How to achieve high-quality conversion between English paper documents and electronic documents has become an urgent problem to be solved. If there are serious deviations, noise and other factors at this stage, it will definitely affect the later work efficiency. In view of this, based on the vector set model EMD algorithm, this article builds an artificial intelligence English recognition model under the guidance of machine learning ideas, uses the discrete curvature of the curve to extract extreme points, and controls the scale of each feature by imposing feature scale restrictions on the extreme points. Moreover, in order to calculate the extreme value envelope of the surface, this paper uses the tensor product B-spline to fit the extreme points and perform plane parameterization on the grid. In addition, in order to reduce the error of fitting the curved surface, this paper adopts the parameterization method of free boundary. Finally, this paper designs a control experiment to verify the performance of the model. The research results show that the model constructed in this paper has a certain effect.

如何实现英文纸质文档与电子文档的高质量转换成为亟待解决的问题。如果这个阶段出现严重的偏差、噪音等因素，肯定会影响到后期的工作效率。鉴于此，本文基于向量集模型EMD算法，在机器学习思想的指导下构建人工智能英语识别模型，利用曲线的离散曲率提取极值点，控制每个特征的尺度通过对极值点施加特征尺度限制。此外，为了计算表面的极值包络，本文使用张量积B-spline拟合极值点并在网格上进行平面参数化。此外，为减小曲面拟合误差，本文采用自由边界参数化方法。最后，本文设计了一个控制实验来验证模型的性能。研究结果表明，本文构建的模型具有一定的效果。