A Handwritten Text Recognition System And Method

Systems and methods are described for recognition of handwritten text. According to an embodiment the handwritten text recognition system can include: an input device to receive a sample of handwritten content as input; a memory device coupled with the one or more processors, the memory device storing a set of instructions executable by the one or more processors to: extract one or more visual features from the received sample of handwritten content to determine one or more characters of a language by comparing at least a part of the extracted one or more visual features with a first dataset comprising a set of visual features for the one or more characters of the language; determine one or more letters of the language by comparing at least a part of the determined one or more characters with a second dataset comprising one or more characters pertaining to the one or more letters of the language; and predict, for the determined one or more letters, a following combination of one or more letters and one or more characters based on a third dataset comprising historical occurrence of a corresponding combination of one or more letters and one or more characters following the determined one or more letters.

Inventors

Harjeet Singh, R K Sharma

Patent File Number - 201911022745        Patent File Date - 07/06/2019