Object classification and detection with context kernel descriptors

TY - GEN

T1 - Object classification and detection with context kernel descriptors

AU - Pan, Hong

AU - Olsen, Søren Ingvor

AU - Zhu, Yaping

N1 - Conference code: 19

PY - 2014

Y1 - 2014

N2 - Context information is important in object representation. By embedding context cue of image attributes into kernel descriptors, we propose a set of novel kernel descriptors called Context Kernel Descriptors (CKD) for object classification and detection. The motivation of CKD is to use spatial consistency of image attributes or features defined within a neighboring region to improve the robustness of descriptor matching in kernel space. For feature selection, Kernel Entropy Component Analysis (KECA) is exploited to learn a subset of discriminative CKD. Different from Kernel Principal Component Analysis (KPCA) that only keeps features contributing mostly to image reconstruction, KECA selects the CKD that contribute mostly to the Rényi entropy of the image. These CKD are discriminative as they relate to the density distribution of the histogram of image attributes. We report superior performance of CKD for object classification on the CIFAR-10 dataset, and for detection on a challenging chicken feet dataset.

AB - Context information is important in object representation. By embedding context cue of image attributes into kernel descriptors, we propose a set of novel kernel descriptors called Context Kernel Descriptors (CKD) for object classification and detection. The motivation of CKD is to use spatial consistency of image attributes or features defined within a neighboring region to improve the robustness of descriptor matching in kernel space. For feature selection, Kernel Entropy Component Analysis (KECA) is exploited to learn a subset of discriminative CKD. Different from Kernel Principal Component Analysis (KPCA) that only keeps features contributing mostly to image reconstruction, KECA selects the CKD that contribute mostly to the Rényi entropy of the image. These CKD are discriminative as they relate to the density distribution of the histogram of image attributes. We report superior performance of CKD for object classification on the CIFAR-10 dataset, and for detection on a challenging chicken feet dataset.

KW - Faculty of Science

KW - Object classification and detection, Feature selection, Kernel descriptors, Kernel entropy component analysis

U2 - 10.1007/978-3-319-12568-8_100

DO - 10.1007/978-3-319-12568-8_100

M3 - Article in proceedings

SN - 978-3-319-12567-1

T3 - Lecture notes in computer science

SP - 827

EP - 835

BT - Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications

A2 - Bayro-Corrochano, Eduardo

A2 - Hancock, Edwin

T2 - Iberoamerican Congress 2014

Y2 - 2 November 2014 through 5 November 2014

ER -