Animation character recognition and character intelligence analysis basedon semantic ontology and Poisson equation

• Autores: Zhirui Wang
• Localización: Applied Mathematics and Nonlinear Sciences, ISSN-e 2444-8656, Vol. 8, Nº. 1, 2023, págs. 1487-1498
• Idioma: inglés
• Enlaces
  • Texto completo
• Resumen

  • In order to make a deeper research on the existing animation character recognition technology andimprove the existing role intelligent analysis technology, semantic ontology and Poisson equationarecombined to apply to the animation character recognition and role intelligent analysis technology. For thethree-dimensional model, the mapping relationship between semantic tags and local geometric features is extracted to form an intelligent recognition ontology. In the recognition process, support vector machine(SVM) and local geometric features are used to identify semantic tags, and the recognition analysis is carried out according to the semantic tag driving level. Ensure the consistency of animation character model recognition level. In view of the equal perimeter of the recognition boundary under attitude change, the isoline is defined by Poisson equation. This optimization method makes the recognition boundarysmooth and consistent under the change of attitude. In the experimental part, various animation character models under different postures are verified and analyzed, and the consistent hierarchical recognitioneffect is obtained. Compared with the existing methods, the proposed recognition ontology can solve theproblem of adaptive selection of optimization parameters of different models and improve the recognitionquality