Object classification and detection with context kernel descriptors

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

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.
TitelProgress in Pattern Recognition, Image Analysis, Computer Vision, and Applications : 19th Iberoamerican Congress, CIARP 2014, Puerto Vallarta, Mexico, November 2-5, 2014. Proceedings
RedaktørerEduardo Bayro-Corrochano, Edwin Hancock
Antal sider9
ISBN (Trykt)978-3-319-12567-1
StatusUdgivet - 2014
BegivenhedIberoamerican Congress 2014 - Puerto Vallarta, Mexico
Varighed: 2 nov. 20145 nov. 2014
Konferencens nummer: 19


KonferenceIberoamerican Congress 2014
ByPuerto Vallarta
NavnLecture notes in computer science

ID: 127191961