Abstract
Reverse-engineering bar charts extract textual and numeric information from the visual representations of bar charts to support application scenarios that require the underlying information. In this paper, we propose a neural network-based method for reverse-engineering bar charts. We adopt a neural network-based object detection model to simultaneously localize and classify textual information. This approach improves the efficiency of textual information extraction. We design an encoder-decoder framework that integrates convolutional and recurrent neural networks to extract numeric information. We further introduce an attention mechanism into the framework to achieve high accuracy and robustness. Synthetic and real-world datasets are used to evaluate the effectiveness of the method. To the best of our knowledge, this work takes the lead in constructing a complete neural network-based method of reverse-engineering bar charts.
Graphic abstract
Similar content being viewed by others
References
Al-ZaidyRA, Giles CL (2015) Automatic extraction of data from bar charts. In: Proceedings of the 8th international conference on knowledge capture. ACM, p 30
Al-ZaidyRA, Choudhury SR, Giles CL (2016) Automatic summary generation for scientific data charts. In: Workshops at the 30th AAAI conference on artificial intelligence. AAAI, pp 658–663
BahdanauD, Cho K, Bengio Y (2014) Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473
Battle L, Duan P, Miranda Z, Mukusheva D, Chang R, Stonebraker M (2018) Beagle: automated extraction and interpretation of visualizations from the web. In: Proceedings of the 2018 CHI conference on human factors in computing systems. ACM, p 594
BeltramelliT (2018) pix2code: generating code from a graphical user interface screenshot. In: Proceedings of the ACM SIGCHI symposium on engineering interactive computing systems. ACM, p 3
Bi C, Yang L, Duan Y, Shi Y (2019a) A survey on visualization of tensor field. J Vis 22(3):641–660
Bi C, Guosheng Pan Lu, Yang C-C, Hou M, Huang Y (2019b) Evacuation route recommendation using auto-encoder and Markov decision process. Appl Soft Comput 84(105741):1–11
BöschenF, Scherp A (2015) Multi-oriented text extraction from information graphics. In: Proceedings of the 2015 ACM symposium on document engineering. ACM, pp 35–38
ChenZ, Cafarella M, Adar E (2015) Diagramflyer: a search engine for data-driven diagrams. In: Proceedings of the 24th international conference on World Wide Web. ACM, pp 183–186
Chen S, Li J, Andrienko G, Andrienko N, Wang Y et al (2020) Supporting story synthesis: bridging the gap between visual analytics and storytelling. IEEE Trans Vis Comput Graph 26(7):2499–2516
CholletF (2017) Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, pp 1251–1258
ChoudhurySR, Wang S, Giles CL (2016) Scalable algorithms for scholarly figure mining and semantics. In: Proceedings of the international workshop on semantic big data. ACM, p 1
Cliche M, Rosenberg D, Madeka D, Yee C (2017a) Scatteract: automated extraction of data from scatter plots. In: Joint European conference on machine learning and knowledge discovery in databases. Springer, Cham, pp 135–150
Cliché M, Rosenberg D, Madeka D et al (2017b) Scatteract: automated extraction of data from scatter plots. In: Joint European conference on machine learning and knowledge discovery in databases. Springer, Cham, pp 135–150
Dai W, Wang M, Niu Z, Zhang J (2018) Chart decoder: generating textual and numeric information from chart images automatically. J Vis Lang Comput 48:101–109
DataThief. https://datathief.org/. Accessed 21 Oct 2019
Everingham M, Van Gool L, Williams CK, Winn J, Zisserman A (2010) The Pascal visual object classes (VOC) challenge. Int J Comput Vis 88(2):303–338
HeK, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, pp 770–778
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780
HuangW, Tan CL (2007) A system for understanding imaged infographics and its applications. In: Proceedings of the 2007 ACM symposium on document engineering. ACM, pp 9–18
Huang Z, Zhao Y, Chen W, Gao S, Yu K, Xu W, Tang M, Zhu M, Xu M (2020) A natural-language-based visual query approach of uncertain human trajectories. IEEE Trans Vis Comput Graph 26(1):1256–1266
JayantC, Renzelmann M, Wen D, Krisnandi S, Ladner R, Comden D (2007) Automated tactile graphics translation: in the field. In: Proceedings of the 9th international ACM SIGACCESS conference on computers and accessibility. ACM, pp 75–82
JungD, Kim W, Song H, Hwang JI, Lee B, Kim B, Seo J (2017) ChartSense: interactive data extraction from chart images. In: Proceedings of the 2017 CHI conference on human factors in computing systems. ACM, pp 6706–6717
Kong N, Agrawala M (2012) Graphical overlays: using layered elements to aid chart reading. IEEE Trans Vis Comput Graph 18(12):2631–2638
