Spatial and Hierarchical Riemannian Dimensionality Reduction and Dictionary Learning for Segmenting Multichannel Images. Fallah, F., Armanious, K., Yang, B., & Bamberg, F. In 2019 27th European Signal Processing Conference (EUSIPCO), pages 1-5, Sep., 2019. Paper doi abstract bibtex 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.
@InProceedings{8903175,
author = {F. Fallah and K. Armanious and B. Yang and F. Bamberg},
booktitle = {2019 27th European Signal Processing Conference (EUSIPCO)},
title = {Spatial and Hierarchical Riemannian Dimensionality Reduction and Dictionary Learning for Segmenting Multichannel Images},
year = {2019},
pages = {1-5},
abstract = {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.},
keywords = {biological tissues;biomedical MRI;cardiology;image classification;image coding;image resolution;image segmentation;medical image processing;cardiac adipose tissues;reduced dimensional RCDs;interclass neighborhoods;spatial Riemannian dimensionality reduction;hierarchical Riemannian dimensionality reduction;fat-water MR images;resolution-specific dictionaries;hierarchical relationships;spatial relationships;Riemannian space;multiscale patches;Riemannian geometry;class overlaps;multiresolution classifier;volumetric multichannel images;automated method;dictionary learning;Training;Image segmentation;Image resolution;Dictionaries;Manifolds;Dimensionality reduction;Feature extraction;Riemannian Manifolds;Nonlinear Dimensionality Reduction;Dictionary Learning;Locality Constrained Coding;Segmenting Multichannel Images},
doi = {10.23919/EUSIPCO.2019.8903175},
issn = {2076-1465},
month = {Sep.},
url = {https://www.eurasip.org/proceedings/eusipco/eusipco2019/proceedings/papers/1570531329.pdf},
}
Downloads: 0
{"_id":"pA5HKScTtpayty9cq","bibbaseid":"fallah-armanious-yang-bamberg-spatialandhierarchicalriemanniandimensionalityreductionanddictionarylearningforsegmentingmultichannelimages-2019","authorIDs":[],"author_short":["Fallah, F.","Armanious, K.","Yang, B.","Bamberg, F."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["F."],"propositions":[],"lastnames":["Fallah"],"suffixes":[]},{"firstnames":["K."],"propositions":[],"lastnames":["Armanious"],"suffixes":[]},{"firstnames":["B."],"propositions":[],"lastnames":["Yang"],"suffixes":[]},{"firstnames":["F."],"propositions":[],"lastnames":["Bamberg"],"suffixes":[]}],"booktitle":"2019 27th European Signal Processing Conference (EUSIPCO)","title":"Spatial and Hierarchical Riemannian Dimensionality Reduction and Dictionary Learning for Segmenting Multichannel Images","year":"2019","pages":"1-5","abstract":"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.","keywords":"biological tissues;biomedical MRI;cardiology;image classification;image coding;image resolution;image segmentation;medical image processing;cardiac adipose tissues;reduced dimensional RCDs;interclass neighborhoods;spatial Riemannian dimensionality reduction;hierarchical Riemannian dimensionality reduction;fat-water MR images;resolution-specific dictionaries;hierarchical relationships;spatial relationships;Riemannian space;multiscale patches;Riemannian geometry;class overlaps;multiresolution classifier;volumetric multichannel images;automated method;dictionary learning;Training;Image segmentation;Image resolution;Dictionaries;Manifolds;Dimensionality reduction;Feature extraction;Riemannian Manifolds;Nonlinear Dimensionality Reduction;Dictionary Learning;Locality Constrained Coding;Segmenting Multichannel Images","doi":"10.23919/EUSIPCO.2019.8903175","issn":"2076-1465","month":"Sep.","url":"https://www.eurasip.org/proceedings/eusipco/eusipco2019/proceedings/papers/1570531329.pdf","bibtex":"@InProceedings{8903175,\n author = {F. Fallah and K. Armanious and B. Yang and F. Bamberg},\n booktitle = {2019 27th European Signal Processing Conference (EUSIPCO)},\n title = {Spatial and Hierarchical Riemannian Dimensionality Reduction and Dictionary Learning for Segmenting Multichannel Images},\n year = {2019},\n pages = {1-5},\n abstract = {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.