C
Chang-Tsun Li
Researcher at Deakin University
Publications - 242
Citations - 4708
Chang-Tsun Li is an academic researcher from Deakin University. The author has contributed to research in topics: Digital watermarking & Watermark. The author has an hindex of 32, co-authored 235 publications receiving 4053 citations. Previous affiliations of Chang-Tsun Li include National Defense University & Charles Sturt University.
Papers
More filters
Journal ArticleDOI
Source Camera Identification Using Enhanced Sensor Pattern Noise
TL;DR: This work proposes a novel approach for attenuating the influence of details from scenes on SPNs so as to improve the device identification rate of the identifier.
Journal ArticleDOI
Trademark image retrieval using synthetic features for describing global shape and interior structure
TL;DR: A trademark image retrieval (TIR) system to deal with the vast number of trademark images in the trademark registration system is proposed and a two-component feature matching strategy is used to measure the similarity between the query and database images.
Journal ArticleDOI
Weighted Level Set Evolution Based on Local Edge Features for Medical Image Segmentation
TL;DR: Evaluation results show that the proposed method leads to more accurate boundary detection results than the state-of-the-art edge-based level set segmentation methods, particularly around weak edges.
Journal ArticleDOI
On Reducing the Effect of Covariate Factors in Gait Recognition: A Classifier Ensemble Method
Yu Guan,Chang-Tsun Li,Fabio Roli +2 more
TL;DR: This paper proposes a classifier ensemble method based on the random subspace Method (RSM) and majority voting (MV) that is insensitive to locations of corrupted features, and thus can generalize well to a large number of covariates.
Journal ArticleDOI
Video Anomaly Detection With Compact Feature Sets for Online Performance
TL;DR: An online framework for video anomaly detection that uses a compact set of highly descriptive features extracted from a novel cell structure that helps to define support regions in a coarse-to-fine fashion and attains a very competitive detection performance compared with state-of-the-art non-online methods.