Segmentation of overwritten online handwriting input

摘要

Implementations of the disclosed subject matter provide methods and systems for identifying a candidate character cut for an overwritten character. A method may include providing a handwriting input area. The handwriting input area may be divided into multiple sections and a first portion of the multiple sections may be located in an end point region. A first handwritten input comprising a first stroke that ends in a section located in the end point region may be received. A second handwritten input comprising a second stroke that begins in a section that is not located in the end point region may be received. As a result, a first candidate character cut may be identified between the first stroke and the second stroke.

主权项

1. A computer-implemented method comprising:
receiving, by a computing device, a sequence of strokes that represent a handwritten input that trace shapes of one or more handwritten characters along a handwriting input area of the computing device; determining, by the computing device, a predetermined sub-area of the handwriting input area that is characterized as a character end point sub-area; determining, by the computing device, that (i) an end point of a first stroke of the sequence of strokes occurs in the predetermined sub-area of the handwriting input area that is characterized as a character end point sub-area, and (ii) a beginning point of a second stroke of the sequence of strokes that immediately follows the first stroke occurs in a second sub-area of the handwriting input area that is not characterized as a character end point sub-area; based on determining that (i) the end point of the first stroke of the sequence of strokes occurs in the predetermined sub-area of the handwriting input area that is characterized as a character end point sub-area and (ii) the beginning point of the second stroke of the sequence of strokes that immediately follows the first stroke occurs in the second sub-area of the handwriting input area that is not characterized as a character end point sub-area, designating, by the computing device, the end point of the first stroke as a candidate end point of a first handwritten character traced by the sequence of strokes; and obtaining, by the computing device, a recognized character corresponding to the first handwritten character based at least in part on the designated candidate end point of the first handwritten character.