Browsing Theses (MU) by Thesis Advisor "Han, Xu (Tony Xu)"
Now showing items 1-15 of 15
-
Action recognition via sequence embedding
(University of Missouri--Columbia, 2011)[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI AT REQUEST OF AUTHOR.] A comb structural exemplar embedding based approach is introduced for action recognition. We propose a new framework to represent an action as a weak ... -
Depth sensor based object detection using surface curvature
(University of Missouri--Columbia, 2014)An object detection system finds objects from an image or video sequence of the real world. The good performance of object detection has been largely driven by the development of well-established robust feature sets. By ... -
A detection based sport player tracker
(University of Missouri--Columbia, 2014)[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI AT AUTHOR'S REQUEST.] Currently, the sliding windows framework dominates the object detection task for its good performance. But the computational cost of this approach is ... -
Face recognition via sparse representation
(University of Missouri--Columbia, 2015)[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI AT REQUEST OF AUTHOR.] Sparse representation has been successfully used for face recognition. The sparse representation classifier (SRC) can solve illumination variations, ... -
Fast object detection on raw depth images
(University of Missouri--Columbia, 2015)[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI AT REQUEST OF AUTHOR.] We propose an effective object detection system which is able to localize object in real time and outperforms the state-of-the-art results on standard ... -
Geometric image segmentation via transform invariant rank cuts
(University of Missouri--Columbia, 2012)This research propose a novel image segmentation algorithm, named as Transform Invariant Rank Cuts (TIRC). Based on salient 3D geometric information of natural scenes. The segmentation algorithm unities an emerging robust ... -
How zenith angle of cross product affects NVP feature
(University of Missouri--Columbia, 2014)[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI AT AUTHOR'S REQUEST.] Recent dramatic advance in visual recognition hardware has made some promising progress. For instance, the impact of the recent emerging low-cost depth ... -
An image-classification leveraged object detector
(University of Missouri--Columbia, 2014) -
Investigation and analysis of image classification on large-scale benchmark datasets
(University of Missouri--Columbia, 2015)[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI AT REQUEST OF AUTHOR.] Image Classification nowadays, which including object recognition and scene classification, remains to be a major challenging task among computer ... -
A novel method of face verification based on EM algorithm
(University of Missouri--Columbia, 2014)In this paper, we implement a novel joint Bayesian method based on the classical Bayesian face recognition method by Baback Moghaddam et al and a creative paper "Bayesian Face Revisited: A Joint Formulation". One face is ... -
Object detection with Kinect sensor
(University of Missouri--Columbia, 2014)[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI AT AUTHOR'S REQUEST.] -
Object detection with large intra-class variation
(University of Missouri--Columbia, 2011)For object detection, the state-of-the-art performance is achieved through supervised learning. The performances of object detectors of this kind are mainly determined by two factors: features and underlying classification ... -
People re-identification in a camera network
(University of Missouri--Columbia, 2012)In this research, we present an appearance based method for people re-identification. It consists in the extraction of two types of features related to human appearance, color histograms and SIFT features. Images are ... -
People re-identification over non-overlapping camera views
(University of Missouri--Columbia, 2013)[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI AT AUTHOR'S REQUEST.] Person re-identification is a computer vision task of recognizing an individual from similar background across non-overlapping camera views. In this ... -
Robust classification with convolutional neural networks
(University of Missouri--Columbia, 2015)For image classification, I achieved the current state-of-the-art performance by using methods based on Convolutional Neural Networks (CNNs). Face image analysis requires both effective feature extraction and classifier ...