CS297 Proposal
Image to LaTeX via Neural Networks
Avinash More (avinash.more@sjsu.edu)
Advisor: Dr. Chris Pollett
Description:
Many research papers in mathematics, computer science, and physics are written in LaTeX format. While writing technical papers or articles, there are some scenarios where the text to be written is a mathematical equation. Writing a mathematical equation in LaTeX format takes a lot more time compared to writing the same equation on a paper. The time-consuming approach of converting the equation written on paper to LaTeX format can be automated and optimized.
This project will develop a tool which will take an image of a mathematical equation as an input and will attempt to output the corresponding mathematical equation in the LaTeX form.
Schedule:
Week 1:
Aug. 29 - Sep. 4 | Project topic discussion meeting with Dr. Pollett |
Week 2:
Sep. 5 - Sep. 11 | Exploring Latex and finding papers |
Week 3:
Sep. 12 - Sep. 18 | Deliverable #1: Famous Mathematical Equations to Corresponding LaTeX |
Week 4:
Sep. 19 - Sep. 25 | Read Paper- "Image-to-Markup Generation with Coarse-to-Fine Attention" |
Week 5:
Sep. 26 - Oct. 2 | Read Paper- "Show and Tell: A Neural Image Caption Generator" |
Week 6:
Oct. 3 - Oct. 9 | Deliverable #2: Install TensorFlow and go through MNIST demo |
Week 7:
Oct. 10 - Oct. 16 | Deep Learning: Chapter 9 |
Week 8:
Oct. 17 - Oct. 23 | Get understanding of RNN and LSTM |
Week 9:
Oct. 24 - Oct. 30 | Work on Deliverable 3 |
Week 10:
Oct. 31 - Nov. 6 | Deliverable #3: Explore data generation approaches |
Week 11:
Nov. 7 - Nov. 13 | Work on Deliverable 4 |
Week 12:
Nov. 14 - Nov. 20 | Work on Deliverable 4 |
Week 13:
Nov. 21 - Nov. 27 | Deliverable #4: Decide the Architectural Diagram |
Week 14:
Nov. 28 - Dec. 4 | Work on Deliverable 5 |
Week 15:
Dec. 4 - Dec. 10 | Work on Deliverable 5 |
Week 16:
Dec. 11 - Dec. 17 | Deliverable #5: Complete the CS297 Final Report |
Deliverables:
The full project will be done when CS298 is completed. The following will
be done by the end of CS297:
Deliverable #1: Famous Mathematical Equations to Corresponding LaTeX
Deliverable #2: Install TensorFlow and go through MNIST demo
Deliverable #3: Explore data generation approaches
Deliverable #4: Decide the Architectural Diagram
Deliverable #5: Complete the CS297 Final Report.
References:
[AuthorYear] Reference_work. Author_Names. Publisher. Year.
Yuntian Deng, Anssi Kanervisto, Jeffrey Ling, Alexander M. Rush; "Image-to-Markup Generation with Coarse-to-Fine Attention"; Proceedings of the 34th International Conference on Machine Learning, 2017
Oriol Vinyals, Alexander Toshev, Samy Bengio, Dumitru Erhan; "Show and Tell: A Neural Image Caption Generator"; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015
|