一种基于类别约束的变分自编码器的书法评价方法及系统
By using a category-constrained variational autoencoder, the problem of comprehensively evaluating the artistic value and technical precision of Chinese characters in the automated evaluation of calligraphy art is solved. It realizes end-to-end intelligent learning to discover the inherent connections from image and text data, thereby improving the accuracy and reliability of the evaluation.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- JIANGNAN UNIV
- Filing Date
- 2024-07-16
- Publication Date
- 2026-07-17
AI Technical Summary
Existing automated evaluation methods for calligraphy art are insufficient to comprehensively assess the artistic value and technical precision of Chinese characters. They have high image quality requirements and struggle to gain a deep understanding of the artistry, technical details, and overall harmony of a work.
A category-constrained variational autoencoder is employed to generate latent variable representations of Chinese character images and corresponding evaluation texts through feature extraction and compression of images and texts. The consistency constraints and semantic associations between images and texts are constructed using category offsets and bidirectional long short-term memory network decoders. The different levels of Chinese character writing quality are reflected by adjusting the mean of the latent variables, and the KL divergence between the posterior and prior distributions is used to constrain the latent variables to generate evaluations.
It significantly improves the accuracy and reliability of the model in Chinese character writing evaluation, ensuring the professionalism and authority of the evaluation results. It can independently discover and construct intrinsic connections from image and text data, achieving end-to-end intelligent learning.
Smart Images
Figure CN119152352B_ABST