Yeunghak Lee

Fuzzy Neural Networks and Fuzzy Integral Approach to Curvature-Based Component Range Facial Recognition

The surface curvatures in the face contain the most important personal features information. In this paper, we develop a method for recognizing 3D face images by combining face component; eyes, cheek, mouth, and nose. For the proposed approach, the first step uses face curvatures which present the facial features for 3D face images, after normalization using the SVD. As a result of this process, we obtain curvature feature for each component range face. Fuzzy neural network, PCA, and Fisherface methods are then applied to each component range face. The reason for adapting PCA and Fisherface method is that the methods maintain the surface attribute for face curvature, even though they can generate reduced image dimension. In the last step, the aggregation of the individual classifiers using the fuzzy integral is explained for each component. The experimental results showed that the proposed approach has outstanding classification performance compared to other methods.

3D Facial Recognition with Soft Computing

The depth information in the face represents personal features in detail. In particular, the surface curvatures extracted from the face contain the most important personal facial information. These surface curvature and eigenface, which reduce the data dimensions with less degradation of original information, are collaborated into the proposed 3D face recognition algorithm. The principal components represent the local facial characteristics without loss of the information. Recognition for the eigenface referred from the maximum and minimum curvatures is performed. The normalized facial images are also considered to enhance the recognition rate. To classify the faces, the cascade architectures of fuzzy neural networks, which can guarantee a high recognition rate as well as parsimonious knowledge base, are considered. Experimental results on a 46 persons data set of 3D images demonstrate the effectiveness of the proposed method.

Depth range component based 3D face recognition using fuzzy methods

The face shape using depth information in the face represents personal features in detail. In particular, the surface curvatures extracted from the face contain the most important personal facial information. In this paper, we develop a method for recognizing range face images by combining the multiple-face-regions (region component based), using fuzzy integral. For the proposed approach, the first step uses face curvatures that helps extract facial features for range face images, after normalization using the SVD. As a result of this process, we obtain curvature feature for each region range face. The second step of approach concerns the application of PCA and Fisherface method to each component range face. The reason for adapted PCA and Fisherface method is these can maintain the surface attribute for face curvature, even though these can generate the reduced image dimension. In the last step, the aggregation of the individual classifiers using the fuzzy integral and the fuzzy neural network (CAFNN) are explained for each region component based. The experimental results obtained that the approach presented in this paper have outstanding classification in comparison to the results obtained by other methods.

Soft computing based range facial recognition using eigenface

The depth information in the face represents personal features in detail. In particular, the surface curvatures extracted from the face contain the most important personal facial information. These surface curvature and eigenface, which reduce the data dimensions with less degradation of original information, are collaborated into the proposed 3D face recognition algorithm. The principal components represent the local facial characteristics without loss for the information. Recognition for the eigenface referred from the maximum and minimum curvatures is performed. The normalized facial images are also considered to enhance the recognition rate. To classify the faces, the cascade architectures of fuzzy neural networks, which can guarantee a high recognition rate as well as parsimonious knowledge base, are considered. Experimental results on a 46 person data set of 3D images demonstrate the effectiveness of the proposed method.

An automated facial pose estimation using surface curvature and tetrahedral structure of a nose

This paper introduces an automated 3D face pose estimation method using the tetrahedral structure of a nose. This method is based on the feature points extracted from a face surface using curvature descriptors. A nose is the most protruding component in a 3D face image. A nose shape that is composed of the feature points such as a nasion, nose tip, nose base, and nose lobes, and is similar to a tetrahedron. Face pose can be estimated by fitting the tetrahedron to the coordinate axes. Each feature point can be localized by curvature descriptors. This method can be established using nasion, nose tip, and nose base. It can be applied to face tracking and face recognition.

Multiple Region Range Face Recognition Based on Fuzzy Integral Using Curvature Feature

The surface curvatures extracted from the face contain the most important personal facial information. In particular, the face shape using depth information in the face represents personal features in detail. In this paper, we develop a method for recognizing range face images by combining the multiple face regions, using Fisherface method, and fuzzy integral. For the proposed approach, the first step uses face curvatures that helps extract facial features for range face images, after normalization using the SVD. As a result of this process, we obtain curvature feature for each region range face. The second step of approach concerns the application of PCA and Fisherface method to each component range face. The reason for adapted PCA and Fisherface method is these can maintain the surface attribute for face curvature, even though these can generate the reduced image dimension. In the last step, the aggregation of the individual classifiers using the fuzzy integral is explained for each component. The experimental results obtain that the approach presented in this paper have outstanding classification in comparison to the results obtained by other methods.

3D facial recognition using eigenface and cascade fuzzy neural networks: normalized facial image approach

The depth information in the face represents personal features in detail. In particular, the surface curvatures extracted from the face contain the most important personal facial information. The principal component analysis using the surface curvature reduces the data dimensions with less degradation of original information, and the proposed 3D face recognition algorithm collaborated into them. The recognition for the eigenface referred from the maximum and minimum curvatures is performed. To classify the faces, the cascade architectures of fuzzy neural networks, which can guarantee a high recognition rate as well as parsimonious knowledge base, are considered. Experimental results on a 46 person data set of 3D images demonstrate the effectiveness of the proposed method.

Curvature based range face recognition analysis using projection vector by subimage

We will present a new practical implementation of a person verification system using the projection vectors based on curvatures for range face images. The combination of the four curvatures according to the curvature threshold and depth values show that proposed method achieves higher recognition rate of the cases for ranked best candidates, respectively, and combined recognition rate also.