• Sagar Shinde
• Lalit Kumar Wadhwa

The recognition of handwritten symbols, numbers, and mathematical expressions is a challenging and inspiring mission due to the varying styles of writing used in documents. It requires a combination of skills and knowledge to perform well. Although there are numerous methods available in the field, none of them can meet the requirements of accuracy, throughput and efficiencies in the recognition of complex equations. The database generated from various writers' strokes, styles, overwriting, and statistical features have been analyzed. A neural network classifier was then used to perform the recognition. The goal of this work is to provide an automatic solution for the recognition of math symbols, numbers, and expressions in various documents such as educational applications, stationery, and postal documents. The system's success rate can be determined by its efficiency, throughput, and identification rate. Keywords – math recognition, back propagation neural network (BPNN), Gradient descent, performance

Soft Computing Approach For Recognition of Handwritten Math equations.

"Soft Computing Approach For Recognition of Handwritten Math equations.", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.1-8, June-2019, Available :http://www.jetir.org/papers/JETIR1907W01.pdf

"Soft Computing Approach For Recognition of Handwritten Math equations.", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp1-8, June-2019, Available at : http://www.jetir.org/papers/JETIR1907W01.pdf