发明名称 |
Methods and systems for efficient handwritten character segmentation |
摘要 |
A system and method for determining handwritten character segmentation shape parameters for a user in automated handwriting recognition by prompting the user for a training sample; obtaining an image that includes handwritten text that corresponds to the training sample; sweeping the image with shapes corresponding to parameters to determine coordinates of the shapes in the image; segmenting the image into segmented characters based on the coordinates of the shapes; determining character segmentation accuracies of the parameters; and storing an association between the user and the parameters. The system and method can further include receiving a writing sample from the same user and utilizing the stored parameters to segment characters in the writing sample for use in automated handwriting recognition of the writing sample. |
申请公布号 |
US9152876(B1) |
申请公布日期 |
2015.10.06 |
申请号 |
US201414218184 |
申请日期 |
2014.03.18 |
申请人 |
XEROX CORPORATION |
发明人 |
Gross Eric M.;Hamby Eric S.;Simmons Isaiah |
分类号 |
G06K9/34;G06K9/03;G06K9/00 |
主分类号 |
G06K9/34 |
代理机构 |
MH2 Technology Law Group LLP |
代理人 |
MH2 Technology Law Group LLP |
主权项 |
1. A method comprising:
displaying a set of characters; obtaining an image comprising handwritten text of a user, wherein the handwritten text corresponds to the set of characters; determining a coordinate of a first shape within the image by sweeping the image with the first shape, wherein the first shape corresponds to a first parameter; segmenting the image into a segmented character based at least on the coordinate of the first shape; determining a character segmentation accuracy of the first parameter by comparing the segmented character with the set of characters; and storing, based on the character segmentation accuracy of the first parameter, an association between the user and the first parameter. |
地址 |
Norwalk CT US |