TY - GEN

T1 - Discriminative kernel feature extraction and learning for object recognition and detection

AU - Pan, Hong

AU - Olsen, Søren Ingvor

AU - Zhu, Yaping

N1 - Conference code: 4

PY - 2015

Y1 - 2015

N2 - Feature extraction and learning is critical for object recognition and detection. By embedding context cue of image attributes into the kernel descriptors, we propose a set of novel kernel descriptors called context kernel descriptors (CKD). The motivation of CKD is to use the spatial consistency of image attributes or features defined within a neighboring region to improve the robustness of descriptor matching in kernel space. For feature learning, we develop a novel codebook learning method, based on the Cauchy-Schwarz Quadratic Mutual Information (CSQMI) measure, to learn a compact and discriminative CKD codebook from a rich and redundant CKD dictionary. Projecting the original full-dimensional CKD onto the codebook, we reduce the dimensionality of CKD without losing its discriminability. CSQMI derived from Rényi quadratic entropy can be efficiently estimated using a Parzen window estimator even in high-dimensional space. In addition, 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 report superior performance of our algorithm for object recognition on benchmark datasets like Caltech-101 and CIFAR-10, as well as for detection on a challenging chicken feet dataset.

AB - Feature extraction and learning is critical for object recognition and detection. By embedding context cue of image attributes into the kernel descriptors, we propose a set of novel kernel descriptors called context kernel descriptors (CKD). The motivation of CKD is to use the spatial consistency of image attributes or features defined within a neighboring region to improve the robustness of descriptor matching in kernel space. For feature learning, we develop a novel codebook learning method, based on the Cauchy-Schwarz Quadratic Mutual Information (CSQMI) measure, to learn a compact and discriminative CKD codebook from a rich and redundant CKD dictionary. Projecting the original full-dimensional CKD onto the codebook, we reduce the dimensionality of CKD without losing its discriminability. CSQMI derived from Rényi quadratic entropy can be efficiently estimated using a Parzen window estimator even in high-dimensional space. In addition, 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 report superior performance of our algorithm for object recognition on benchmark datasets like Caltech-101 and CIFAR-10, as well as for detection on a challenging chicken feet dataset.

KW - Faculty of Science

KW - Context kernel descriptors, Cauchy-Schwarz Quadratic Mutual Information, Feature extraction and learning, Object recognition and detection

U2 - 10.5220/0005212900990109

DO - 10.5220/0005212900990109

M3 - Article in proceedings

VL - 1

SP - 99

EP - 109

BT - Proceedings of the International Conference on Pattern Recognition Applications and Methods

A2 - De Marsico, Maria

A2 - Figueiredo, Mário

A2 - Fred, Ana

PB - SCITEPRESS Digital Library

T2 - 4th International Conference on Pattern Recognition: Applications and Methods

Y2 - 10 January 2015 through 12 January 2015

ER -