Qimeng Lu

Nan Wang

Xu Yang

Xiaohong Chen

Yachen Wang

The present invention provides an offline handwriting individual recognition system and method. The method comprises: scanning the suspicious handwriting to obtain a first white light image and a first three-dimensional image, and scanning the sample handwriting to obtain a second white light image and a second three-dimensional image; pre-processing the first white light image and the second white light image to obtain a first pre-processed image and a second pre-processed image; extracting a first skeleton image and a second skeleton image from the first pre-processed image and the second pre-processed image; obtaining a first writing trajectory and a second writing trajectory according to the first skeleton image and the second skeleton image; extracting a first dynamic feature, a first three-dimensional feature, and a second dynamic feature, a second three-dimensional feature; processing to obtain a correlation coefficient, and obtaining an individual recognition result.

Offline handwriting individual recognition system and method based on three-dimensional dynamic features

The invention provides an offline handwriting individual recognition system and method based on two-dimensional dynamic features. The method comprises: obtaining a first handwriting image corresponding to suspicious handwriting and second handwriting images corresponding to a plurality of sample handwriting; pre-processing the first handwriting image and the second handwriting images to obtain a first pre-processed image and second pre-processed images; extracting a first skeleton image and second skeleton images from the first pre-processed image and the second pre-processed images; obtaining a first writing trajectory and second writing trajectories according to the first skeleton image and the second skeleton images; extracting first dynamic features and second dynamic features according to the first writing trajectory and the second writing trajectories; performing processing to obtain a correlation coefficient between the suspicious handwriting and the sample handwriting, and performing processing to obtain an individual recognition result according to the correlation coefficient.

Growing community of inventors

Shanghai, China

Qimeng Lu