},\n keywords = {biological tissues;biomedical MRI;cardiology;image classification;image coding;image resolution;image segmentation;medical image processing;cardiac adipose tissues;reduced dimensional RCDs;interclass neighborhoods;spatial Riemannian dimensionality reduction;hierarchical Riemannian dimensionality reduction;fat-water MR images;resolution-specific dictionaries;hierarchical relationships;spatial relationships;Riemannian space;multiscale patches;Riemannian geometry;class overlaps;multiresolution classifier;volumetric multichannel images;automated method;dictionary learning;Training;Image segmentation;Image resolution;Dictionaries;Manifolds;Dimensionality reduction;Feature extraction;Riemannian Manifolds;Nonlinear Dimensionality Reduction;Dictionary Learning;Locality Constrained Coding;Segmenting Multichannel Images},\n doi = {10.23919/EUSIPCO.2019.8903175},\n issn = {2076-1465},\n month = {Sep.},\n url = {https://www.eurasip.org/proceedings/eusipco/eusipco2019/proceedings/papers/1570531329.pdf},\n}\n\n","author_short":["Fallah, F.","Armanious, K.","Yang, B.","Bamberg, F."],"key":"8903175","id":"8903175","bibbaseid":"fallah-armanious-yang-bamberg-spatialandhierarchicalriemanniandimensionalityreductionanddictionarylearningforsegmentingmultichannelimages-2019","role":"author","urls":{"Paper":"https://www.eurasip.org/proceedings/eusipco/eusipco2019/proceedings/papers/1570531329.pdf"},"keyword":["biological tissues;biomedical MRI;cardiology;image classification;image coding;image resolution;image segmentation;medical image processing;cardiac adipose tissues;reduced dimensional RCDs;interclass neighborhoods;spatial Riemannian dimensionality reduction;hierarchical Riemannian dimensionality reduction;fat-water MR images;resolution-specific dictionaries;hierarchical relationships;spatial relationships;Riemannian space;multiscale patches;Riemannian geometry;class overlaps;multiresolution classifier;volumetric multichannel images;automated method;dictionary learning;Training;Image segmentation;Image resolution;Dictionaries;Manifolds;Dimensionality reduction;Feature extraction;Riemannian Manifolds;Nonlinear Dimensionality Reduction;Dictionary Learning;Locality Constrained Coding;Segmenting Multichannel Images"],"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/Roznn/EUSIPCO/main/eusipco2019url.bib","creationDate":"2021-02-11T19:15:22.181Z","downloads":0,"keywords":["biological tissues;biomedical mri;cardiology;image classification;image coding;image resolution;image segmentation;medical image processing;cardiac adipose tissues;reduced dimensional rcds;interclass neighborhoods;spatial riemannian dimensionality reduction;hierarchical riemannian dimensionality reduction;fat-water mr images;resolution-specific dictionaries;hierarchical relationships;spatial relationships;riemannian space;multiscale patches;riemannian geometry;class overlaps;multiresolution classifier;volumetric multichannel images;automated method;dictionary learning;training;image segmentation;image resolution;dictionaries;manifolds;dimensionality reduction;feature extraction;riemannian manifolds;nonlinear dimensionality reduction;dictionary learning;locality constrained coding;segmenting multichannel images"],"search_terms":["spatial","hierarchical","riemannian","dimensionality","reduction","dictionary","learning","segmenting","multichannel","images","fallah","armanious","yang","bamberg"],"title":"Spatial and Hierarchical Riemannian Dimensionality Reduction and Dictionary Learning for Segmenting Multichannel Images","year":2019,"dataSources":["NqWTiMfRR56v86wRs","r6oz3cMyC99QfiuHW"]}