In this paper, we proposed an automated method for segmenting objects of weak boundaries and similar intensities on volumetric multichannel images. This method relied on a multiresolution classifier that tackled class...
详细信息
ISBN:
(纸本)9789082797039
In this paper, we proposed an automated method for segmenting objects of weak boundaries and similar intensities on volumetric multichannel images. This method relied on a multiresolution classifier that tackled class overlaps by using the Riemannian geometry of the RCDs of the multiscale patches of every multichannel image and reducing the dimensionality of these RCDs through a novel method that incorporated the intra- and inter-class neighborhoods of the RCDs in the Riemannian space and the spatial and hierarchical relationships between their corresponding patches. The reduced dimensional RCDs were then used to learn resolution-specific dictionaries for coding and classifications. To speed up the optimizations and to avoid convergence to local extrema, the dictionaries and the codes got initialized by a novel scheme that used the Riemannian geometry of the RCDs. This method was evaluated on the challenging task of segmenting cardiac adipose tissues on fat-water MR images.
Bag of visual words (BoVW) models are widely utilized in image/video representation and recognition. The cornerstone of these models is the encoding stage, in which local features are decomposed over a codebook in ord...
详细信息
Bag of visual words (BoVW) models are widely utilized in image/video representation and recognition. The cornerstone of these models is the encoding stage, in which local features are decomposed over a codebook in order to obtain a representation of features. In this paper, we propose a new encoding algorithm by jointly encoding the set of local descriptors of each sample and considering the locality structure of descriptors. The proposed method takes advantages of localitycoding such as its stability and robustness to noise in descriptors, as well as the strengths of the group coding strategy by taking into account the potential relation among descriptors of a sample. To efficiently implement our proposed method, we consider the Alternating Direction Method of Multipliers (ADMM) framework, which results in quadratic complexity in the problem size. The method is employed for a challenging classification problem: action recognition by depth cameras. Experimental results demonstrate the outperformance of our methodology compared to the state-of-the-art on the considered datasets. (C) 2017 Elsevier Inc. All rights reserved.
暂无评论