ViT and convolutional neural network fused calligraphy body type rapid identification method

Abstract

The invention discloses a ViT and convolutional neural network fused calligraphy body type rapid identification method. The method comprises the steps of 1, preprocessing various types of calligraphy body image data obtained from a calligraphy font library; 2, adjusting the brightness and the contrast saturation of the calligraphy character body image data; 3, adjusting the calligraphy character body images in the data set to be in the same resolution format; step 4, sending the adjusted calligraphy body image and the annotation data into a CNN, and extracting local feature information of the font; 5, sending the adjusted calligraphy body image and the annotation data into ViT, and extracting the structural feature information of the font; 6, combining the local feature information and the structural feature information of the fonts, and sending the combined information into a classification model for training; according to the method, good recognition precision is achieved, the speed and convenience of calligraphy font recognition are greatly improved, and technical guarantee is provided for development and application of intelligent equipment.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to a method for quickly identifying brush font types by integrating vision (Vision Transformer, ViT) and convolutional neural network (Convolutional Neural Networks, CNN). Background technique [0002] Brush calligraphy is a traditional artistic expression of Chinese characters. There are five types of calligraphy, which are seal script, official script, regular script, cursive script and running script. Each font has its own unique writing style. Seal script is a pictographic font, which is characterized by flexible and lifelike brushstrokes. The clerical script has distinct dots and paintings, horizontal and vertical, and pays attention to "the head of the silkworm and the tail of the wild goose" and "the twists and turns". Regular script is square in shape and straight in strokes, paying attention to "fullness and vigor" and "strong body". Cursive script is di...

AI Technical Summary

Problems solved by technology

Because beginners do not understand the difference between fonts, they often have problems with irregular writing

Although ordinary deep learning methods can obtain more feature information of font images, they ignore the subtle features of font radicals and stroke order, which have an important impact on the judgment of brush font types

Images