Sign in to use this feature.

Years

Between: -

Subjects

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Journals

Article Types

Countries / Regions

Search Results (3)

Search Parameters:
Keywords = mathematical formula transcription

Order results
Result details
Results per page
Select all
Export citation of selected articles as:
16 pages, 1256 KiB  
Article
Investigating Models for the Transcription of Mathematical Formulas in Images
by Christian Feichter and Tim Schlippe
Appl. Sci. 2024, 14(3), 1140; https://doi.org/10.3390/app14031140 - 29 Jan 2024
Cited by 5 | Viewed by 3001
Abstract
The automated transcription of mathematical formulas represents a complex challenge that is of great importance for digital processing and comprehensibility of mathematical content. Consequently, our goal was to analyze state-of-the-art approaches for the transcription of printed mathematical formulas on images into spoken English [...] Read more.
The automated transcription of mathematical formulas represents a complex challenge that is of great importance for digital processing and comprehensibility of mathematical content. Consequently, our goal was to analyze state-of-the-art approaches for the transcription of printed mathematical formulas on images into spoken English text. We focused on two approaches: (1) The combination of mathematical expression recognition (MER) models and natural language processing (NLP) models to convert formula images first into LaTeX code and then into text, and (2) the direct conversion of formula images into text using vision-language (VL) models. Since no dataset with printed mathematical formulas and corresponding English transcriptions existed, we created a new dataset, Formula2Text, for fine-tuning and evaluating our systems. Our best system for (1) combines the MER model LaTeX-OCR and the NLP model BART-Base, achieving a translation error rate of 36.14% compared with our reference transcriptions. In the task of converting LaTeX code to text, BART-Base, T5-Base, and FLAN-T5-Base even outperformed ChatGPT, GPT-3.5 Turbo, and GPT-4. For (2), the best VL model, TrOCR, achieves a translation error rate of 42.09%. This demonstrates that VL models, predominantly employed for classical image captioning tasks, possess significant potential for the transcription of mathematical formulas in images. Full article
(This article belongs to the Special Issue Deep Learning and Technology-Assisted Education)
Show Figures

Figure 1

14 pages, 341 KiB  
Article
A Novel Dynamical Regulation of mRNA Distribution by Cross-Talking Pathways
by Qiwen Sun, Zhaohang Cai and Chunjuan Zhu
Mathematics 2022, 10(9), 1515; https://doi.org/10.3390/math10091515 - 2 May 2022
Cited by 4 | Viewed by 1712
Abstract
In this paper, we use a similar approach to the one proposed by Chen and Jiao to calculate the mathematical formulas of the generating function V(z,t) and the mass function Pm(t) of a cross-talking [...] Read more.
In this paper, we use a similar approach to the one proposed by Chen and Jiao to calculate the mathematical formulas of the generating function V(z,t) and the mass function Pm(t) of a cross-talking pathways model in large parameter regions. Together with kinetic rates from yeast and mouse genes, our numerical examples reveal novel bimodal mRNA distributions for intermediate times, whereby the mode of distribution Pm(t) displays unimodality with the peak at m=0 for initial and long times, which has not been obtained in previous works. Such regulation of mRNA distribution exactly matches the transcriptional dynamics for the osmosensitive genes in Saccharomyces cerevisiae, which has not been generated by those models with one single pathway or feedback loops. This paper may provide us with a novel observation on transcriptional distribution dynamics regulated by multiple signaling pathways in response to environmental changes and genetic perturbations. Full article
(This article belongs to the Special Issue Difference and Differential Equations and Applications)
Show Figures

Figure 1

12 pages, 4042 KiB  
Proceeding Paper
Ad Oculos. Images, Imagination and Abstract Thinking
by Alessandra Cirafici
Proceedings 2017, 1(9), 945; https://doi.org/10.3390/proceedings1090945 - 14 Mar 2018
Cited by 1 | Viewed by 2526
Abstract
The unusual edition of Elements of Euclid released for publishing in 1847 by Oliver Byrne offers the occasion to suggest a few elements for discussion on the uniqueness of the ‘representation’ of geometric-mathematical thinking—and more in general of the abstract thinking—enshrined in its [...] Read more.
The unusual edition of Elements of Euclid released for publishing in 1847 by Oliver Byrne offers the occasion to suggest a few elements for discussion on the uniqueness of the ‘representation’ of geometric-mathematical thinking—and more in general of the abstract thinking—enshrined in its ‘nature of a pure imaginative vision able to connect the intelligible with the tangible’. The purpose is, thus, a reasoning on images and communicative artefacts, that, when articulated, provide different variations of the idea of ‘transcription’ of complex theoretical structures from one language (that of abstract logic) to another (that of sensory experience), with a view to facilitate, ease and make more accurate the noetic process. Images able over time to facilitate the understanding of complex and abstract theoretical principles—since able to show them in an extremely concrete way, ad oculos,—and which at some points could reveal the horizons of art interpretation to inscrutable and figurative meaningless formulas. Full article
Show Figures

Figure 1

Back to TopTop