Recognition of Handwritten Words from Digital Writing Pad Using MMU-SNet

In this paper, Modified Multi-scale Segmentation Network (MMU-SNet) method is proposed for Tamil text recognition. Handwritten texts from digital writing pad notes are used words recognition written through file conversion challenging due to stylus pressure, on glass frictionless surfaces, and being less skilled in short writing, alphabet size, style, carved symbols, orientation angle variations. Stylus pressure the changes language because alphabets have a smaller number of lines, angles, curves, bends. The small change dots, bends leads error meaning wrong conversion. However, handwritten English word files performed various algorithms such as Support Vector Machine (SVM), Kohonen Neural (KNN), Convolutional (CNN) offline online compared with above MMU-SNet has achieved good accuracy predicting text, about 96.8% other traditional CNN algorithms.