Feature extraction and learning using context cue and Rényi entropy based mutual information
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
Feature extraction and learning using context cue and Rényi entropy based mutual information. / Pan, Hong; Olsen, Søren Ingvor; Zhu, Yaping.
Pattern recognition: applications and methods: 4th International Conference, ICPRAM 2015, Lisbon, Portugal, January 10-12, 2015, Revised Selected Papers. ed. / Ana Fred; Maria De Marsico; Mário Figueiredo. Springer, 2015. p. 69-88 (Lecture notes in computer science, Vol. 9493).Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Feature extraction and learning using context cue and Rényi entropy based mutual information
AU - Pan, Hong
AU - Olsen, Søren Ingvor
AU - Zhu, Yaping
N1 - Conference code: 4
PY - 2015
Y1 - 2015
N2 - Feature extraction and learning play a critical role for visual perception tasks. We focus on improving the robustness of the kernel descriptors (KDES) by embedding context cues and further learning a compact and discriminative feature codebook for feature reduction using Rényi entropy based mutual information. In particular, for feature extraction, we develop a new set of kernel descriptors−Context Kernel Descriptors (CKD), which enhance the original KDES by embedding the spatial context into the descriptors. Context cues contained in the context kernel enforce some degree of spatial consistency, thus improving the robustness of CKD. For feature learning and reduction, we propose a novel codebook learning method, based on a Rényi quadratic entropy based mutual information measure called Cauchy-Schwarz Quadratic Mutual Information (CSQMI), to learn a compact and discriminative CKD codebook. Projecting the original full-dimensional CKD onto the codebook, we reduce the dimensionality of CKD while preserving its discriminability. Moreover, the latent connection between Rényi quadratic entropy and the mapping data in kernel feature space further facilitates us to capture the geometric structure as well as the information about the underlying labels of the CKD using CSQMI. Thus the resulting codebook and reduced CKD are discriminative. We verify the effectiveness of our method on several public image benchmark datasets such as YaleB, Caltech-101 and CIFAR-10, as well as a challenging chicken feet dataset of our own. Experimental results show that our method has promising potential for visual object recognition and detection applications.
AB - Feature extraction and learning play a critical role for visual perception tasks. We focus on improving the robustness of the kernel descriptors (KDES) by embedding context cues and further learning a compact and discriminative feature codebook for feature reduction using Rényi entropy based mutual information. In particular, for feature extraction, we develop a new set of kernel descriptors−Context Kernel Descriptors (CKD), which enhance the original KDES by embedding the spatial context into the descriptors. Context cues contained in the context kernel enforce some degree of spatial consistency, thus improving the robustness of CKD. For feature learning and reduction, we propose a novel codebook learning method, based on a Rényi quadratic entropy based mutual information measure called Cauchy-Schwarz Quadratic Mutual Information (CSQMI), to learn a compact and discriminative CKD codebook. Projecting the original full-dimensional CKD onto the codebook, we reduce the dimensionality of CKD while preserving its discriminability. Moreover, the latent connection between Rényi quadratic entropy and the mapping data in kernel feature space further facilitates us to capture the geometric structure as well as the information about the underlying labels of the CKD using CSQMI. Thus the resulting codebook and reduced CKD are discriminative. We verify the effectiveness of our method on several public image benchmark datasets such as YaleB, Caltech-101 and CIFAR-10, as well as a challenging chicken feet dataset of our own. Experimental results show that our method has promising potential for visual object recognition and detection applications.
U2 - 10.1007/978-3-319-27677-9_5
DO - 10.1007/978-3-319-27677-9_5
M3 - Article in proceedings
SN - 978-3-319-27676-2
T3 - Lecture notes in computer science
SP - 69
EP - 88
BT - Pattern recognition: applications and methods
A2 - Fred, Ana
A2 - De Marsico, Maria
A2 - Figueiredo, Mário
PB - Springer
T2 - 4th International Conference on Pattern Recognition: Applications and Methods
Y2 - 10 January 2015 through 12 January 2015
ER -
ID: 154047214