Skip to main content
Top

2022 | OriginalPaper | Chapter

Developing a Corpus of Hierarchically Classified STEM Images for Accessibility Purposes

Authors : Theodora Antonakopoulou, Paraskevi Riga, Georgios Kouroupetroglou

Published in: Computers Helping People with Special Needs

Publisher: Springer International Publishing

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

Even though considerable efforts have been made to provide effective image descriptions for digital accessibility, a large portion of STEM images, especially complex STEM images, nowadays remains inaccessible to people with visual disability. The quality of alt text is much more critical for university STEM textbooks as image descriptions must be accurate and detailed but not tire out the reader. This work aims to develop a large corpus of hierarchically classified STEM images from university textbooks which later will be used for developing appropriate guidelines for meaningful non-automatic high-quality alt-text image descriptions with the purpose of accessibility in mind. We present first our approach for the creation of the corpus with the STEM images. Our corpus at the current stage includes 8.859 STEM images from 82 textbooks in the domains of Mathematics, Biology, Computer Science, Chemistry, Physics and Geology. Then, we describe the methodology we followed for the classification of the images in the corpus and in particular, the way for the creation of the five categories and twenty-four subcategories, as well as the manner of the assignment of images to categories.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literature
4.
go back to reference Kavasidis, I., et al.: A saliency-based convolutional neural network for table and chart detection in digitized documents. In: International Conference on Image Analysis and Processing, 2019, pp. 292–302. Springer (2019) Kavasidis, I., et al.: A saliency-based convolutional neural network for table and chart detection in digitized documents. In: International Conference on Image Analysis and Processing, 2019, pp. 292–302. Springer (2019)
5.
go back to reference Savva, M., Kong, N., Chhajta, A., Fei-Fei, L., Agrawala, M., Heer, J.: ReVision: automated classification, analysis and redesign of chart images. In: 24th Annual ACM Symposium on User Interface Software and Technology, pp. 393–402 (2011). https://doi.org/10.1145/2047196.2047247 Savva, M., Kong, N., Chhajta, A., Fei-Fei, L., Agrawala, M., Heer, J.: ReVision: automated classification, analysis and redesign of chart images. In: 24th Annual ACM Symposium on User Interface Software and Technology, pp. 393–402 (2011). https://​doi.​org/​10.​1145/​2047196.​2047247
6.
go back to reference Amara, J., Kaur, P., Owonibi, M., Bouaziz, B.: Convolutional neural network based chart image classification. In: 25th Int. Conf. Central Europe on Computer Graphics, Visualization and Computer Vision, pp. 83–88 (2017) Amara, J., Kaur, P., Owonibi, M., Bouaziz, B.: Convolutional neural network based chart image classification. In: 25th Int. Conf. Central Europe on Computer Graphics, Visualization and Computer Vision, pp. 83–88 (2017)
7.
go back to reference Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: F. Pereira, F., C.J.C. Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 25, pp. 1097–1105 (2012) Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: F. Pereira, F., C.J.C. Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 25, pp. 1097–1105 (2012)
Metadata
Title
Developing a Corpus of Hierarchically Classified STEM Images for Accessibility Purposes
Authors
Theodora Antonakopoulou
Paraskevi Riga
Georgios Kouroupetroglou
Copyright Year
2022
DOI
https://doi.org/10.1007/978-3-031-08648-9_8