International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Write2Math: Adaptive Handwritten Math Recognition with Self-Correction and LaTeX Conversion |
|---|---|
| ABSTRACT | With the era of digital education, the skill to transform handwritten math expressions into well-defined forms like LaTeX is more valuable than ever. Write2Math is an intelligent handwriting math recognition system based on pix2tex deep learning. It allows users to input images or digital ink of handwritten math and obtain correct LaTeX output. Three main innovations are included in the system: Adaptive Learning, which adapts recognition to the unique handwriting of each user over time; Self-Correction Logic, wherein the model retrains low-confidence predictions or requests clarification; Mobile-First Interface, allowing for easy usage on mobile phones through image uploads or drawing input. These aspects unite to give a robust, convenient tool for students, teachers, and researchers requiring trustworthy mathematical OCR in real-time. |
| AUTHOR | ANITA JOSHI, VYOM PHUKANE, JATIN SHENDE, HIMANSHU PAWAR, RAAGHAV KULSHRESTHA, OMKAR RASKAR, GAUREE HATKAR |
| VOLUME | 176 |
| DOI | DOI: 10.15680/IJIRCCE.2025.1311105 |
| pdf/105_Write2Math Adaptive Handwritten Math Recognition with Self-Correction and LaTeX Conversion.pdf | |
| KEYWORDS |
