Handwritten numeral recognition method based on feature dimension reduction

Abstract

The invention relates to the technical field of image recognition, in particular to a handwritten numeral recognition method based on feature dimension reduction, which comprises the following steps:obtaining a handwritten numeral image for recognition, and obtaining a preprocessed handwritten numeral image after image preprocessing; extracting handwritten numeral features in the preprocessed handwritten numeral image through feature extraction processing; through feature dimension reduction processing, reducing the feature dimension of the handwritten numeral features, and obtaining low-dimension handwritten numeral features; and performing feature recognition processing on the low-dimensional handwritten numeral features to obtain a handwritten numeral recognition result. According to the handwritten numeral recognition method based on feature dimension reduction, feature dimension reduction processing can be carried out on handwritten numeral features so as to reduce the difficultyand complexity of feature recognition, and therefore the recognition effect and efficiency of handwritten numerals can be improved.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a method for recognizing handwritten digits based on feature dimensionality reduction. Background technique [0002] Handwritten digit recognition is an important link in the field of pattern recognition. It has important applications in optical character recognition, postal mail classification, bank check processing, form data entry, etc. Using computers to recognize handwritten digits, due to the different writing styles of different people different, making it more difficult for computers to recognize handwritten digits than printed ones. [0003] With the rapid development of the information society, all kinds of data are growing explosively. Manually entering all kinds of data has gradually failed to keep up with the speed of data generation. Therefore, using computers to automatically identify and enter various data has become As long as a classifier with high re...

AI Technical Summary

Problems solved by technology

The image feature extraction in this scheme is the extraction of the structural features of the digital skeleton, which has the problem of too many feature dimensions when extracting the handwritten digital features (structural features of the digital skeleton), that is, the image features contain noise and other unimportant These redundant features will form redundant variables in the process of feature recognition and calculation, which will increase the difficulty and complexity of feature recognition, making the efficiency of handwritten digit recognition very low and the effect is not good

Images