Krizhevsky A, Sutskever I, Hinton GE (2017) Imagenet classification with deep convolutional neural networks. Commun ACM 60(6):84–90
Lin TY, Maire M, Belongie S, Hays J, Perona P et al (2014) Microsoft coco: common objects in context. In: European conference on computer vision. Springer, Cham, pp 740–755
Liu L, Ouyang W, Wang X, Fieguth P, Chen J, Liu X, Pietikäinen M (2019a) Deep learning for generic object detection: a survey. Int J Comput Vis 128(1):261–318
Liu X, Klabjan D, NBless P (2019) Data extraction from charts via single deep neural network. arXiv preprint arXiv:1906.11906
Ma Y, Tung AKH, Wang W, Gao X, Pan Z, Chen W (2020) ScatterNet: a deep subjective similarity model for visual analysis of scatterplots. IEEE Trans Vis Comput Graph 26(3):1562–1576
Matplotlib. https://matplotlib.org/. Accessed 21 Oct 2019
Mei H, Wei Y, Zhou S, Lin B, Zhao Y, Xia J, Chen W (2020a) RSATree: distribution-aware data representation of large-scale tabular datasets for flexible visual query. IEEE Trans Vis Comput Graph 26(1):1161–1171
Mei H, Guan H, Wen X, Chen W (2020b) DataV: data visualization on large high-resolution displays. Vis Inform 4(3):12–23
MéndezGG, Nacenta MA, Vandenheste S (2016) iVoLVER: interactive visual language for visualization extraction and reconstruction. In: Proceedings of the 2016 CHI conference on human factors in computing systems. ACM, pp 4073–4085
Microsoft Project Oxford. https://www.projectoxford.ai/vision. Accessed 21 Oct 2019
Poco J, Heer J (2017) Reverse-engineering visualizations: recovering visual encodings from chart images. Comput Graph For 36(3):353–363
Ren S, He K, Girshick R, Sun J (2017) Faster r-cnn: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137–1149
SavvaM, Kong N, Chhajta A, Fei-Fei L, Agrawala M, Heer J (2011) Revision: automated classification, analysis and redesign of chart images. In: Proceedings of the 24th annual ACM symposium on user interface software and technology. ACM, pp 393–402
SiegelN, Horvitz Z, Levin R, Divvala S, Farhadi A (2016) FigureSeer: parsing result-figures in research papers. In: European conference on computer vision. Springer, Cham, pp 664–680
SmithR (2007) An overview of the Tesseract OCR engine. In: 9th international conference on document analysis and recognition. IEEE, pp 629–633
WebPlotDigitizer. https://automeris.io/WebPlotDigitizer/. Accessed 21 Oct 2019
Wei Y, Mei H, Zhao Y, Zhou S, Lin B, Jiang H, Chen W (2020) Evaluating perceptual bias during geometric scaling of scatterplots. IEEE Trans Vis Comput Graph 26(1):100–111
Xia J, Ye F, Chen W, Wang Y, Chen W, Ma Y, Tung AKH (2018) LDSScanner: exploratory analysis of low-dimensional structures in high-dimensional datasets. IEEE Trans Vis Comput Graph 24(1):236–245
XuK, Ba JL, Kiros R, Cho K, Courville A et al (2015) Show, attend and tell: Neural image caption generation with visual attention. In: International conference on machine learning. IEEE, pp 2048–2057
YuanJ, Chen C, Yang W, Liu M, Xia J, Liu S (2020) A survey of visual analytics techniques for machine learning. arXiv preprint arXiv:2008.09632
Zhao Y, Zhou F, Fan X, Liang X, Liu Y (2013) IDSRadar: a real-time visualization framework for IDS alerts. Sci China Inf Sci 56(8):1–12
Zhao Y, Wang L, Li S, Zhou F, Lin X, Lu Q, Ren L (2019) A visual analysis approach for understanding durability test data of automotive products. ACM Trans Intell Syst Technol 10(6):70–93
Zhao Y, Luo X, Lin X, Wang H, Kui X, Zhou F, Wang J, Chen Y, Chen W (2020) Visual analytics for electromagnetic situation awareness in radio monitoring and management. IEEE Trans Vis Comput Graph 26(1):590–600
Zhou ZH (2019) Abductive learning: towards bridging machine learning and logical reasoning. Sci China Inf Sci 62(7):191–193
ZhouYP, Tan CL (2000) Hough technique for bar charts detection and recognition in document images. In: Proceedings 2000 international conference on image processing. IEEE, pp 605–608
Zhou F, Lin X, Liu C, Zhao Y, Xu P, Ren L, Xue T, Ren L (2019) A survey of visualization for smart manufacturing. J Vis 22(2):419–435
Acknowledgements
This work was supported in part by the National Natural Science and Technology Fundamental Resources Investigation Program of China (No. 2018FY10090002), the National Natural Science Foundation of China (Nos. 61672538 and 61872388), and the Natural Science Foundation of Hunan Province (No. 2020JJ4758). The data sets and source codes of this work are available at Github: https://github.com/csuvis/BarchartReverseEngineering.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Zhou, F., Zhao, Y., Chen, W. et al. Reverse-engineering bar charts using neural networks. J Vis 24, 419–435 (2021). https://doi.org/10.1007/s12650-020-00702-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12650-020-00702-6