Handwritten digit recognition method and device and computer storage medium

The invention discloses a handwritten digit recognition method, which comprises the following steps: normalizing a collected sample to obtain training data, the training data comprising label data and label-free data; calculating an intra-class divergence matrix and an inter-class divergence matrix...

Full description

Saved in:
Bibliographic Details
Main Authors ZHONG SHAN, XUE YANGTAO, GONG SHENGRONG, SI YALI, BAI WENTAO
Format Patent
LanguageChinese
English
Published 08.03.2024
Subjects
Online AccessGet full text

Cover

Loading…
More Information
Summary:The invention discloses a handwritten digit recognition method, which comprises the following steps: normalizing a collected sample to obtain training data, the training data comprising label data and label-free data; calculating an intra-class divergence matrix and an inter-class divergence matrix according to the label data; constructing a neighbor graph according to the label data and the label-free data to calculate a manifold regular term; training data is utilized to learn through a Laplacian adaptive weight discriminant analysis method to obtain an optimal projection matrix, an iterative optimization method is adopted to solve an optimization problem to obtain the optimal projection matrix, normalization processing is performed on a to-be-identified sample, projected data is obtained through the optimal projection matrix, and the to-be-identified sample is identified. And a nearest neighbor classifier is adopted to obtain an identification tag. The invention further discloses a device based on the meth
Bibliography:Application Number: CN202410130100