Evaluation of Shallow Convolutional Neural Network in Open-World Chart Image Classification

被引:0
作者
Bajić F. [1 ]
Habijan M. [2 ]
Nenadić K. [2 ]
机构
[1] University Computing Centre, University of Zagreb, Zagreb
[2] Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek
来源
Informatica (Slovenia) | 2024年 / 48卷 / 06期
关键词
chart image; data visualization; machine learning; neural network; pattern recognition;
D O I
10.31449/inf.v48i6.5660
中图分类号
学科分类号
摘要
Data’s role is pivotal in the era of internet technologies, but unstructured data poses comprehension challenges. Data visualizations like charts have emerged as crucial tools for condensing complex information. Classifying charts and applying various processing techniques are vital to interpreting visual data. Traditional chart image classification methods rely on predefined rules and have limited accuracy. The advent of support vector machines (SVMs) and convolutional neural networks (CNNs) significantly improved the accuracy of these methods. This research evaluates our previously introduced Shallow convolutional neural network (SCNN) architecture for chart image classification, comprising four convolutional layers, two max-pooling layers, and one fully-connected layer. The network achieves state-of-the-art results, requiring smaller datasets and reduced computational resources. When two networks are combined into Siamese SCNN (SSCNN), emphasizing generalization, it achieves high accuracy with small datasets and excels in open-set classification. The evaluation process encompasses the utilization of six publicly available datasets. © 2024 Slovene Society Informatika. All rights reserved.
引用
收藏
页码:185 / 198
页数:13
相关论文
共 57 条
  • [1] Choi J., Jung S., Park D. G., Choo J., Elmqvist N., Visualizing for the non□visual: Enabling the visually impaired to use visualization, Computer Graphics Forum, 38, (2019)
  • [2] Poco J., Heer J., Reverse□engineering visualizations: Recovering visual encodings from chart images, Computer Graphics Forum, 36, (2017)
  • [3] Bajic F., Job J., Review of chart image detection and classification, International Journal on Document Analysis and Recognition (IJDAR), pp. 1-22, (2023)
  • [4] Bajic F., Job J., Nenadic K., Chart classification using simplified vgg model, 2019 International Conference on Systems, Signals and Image Processing (IWSSIP), pp. 229-233, (2019)
  • [5] Shahira K. C., Lijiya A., Document image classification: Towards assisting visually impaired, TENCON 2019 - 2019 IEEE Region 10 Conference (TENCON), pp. 852-857, (2019)
  • [6] Bajic F., Job J., Nenadic K., Data visualization classification using simple convolutional neural network model, International Journal of Electrical and Computer Engineering, 11, pp. 43-51, (2020)
  • [7] Rane C., Subramanya S. M., Endluri D. S., Wu J., Giles C. L., Chartreader: Automatic parsing of bar-plots, 2021 IEEE 22nd International Conference on Information Reuse and Integration for Data Science (IRI), pp. 318-325, (2021)
  • [8] Dai W., Wang M., Niu Z., Zhang J., Chart decoder: Generating textual and numeric information from chart images automatically, J. Vis. Lang. Com-put, 48, pp. 101-109, (2018)
  • [9] Balaji A., Ramanathan T., Sonathi V., Chart-text: A fully automated chart image descriptor, (2018)
  • [10] Jung D., Kim W., Song H., Hwang J., Lee B., Kim B. H., Seo J., Chartsense: Interactive data extraction from chart images, Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems, (2017)