Compressed Sensing Ensemble Classifier for Human Detection
Author(s)
Zhang, Baochang
Liu, Juan
Gao, Yongsheng
Liu, Jianzhuang
Griffith University Author(s)
Year published
2013
Metadata
Show full item recordAbstract
This paper proposes a novel Compressed Sensing Ensemble Classifier (CSEC) for human detection. The proposed CSEC employs the compressed sensing technique to get a more sparse model with a more reasonable selection of base classifiers. The major contributions of this paper are: 1) a novel principled framework for ensemble classifier design based on compressed sensing; 2) a new concept of considering both the simplicity of ensemble classifier and irrelevance of base classifiers towards optimal classifier design; and 3) a quadratic function for CSEC optimization which includes a new optimizable positive semi-definite relevance ...
View more >This paper proposes a novel Compressed Sensing Ensemble Classifier (CSEC) for human detection. The proposed CSEC employs the compressed sensing technique to get a more sparse model with a more reasonable selection of base classifiers. The major contributions of this paper are: 1) a novel principled framework for ensemble classifier design based on compressed sensing; 2) a new concept of considering both the simplicity of ensemble classifier and irrelevance of base classifiers towards optimal classifier design; and 3) a quadratic function for CSEC optimization which includes a new optimizable positive semi-definite relevance matrix to simultaneously select appropriate base classifiers with minimized relevance. Experimental results on INRIA and SDL databases show that the performance of CSEC is better than two most popular classifiers SVM and AdaBoost, as well as a most recent method CLML.
View less >
View more >This paper proposes a novel Compressed Sensing Ensemble Classifier (CSEC) for human detection. The proposed CSEC employs the compressed sensing technique to get a more sparse model with a more reasonable selection of base classifiers. The major contributions of this paper are: 1) a novel principled framework for ensemble classifier design based on compressed sensing; 2) a new concept of considering both the simplicity of ensemble classifier and irrelevance of base classifiers towards optimal classifier design; and 3) a quadratic function for CSEC optimization which includes a new optimizable positive semi-definite relevance matrix to simultaneously select appropriate base classifiers with minimized relevance. Experimental results on INRIA and SDL databases show that the performance of CSEC is better than two most popular classifiers SVM and AdaBoost, as well as a most recent method CLML.
View less >
Book Title
Intelligence Science and Big Data Engineering: Lecture Notes in Computer Science
Volume
8261
Publisher URI
Subject
Artificial Intelligence and Image Processing not elsewhere classified