Laplace gradient based Discriminative and Contrast Invertible descriptor

Zhenwei Miao; Kim-Hui Yap; Xudong Jiang; Subbhuraam Sinduja; Zhenhua Wang

ICASSP 2017accepted0 citations

Laplace gradient based Discriminative and Contrast Invertible descriptor

Zhenwei Miao, Kim-Hui Yap, Xudong Jiang, Subbhuraam Sinduja, Zhenhua Wang

Abstract

The performance of local descriptors such as SIFT drops under severe illumination changes. In this paper, we propose a Discriminative and Contrast Invertible (DCI) local feature descriptor. In order to increase the discriminative ability of the descriptor under illumination changes, a Laplace gradient based histogram is proposed. Moreover, a robust contrast flipping estimate is proposed based on the divergence of a local region. Experiments on fine-grained object recognition and retrieval applications demonstrate the superior performance of the DCI descriptor to others.

BibTeX

@inproceedings{icassp2017_laplacegradientb,
  title = {Laplace gradient based Discriminative and Contrast Invertible descriptor},
  author = {Zhenwei Miao and Kim-Hui Yap and Xudong Jiang and Subbhuraam Sinduja and Zhenhua Wang},
  booktitle = {ICASSP 2017},
  year = {2017}
}