Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{167488,
        author = {Girish S. Katkar and Pooja C.Ukey and Ajay S.Ramteke},
        title = {Handwritten Mathematical Symbol Recognition using Convolutional Neural Network},
        journal = {International Journal of Innovative Research in Technology},
        year = {2024},
        volume = {11},
        number = {3},
        pages = {1096-1099},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=167488},
        abstract = {In our day-to-day life handwritten symbols are seen everywhere. We do involve automating data entry, letters, from writing cheques to writing notes manually. Symbol recognition is a process of detecting and recognizing symbols from input images and converting them into machine editable form. The technique by which a computer system can recognize symbols and other text written by hand is called a handwriting recognition system. Handwritten mathematical symbol recognition used widely for performing automating data entry, and processing handwritten applications. It is challenging for a computerized system to carry out certain types of tasks is not easy. Handwritten style of an individual person is different and varies from time to time. While understanding handwritten symbols, there are many challenges which we have to deal with. The degradation of a document or image over time can impair the ability to accurately interpret the symbols. However, we can find a solution for this using deep learning. This paper presents a model that accurately interprets handwritten characters using a dataset employed to train the model. The primary aim of this paper is to establish effective and dependable methods for recognizing handwritten symbols, and the accuracy of handwritten symbol recognition using a sequential model is 99%.},
        keywords = {Deep learning, Feature Extraction, Handwritten Mathematical Symbol recognition, Neural Networks.},
        month = {August},
        }