Face recognition with radial basis function (RBF) neural networks

By Meng Joo Er, Shiqian Wu, Juwei Lu, Hock Lye Toh. IEEE Trans. Neural Networks, 2002

729 citations recorded by the source corpus.

Subfields: Atmospheric Science, Computer Vision and Pattern Recognition, Control and Systems Engineering

View Paper: https://www.semanticscholar.org/paper/0ad90118b4c91637ee165f53d557da7141c3fde0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atmospheric Science

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

Citations in the corpus

Independent component analysis of Gabor features for face recognition (2003, background): “Popularstatisticaltechniquesplay a very importantrole in developingfacerecognitionmeth- ods[42], [4], [35], [15], [1], [10], [20].”
Recent advances in visual and infrared face recognition - a review (2005, background): “SVMs can be considered as a new paradigm to train polynomial functions, neural networks, or radial basis function classifiers [126].”
2D and 3D face recognition: A survey (2007, methodology): “At last, Meng et al. (2002) introduced a hybrid approach, in which, through the PCA, the most discriminating features are extracted and used as the input of a RBF neural network.”
A novel hybrid method of forecasting crude oil prices using complex network science and artificial intelligence algorithms (2018, background): “The radial basis function (RBF) neural network has been widely applied in the neural network community [53].”
Gabor wavelets and General Discriminant Analysis for face identification and verification (2007, neutral): “Comparison with other methods For further comparison of Gabor feature and GDA based methods with other approaches, the results on the same database for the Radial Basis Function (RBF) neural network [30] and HMM [3,31] based methods are shown in Table 1.”
Towards Deep Machine Reasoning: a Prototype-based Deep Neural Network with Decision Tree Inference (2020, methodology): “Prototype-based models have demonstrated their high efficiency, e.g. the discriminative models such as kNN [12], SVM [13], less so RBF [14] and LVQ [15].”
Surrogate-Assisted Cooperative Swarm Optimization of High-Dimensional Expensive Problems (2017, background): “It has been shown that the performance of RBF networks is relatively insensitive to the increase in the dimension of the function to be approximated [62], [63].”
Non‐intrusive reduced‐order modelling of the Navier–Stokes equations based on RBF interpolation (2015, methodology): “RBF interpolation is a method that represents a function through scattered data, and it has been applied to various research areas such as partial differential equations (PDEs) [32], coupled problem [33], mesh generation [34], facial recognition [35] and feedback control [36].”
High-speed face recognition based on discrete cosine transform and RBF neural networks (2005, methodology): “Hence, in our proposed system, the FLD is also employed in the DCT domain to extract the most discriminating features of face images.”