Geometrical probability covering algorithm

Authors:
Junping Zhang;Stan Z. Li;Jue Wang
Affiliations:
Shanghai Key Laboratory of Intelligent Information Processing, Department of Computer Science and Engineering, Fudan University, Shanghai, China;National Laboratory of Pattern Recognition & Center for Biometrics and Security Research, Institute of Automation, Chinese Academy of Sciences, Beijing, China;The Key Laboratory of Complex Systems and Intelligence Science, Institute of Automation, Chinese Academy of Sciences, Beijing, China
Venue:
FSKD'05 Proceedings of the Second international conference on Fuzzy Systems and Knowledge Discovery - Volume Part I
Year:
2005

Citing 7
Cited 0

Using Discriminant Eigenfeatures for Image Retrieval

IEEE Transactions on Pattern Analysis and Machine Intelligence
Automatic Classification of Single Facial Images

IEEE Transactions on Pattern Analysis and Machine Intelligence
Performance Evaluation of the Nearest Feature Line Method in Image Classification and Retrieval

IEEE Transactions on Pattern Analysis and Machine Intelligence
Pattern Classification (2nd Edition)

Pattern Classification (2nd Edition)
Eigenfaces for recognition

Journal of Cognitive Neuroscience
Nearest manifold approach for face recognition

FGR' 04 Proceedings of the Sixth IEEE international conference on Automatic face and gesture recognition
Unified locally linear embedding and linear discriminant analysis algorithm (ULLELDA) for face recognition

SINOBIOMETRICS'04 Proceedings of the 5th Chinese conference on Advances in Biometric Person Authentication

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we propose a novel classification algorithm, called geometrical probability covering (GPC) algorithm, to improve classification ability. On the basis of geometrical properties of data, the proposed algorithm first forms extended prototypes through computing means of any two prototypes in the same class. Then Gaussian kernel is employed for covering the geometrical structure of data and used as a local probability measurement. By computing the sum of the probabilities that a new sample to be classified to the set of prototypes and extended prototypes, the classified criterion based on the global probability measurement is achieved. The proposed GPC algorithm is simple but powerful, especially, when training samples are sparse and small size. Experiments on several databases show that the proposed algorithm is promising. Also, we explore other potential applications such as outlier removal with the proposed GPC algorithm.