dc.contributor.advisor | Nguyễn, Quốc Trung | |
dc.contributor.advisor | Nguyễn, Quốc Tiến | |
dc.contributor.author | Hoàng, Quốc Trung | |
dc.contributor.author | Thái, Duy Bảo | |
dc.date.accessioned | 2024-06-19T08:28:22Z | |
dc.date.available | 2024-06-19T08:28:22Z | |
dc.date.issued | 2024 | |
dc.identifier.uri | http://ds.libol.fpt.edu.vn/handle/123456789/4105 | |
dc.description.abstract | Recognizing mathematical formulas in images and translating them into LaTeX sequences, both printed and handwritten, is challenging due to the complexity of two-dimensional formulas and lack of training data. Traditional methods can only handle simple formulas and are not effective for complex formulas. In this paper, we introduce the Sumen (Scaling Up Image-to-LaTeX Performance) model, an encoder-decoder architecture based on Transformer with attention mechanism trained on the largest dataset from previous works. The model achieves a BLEU score of 95.59, Edit Distance (ED) of 97.3, and Exact Match (EM) of 69.23 on the img2latex100k benchmark. On the CROHME 2014/2016/2019 benchmark, the corresponding results on Expression Recognition Rates (ExpRate) are 58.01/82.39/78.99 and Word Error Rate (WER) are 9.46/2.55/4.51. All of our metrics outperform stateof-the-art methods on both printed and handwritten formulas. | en_US |
dc.language.iso | en | en_US |
dc.publisher | FPTU HCM | en_US |
dc.subject | Đồ án tốt nghiệp | en_US |
dc.subject | Capstone Project | en_US |
dc.subject | Trí tuệ nhân tạo | en_US |
dc.subject | Artificial Intelligence | en_US |
dc.subject | LaTeX code | en_US |
dc.subject | End to end | en_US |
dc.subject | Attention mechanism | en_US |
dc.subject | SP24AI12 | en_US |
dc.subject | Chuyển đổi hình ảnh | en_US |
dc.title | Math Formula Images to LaTeX code based on end-to-end approach with Attention mechanism | en_US |
dc.title.alternative | Chuyển đổi hình ảnh công thức toán học sang mã LaTeX dựa trên cách tiếp cận end-to-end với cơ chế Attention | en_US |
dc.type | Thesis | en_US |
Bộ sưu tập thuộc về Trung tâm Thông tin - Thư viện - Trường Đại học FPT
Địa chỉ: Phòng 207 - Tầng 1 - Km 28 - Khu công nghệ cao Hòa Lạc - Thạch Hòa - Thạch Thất - Hà Nội
Điện thoại: 844.66805912 - FAX: - Email: thuvien_fu_hoalac@fpt.edu.vn