Xu Liu

Dataset: Microsoft Research Asia salient object database (1000 images). [download]

Saliency Detection is one of the extraordinary capabilities of human visual system (HSV). We have proved a novel model for image saliency detection. A rough-to-fine strategy is carried out based on quaternion discrete cosine transformand (QDCT ) and Bayes theorem. (paper)

• Dataset: Mitosis Detection in Breast Cancer Histological Images for ICPR 2012 [download]

  To diagnose breast cancer (BCa), the number of mitotic cells present in tissue sections is an important parameter to examine and grade breast biopsy specimen.This work aims at improving the accuracy of mitosis classification by characterizing objects of interest (tissue cells) in wavelet based multi-resolution representations.A dual-tree complex wavelet transform (DT-CWT) is performed to decompose the image patches into multi-scale forms and five commonly-used statistical features are extracted from subband seperately. (paper)

PUBLICATIONS

• Tao Wan #, Xu Liu #, Jianhui Chen, Zengchang Qin, Wavelet-based statistical features for distinguishing mitotic and non-mitotic cells in breast cancer histopathology, ICIP 2014.

( # These two authors contributed equally to this paper. )

• Xu Liu, Zengchang Qin, Xiaofan Zhang and Tao Wan, Color saliency model based on mean shift segmentation, ICASSP 2013, pp. 2104-2108