Automatic parameters selection is an important issue to make support vector machines (SVMs) practically useful. Most existing approaches use Newton method directly to compute the optimal parameters. They treat paramet...
详细信息
Multi-spectral imaging for the analysis and preservation of ancient documents has gained high attention in recent years. While readability enhancement is based on the multi-spectral image corpus, foreground-background...
详细信息
ISBN:
(纸本)9781605587738
Multi-spectral imaging for the analysis and preservation of ancient documents has gained high attention in recent years. While readability enhancement is based on the multi-spectral image corpus, foreground-background separation still relies mainly on gray level or color images. In this paper we propose a foreground-background separation algorithm designed for multi-spectral images. The main contribution is the simultaneously utilization of spectral and spatial features. While spectral features incorporate the spectral components of the multi-spectral images, the spatial features are based on stroke properties. Higher order Markov Random Fields enables an efficient way to combine both features. To solve higher order energy functions, we introduce a new message update rule in the well known belief propagation algorithm based on a higher order potential function. Copyright 2010 ACM.
A concept relating story-board description of video sequences with spatio-temporal hierarchies build by local contraction processes of spatio-temporal relations is presented. Object trajectories are curves in which th...
详细信息
Two segmentation methods based on the minimum spanning tree principle are evaluated with respect to each other. The hierarchical minimum spanning tree method is also evaluated with respect to human segmentations. Disc...
详细信息
This paper proposes a drawing tool recognition method based on features calculated from the shape of stroke endings. The application for this method is to help art historians to identify the drawing tool used for a dr...
Motivated by claims to 'bridge the representational gap between image and model features' and by the growing importance of topological properties we discuss several extensions to dual graph pyramids: structura...
详细信息
Although scene classification has been studied for decades, indoor scene recognition remains challenging due to its large view point variance and massive irregular artefacts. In fact, most existing methods for outdoor...
详细信息
In this paper, we present a novel viewpoint of treating conks-based calibration as the algebraic and geometric constraints. From this viewpoint, we use four intersection points correspondence to conduct a unified alge...
详细信息
We propose a new method for human action recognition based on multiple features and a hybrid generative/discriminative model. Specifically, we propose a new action representation based on computing a rich set of descr...
详细信息
Visual attention has been widely used in image pre-processing, since it can rapidly detect the region of interest in the given scene. This paper presents a novel technique to track the moving object, which is based on...
详细信息
Visual attention has been widely used in image pre-processing, since it can rapidly detect the region of interest in the given scene. This paper presents a novel technique to track the moving object, which is based on the motion saliency model. The salient region is computed by the combination of multi-feature maps and motion saliency map, which vastly reduce the amount of information in further imageprocessing. Next, a single matching method, normalized color histogram, is used to measure the similarity for tracking processing. Experimental results, found in AVSS 07, are reported, which validate our model useful and effective.
暂无评论