Feature extraction and learning using context cue and Rényi entropy based mutual information

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

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. red. / Ana Fred; Maria De Marsico; Mário Figueiredo. Springer, 2015. s. 69-88 (Lecture notes in computer science, Bind 9493).

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

Harvard

Pan, H, Olsen, SI & Zhu, Y 2015, Feature extraction and learning using context cue and Rényi entropy based mutual information. i A Fred, M De Marsico & M Figueiredo (red), Pattern recognition: applications and methods: 4th International Conference, ICPRAM 2015, Lisbon, Portugal, January 10-12, 2015, Revised Selected Papers. Springer, Lecture notes in computer science, bind 9493, s. 69-88, 4th International Conference on Pattern Recognition: Applications and Methods, Lissabon, Portugal, 10/01/2015. https://doi.org/10.1007/978-3-319-27677-9_5

APA

Pan, H., Olsen, S. I., & Zhu, Y. (2015). Feature extraction and learning using context cue and Rényi entropy based mutual information. I A. Fred, M. De Marsico, & M. Figueiredo (red.), Pattern recognition: applications and methods: 4th International Conference, ICPRAM 2015, Lisbon, Portugal, January 10-12, 2015, Revised Selected Papers (s. 69-88). Springer. Lecture notes in computer science, Bind. 9493 https://doi.org/10.1007/978-3-319-27677-9_5

Vancouver

Pan H, Olsen SI, Zhu Y. Feature extraction and learning using context cue and Rényi entropy based mutual information. I Fred A, De Marsico M, Figueiredo M, red., Pattern recognition: applications and methods: 4th International Conference, ICPRAM 2015, Lisbon, Portugal, January 10-12, 2015, Revised Selected Papers. Springer. 2015. s. 69-88. (Lecture notes in computer science, Bind 9493). https://doi.org/10.1007/978-3-319-27677-9_5

Author

Pan, Hong ; Olsen, Søren Ingvor ; Zhu, Yaping. / Feature extraction and learning using context cue and Rényi entropy based mutual information. Pattern recognition: applications and methods: 4th International Conference, ICPRAM 2015, Lisbon, Portugal, January 10-12, 2015, Revised Selected Papers. red. / Ana Fred ; Maria De Marsico ; Mário Figueiredo. Springer, 2015. s. 69-88 (Lecture notes in computer science, Bind 9493).

Bibtex

@inproceedings{ed68184227b94dfeb9b664faea53bdff,
title = "Feature extraction and learning using context cue and R{\'e}nyi entropy based mutual information",
abstract = "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 R{\'e}nyi 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 R{\'e}nyi 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 R{\'e}nyi 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.",
author = "Hong Pan and Olsen, {S{\o}ren Ingvor} and Yaping Zhu",
year = "2015",
doi = "10.1007/978-3-319-27677-9_5",
language = "English",
isbn = "978-3-319-27676-2",
series = "Lecture notes in computer science",
publisher = "Springer",
pages = "69--88",
editor = "Ana Fred and {De Marsico}, Maria and M{\'a}rio Figueiredo",
booktitle = "Pattern recognition: applications and methods",

}

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

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

ER -

ID: 154047214