Search For:

Displaying 1-15 out of 15 total
Mean-Value Laplacian Coordinates for Triangular Meshes
Found in: Computer Graphics, Imaging and Visualization, International Conference on
By H.Y. Wu,, Chunhong Pan, Qing Yang, Jia Pan, Songde Ma
Issue Date:July 2006
pp. 156-160
This paper presents an effective approach for triangular mesh editing, based on mean-value laplacian coordinates for triangular meshes. We discretize the Laplace operator using mean value weights instead of uniform weights for fine approximation qualities....
Active Flattening of Curved Document Images via Two Structured Beams
Found in: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Gaofeng Meng,Ying Wang,Shenquan Qu,Shiming Xiang,Chunhong Pan
Issue Date:June 2014
pp. 3890-3897
Document images captured by a digital camera often suffer from serious geometric distortions. In this paper, we propose an active method to correct geometric distortions in a camera-captured document image. Unlike many passive rectification methods that re...
Efficient Image Dehazing with Boundary Constraint and Contextual Regularization
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Gaofeng Meng,Ying Wang,Jiangyong Duan,Shiming Xiang,Chunhong Pan
Issue Date:December 2013
pp. 617-624
Images captured in foggy weather conditions often suffer from bad visibility. In this paper, we propose an efficient regularization method to remove hazes from a single input image. Our method benefits much from an exploration on the inherent boundary cons...
Nonparametric Illumination Correction for Scanned Document Images via Convex Hulls
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Gaofeng Meng, Shiming Xiang, Nanning Zheng, Chunhong Pan
Issue Date:July 2013
pp. 1730-1743
A scanned image of an opened book page often suffers from various scanning artifacts known as scanning shading and dark borders noises. These artifacts will degrade the qualities of the scanned images and cause many problems to the subsequent process of do...
Metric Rectification of Curved Document Images
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Gaofeng Meng,Chunhong Pan,Shiming Xiang,Jiangyong Duan
Issue Date:April 2012
pp. 707-722
In this paper, we propose a metric rectification method to restore an image from a single camera-captured document image. The core idea is to construct an isometric image mesh by exploiting the geometry of page surface and camera. Our method uses a general...
Partwise Cross-Parameterization via Nonregular Convex Hull Domains
Found in: IEEE Transactions on Visualization and Computer Graphics
By Huai-Yu Wu,Chunhong Pan,Hongbin Zha,Qing Yang,Songde Ma
Issue Date:October 2011
pp. 1531-1544
In this paper, we propose a novel partwise framework for cross-parameterization between 3D mesh models. Unlike most existing methods that use regular parameterization domains, our framework uses nonregular approximation domains to build the cross-parameter...
Consistent Correspondence between Arbitrary Manifold Surfaces
Found in: Computer Vision, IEEE International Conference on
By Huai-Yu Wu, Chunhong Pan, Qing Yang, Songde Ma
Issue Date:October 2007
pp. 1-8
We propose a novel framework for consistent correspondence between arbitrary manifold meshes. Different from most existing methods, our approach directly maps the connectivity of the source mesh onto the target mesh without needing to segment input meshes,...
An Iterative Bayesian Approach for Digital Matting
Found in: Pattern Recognition, International Conference on
By Hang Chang, Qing Yang, Chunhong Pan
Issue Date:August 2006
pp. 122-125
This paper proposes a new iterative approach for digital image matting. It combines pre-segmentation and matting into an unified approach and extracts good matte iteratively within a well-defined Bayesian framework based on a few user strokes on foreground...
A Semi-Supervised Framework for Mapping Data to the Intrinsic Manifold
Found in: Computer Vision, IEEE International Conference on
By Haifeng Gong, Chunhong Pan, Qing Yang, Hanqing Lu, Songde Ma
Issue Date:October 2005
pp. 98-105
This paper presents a novel scheme for manifold learning. Different from the previous work reducing data to Euclidean space which cannot handle the looped manifold well, we map the scattered data to its intrinsic parameter manifold by semi-supervised learn...
A Band-Weighted Landuse Classification Method for Multispectral Images
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Chunhong Pan, Gang Wu, Veronique Prinet, Qing Yang, Songde Ma
Issue Date:June 2005
pp. 96-102
Landuse classification is an important problem in the remote sensing field. It can be used in a wide range of applications. In this paper, we propose a hybrid method fusing edges and regions information for the landuse classification of multispectral image...
3D Motion Estimation of Human by Genetic Algorithm
Found in: Pattern Recognition, International Conference on
By Chunhong Pan, Songde Ma
Issue Date:September 2000
pp. 1159
In the paper we show that based on coplanar constraint, the motion and structure of the articulated object can be determined within a scale factor from a monocular sequence of images. By Genetic Algorithm, we achieve the unique robust numerical solution to...
Tone-aware sparse representation for face recognition
Found in: 2013 10th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2013)
By Lingfeng Wang,Huaiyu Wu,Chunhong Pan
Issue Date:April 2013
pp. 1-6
It is still a very challenging task to recognize a face in a real world scenario, since the face may be corrupted by many unknown factors. Among them, illumination variation is an important one, which will be mainly discussed in this paper. First, the illu...
Generalized Optical Flow in the Scale Space
Found in: Image and Graphics, International Conference on
By Haifeng Gong, Qing Yang, Chunhong Pan, Hanqing Lu
Issue Date:December 2004
pp. 536-539
Scale space is a natural way to handle multi-scale problem. Yang and Ma considered the correspondence between scales, and proposed optical flow in the scale space. In this paper, we generalized Yang and Ma's work to generic images. We first genralize the H...
Parametric Tracking of Human Contour by Exploiting Intelligent Edge
Found in: Automatic Face and Gesture Recognition, IEEE International Conference on
By Chunhong Pan, Songde Ma
Issue Date:May 2004
pp. 663
In this paper, we adapt the idea of Intelligent Scissors for contour tracking in dynamic image sequence. Tracking contour of human can therefore be converted to tracking seed points in images by making use of the properties of the optimal path (Intelligent...
Guided tone mapping
Found in: ACM SIGGRAPH 2012 Posters (SIGGRAPH '12)
By Chunhong Pan, Gaofeng Meng, Huxiang Gu, Shiming Xiang, Ying Wang
Issue Date:August 2012
pp. 1-1
In this paper, we propose a simple but effective tone mapping operator, which can achieve impressive results with low complexity in both the formulation and computation. The key point of our operator is to calculate a scalar matrix by which the input HDR i...