. Tensmeyer, S. Shekhar, H. Singh, S. Setlur, and V. Govindaraju, “ICPR 2020 - Competition on Harvesting Raw Tables from Infographics,” pp. 361–380, Feb. 2021.
  33. J. Thiyam, S. R. Singh, and P. K. Bora, “Challenges in chart image classification: a comparative study of different deep learning methods,” in Proceedings of the 21st ACM Symposium on Document Engineering, DocEng ’21, (New York, NY, USA), pp. 1–4, Association for Computing Machinery, Aug. 2021.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Anurag Dhote (2 papers)
  2. Mohammed Javed (29 papers)
  3. David S Doermann (3 papers)

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now