当前位置:
X-MOL 学术
›
Pattern Recognit. Image Anal.
›
论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Invariant Gaussian–Hermite Moments Based Neural Networks for 3D Object Classification
Pattern Recognition and Image Analysis Pub Date : 2020-03-31 , DOI: 10.1134/s1054661820010186 Amal Zouhri , Hicham Amakdouf , Mostafa El Mallahi , Ahmed Tahiri , Zakia Lakhliai , Driss Chenouni , Hassan Qjidaa
中文翻译:
基于不变高斯-赫姆特矩的神经网络用于3D对象分类
更新日期:2020-03-31
Pattern Recognition and Image Analysis Pub Date : 2020-03-31 , DOI: 10.1134/s1054661820010186 Amal Zouhri , Hicham Amakdouf , Mostafa El Mallahi , Ahmed Tahiri , Zakia Lakhliai , Driss Chenouni , Hassan Qjidaa
Abstract
In this article, we suggest a new approach for classification and Recognition of 3D image Gaussian–Hermite moments using a Multilayer Perceptron architecture. The Multilayer Perceptron is an artificial neural network to evaluate the efficient structure in the non-linear systems. However, the determination of its architecture and weights is a fundamental issue due to their direct impact on the network convergence and performance. The robustness of the proposed approach have provided under many transforms. The experimental results show that our approaches are more robust than 3D Geometric moments.中文翻译:
基于不变高斯-赫姆特矩的神经网络用于3D对象分类