![Loading...](https://link.springer.com/static/c4a417b97a76cc2980e3c25e2271af3129e08bbe/images/pdf-preview/spacer.gif)
-
Chapter and Conference Paper
Segmentation of Brain Tumors in Multi-parametric MR Images via Robust Statistic Information Propagation
A method is presented to segment brain tumors in multi-parametric MR images via robustly propagating reliable statistical tumor information which is extracted from training tumor images using a support vector ...
-
Chapter and Conference Paper
Context-Based Support Vector Machines for Interconnected Image Annotation
We introduce in this paper a novel image annotation approach based on support vector machines (SVMs) and a new class of kernels referred to as context-dependent. The method goes beyond the naive use of the int...
-
Chapter and Conference Paper
Edge-preserving smoothing by convex minimization
This work presents a new approach for analyzing the problem of edge-preserving image smoothing using convex minimization and for selecting smoothing parameters. The close-form (global) solution is derived as t...
-
Chapter and Conference Paper
Shape recovery from one image under multiple light sources
In this paper, we propose a rectangular light source model and a novel method for recovering surface shape from one image under multiple planar light sources using shape-from-shading(SFS). This method can be e...
-
Chapter and Conference Paper
Model-based active object recognition using MRF matching and sensor planning
This paper presents an active object recognition algorithm using MAP-MRF matching and sensor planning strategy. The matching between the sensed and model object is based on surface properties. A new measure of...
-
Chapter and Conference Paper
Spherical and cylindrical light source models for shape recovery
Parallel rays of light coming from the same direction is the basic assumption for the lighting condition of the conventional shape from shading(SFS) methods. This is at best approximately true in controlled en...
-
Chapter and Conference Paper
A morphological method for moving object segmentation and posture recognition
Based on a parallel application dealing with the segmentation and posture recognition of 2-D figure moving over a relatively stationary background from a monocular video frame flow, this paper presents a gener...
-
Chapter and Conference Paper
Dynamic calibration of an active vision system to compute the ground plane transformation
Calibration is fundamental, but difficult problem in computer vision. It is even difficult to calibrate an active vision system where the head geometry and/or camera intrinsic parameters change. Conventionally...