Automatic Conversions of Mathematical Braille: A Survey of Main Difficulties in Different Languages

Moço, Victor; Archambault, Dominique

doi:10.1007/978-3-540-27817-7_95

Cited by 12 publications

(4 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…listening their textual descriptions or not. For this purpose, we create a test set of mathematical equation images which are cropped from NCRT class V mathematical book 1 . Test set consists of 398 cropped equation images of various types of equations: integer, decimal, fraction, addition, subtraction, multiplication and division.…”

Section: Real World Experimentsmentioning

confidence: 99%

“…Braille is the popular and more convenient way to access the document for blind and VI students. Unfortunately, many documents are not available in Braille, since the conversion of mathematical documents in Braille is more difficult and complicated [1]. Moreover, it is also difficult for students who are comfortable for reading literary Braille transcriptions [2].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Textual Description for Mathematical Equations

Mondal

Jawahar

2019

2019 International Conference on Document Analysis and Recognition (ICDAR)

View full text Add to dashboard Cite

Reading of mathematical expression or equation in the document images is very challenging due to the large variability of mathematical symbols and expressions. In this paper, we pose reading of mathematical equation as a task of generation of the textual description which interprets the internal meaning of this equation. Inspired by the natural image captioning problem in computer vision, we present a mathematical equation description (MED) model, a novel end-to-end trainable deep neural network based approach that learns to generate a textual description for reading mathematical equation images. Our MED model consists of a convolution neural network as an encoder that extracts features of input mathematical equation images and a recurrent neural network with attention mechanism which generates description related to the input mathematical equation images. Due to the unavailability of mathematical equation image data sets with their textual descriptions, we generate two data sets for experimental purpose. To validate the effectiveness of our MED model, we conduct a real-world experiment to see whether the students are able to write equations by only reading or listening their textual descriptions or not. Experiments conclude that the students are able to write most of the equations correctly by reading their textual descriptions only.

show abstract

Section: Real World Experimentsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Textual Description for Mathematical Equations

Mondal

Jawahar

2019

2019 International Conference on Document Analysis and Recognition (ICDAR)

View full text Add to dashboard Cite

show abstract

“…For web browsing, software like BrailleSurf [7] and WebblE [8] would convert text data into either speech or Braille. Also mathematical software for the visually impaired such as VICKIE [9] and AudioMath [10] could transfer data expressed in LaTex or MathML format into another form (i.e. Braille or speech).…”

Section: Introductionmentioning

confidence: 99%

“…With reference to the user profile and context, the CA would convert text into speech. 9. DMA receives converted data.…”

mentioning

confidence: 99%

Information Access in a Multimodal Multimedia Computing System for Mobile Visually-Impaired Users

Awde

Hina

Tadj

et al. 2006

2006 IEEE International Symposium on Industrial Electronics

View full text Add to dashboard Cite

A multimodal interface allows computing with input and output that best suits the needs of a user, including those with disability. In our multimodal multimedia (MM) computing system for visually-impaired users, the selection of media, modalities and types of applications for activation depends on user's context and application data. The adaptation of a computing system to the needs of a mobile user is essential in order that the user could continue working on his task at anytime and anywhere, thereby increasing his productivity. Our system is adaptive because the user could access his information anytime and anywhere. This access to user information is made possible through wired and wireless networks. The user profile, user task and data, and the system's knowledge database (KD) do "follow" the user wherever he goes, hence the system adapts accordingly based on the user's condition. Our system detects user context and the user's application data, consults the KD and selects the appropriate media, modalities and types of applications for activation. This work is an original contribution to the ongoing research in helping the visually-impaired users to become autonomous in using the computing system. Our aim is to improve the computing productivity of a visually-impaired user.

show abstract