{
    "extrinsic": {
        "provider": "https://deposit.softwareheritage.org/1/private/1308/meta/",
        "raw": {
            "origin": {
                "type": "deposit",
                "url": "https://doi.org/10.5201/ipol.2017.204"
            },
            "origin_metadata": {
                "metadata": {
                    "atom:external_identifier": "ipol.2017.204",
                    "atom:title": "ipol_204",
                    "codemeta:applicationCategory": "Image Processing",
                    "codemeta:author": [
                        {
                            "codemeta:affiliation": "Department of Mathematics, UCLA",
                            "codemeta:name": "Zhaoyi Meng"
                        },
                        {
                            "codemeta:affiliation": "Department of Mathematics, MSU",
                            "codemeta:name": "Ekaterina Merkurjev"
                        },
                        {
                            "codemeta:affiliation": "Lawrence Berkeley National Laboratory",
                            "codemeta:name": "Alice Koniges"
                        },
                        {
                            "codemeta:affiliation": "Department of Mathematics, UCLA",
                            "codemeta:name": "Andrea L. Bertozzi"
                        }
                    ],
                    "codemeta:dateCreated": "2017-02-15",
                    "codemeta:datePublished": "2017-08-19",
                    "codemeta:description": "Hyperspectral Image Classification Using Graph Clustering Methods",
                    "codemeta:downloadUrl": "http://www.ipol.im/pub/art/2017/204/semi.tgz",
                    "codemeta:identifier": "https://doi.org/10.5201/ipol.2017.204",
                    "codemeta:isPartOf": {
                        "codemeta:identifier": "ISSN: 2105-1232 DOI: 10.5201/ipol",
                        "codemeta:name": "Image Processing On Line (IPOL)",
                        "codemeta:type": "Journal"
                    },
                    "codemeta:keywords": [
                        "multi-class classification",
                        "hyperspectral video",
                        "energy minimization",
                        "MBO scheme",
                        "Nystr\u00f6m extension method",
                        "parallel computing"
                    ],
                    "codemeta:license": {
                        "codemeta:name": "BSD-2-Clause",
                        "codemeta:url": "https://spdx.org/licenses/BSD-2-Clause.html"
                    },
                    "codemeta:operatingSystem": "Linux",
                    "codemeta:programmingLanguage": "C",
                    "codemeta:referencePublication": {
                        "codemeta:abstract": "Hyperspectral imagery is a challenging modality due to the dimension of the pixels which can range from hundreds to over a thousand frequencies depending on the sensor. Most methods in the literature reduce the dimension of the data using a method such as principal component analysis, however this procedure can lose information. More recently methods have been developed to address classification of large datasets in high dimensions. This paper presents two classes of graph-based classification methods for hyperspectral imagery. Using the full dimensionality of the data, we consider a similarity graph based on pairwise comparisons of pixels. The graph is segmented using a pseudospectral algorithm for graph clustering that requires information about the eigenfunctions of the graph Laplacian but does not require computation of the full graph. We develop a parallel version of the Nystr\u00f6m extension method to randomly sample the graph to construct a low rank approximation of the graph Laplacian. With at most a few hundred eigenfunctions, we can implement the clustering method designed to solve a variational problem for a graph-cut-based semi-supervised or unsupervised classification problem. We implement OpenMP directive-based parallelism in our algorithms and show performance improvement and strong, almost ideal, scaling behavior. The method can handle very large datasets including a video sequence with over a million pixels, and the problem of segmenting a data set into a pre-determined number of classes.",
                        "codemeta:identifier": "https://doi.org/10.5201/ipol.2017.204",
                        "codemeta:name": "Hyperspectral Image Classification Using Graph Clustering Methods",
                        "codemeta:url": "http://www.ipol.im/pub/art/2017/204/article.pdf"
                    },
                    "codemeta:relatedLink": "http://ipolcore.ipol.im/demo/clientApp/demo.html?id=204",
                    "codemeta:releaseNotes": "This code implements the algorithm(s) published in the IPOL paper \"Hyperspectral Image Classification Using Graph Clustering Methods\"",
                    "codemeta:url": "http://www.ipol.im/pub/art/2017/204/",
                    "codemeta:version": "1.0"
                },
                "provider": {
                    "metadata": {},
                    "provider_name": "",
                    "provider_type": "deposit_client",
                    "provider_url": "https://doi.org/10.5201/"
                },
                "tool": {
                    "configuration": {
                        "sword_version": "2"
                    },
                    "name": "swh-deposit",
                    "version": "0.8.0"
                }
            }
        },
        "when": "2020-12-23T23:20:46.781443+00:00"
    },
    "original_artifact": [
        {
            "checksums": {
                "sha1": "9cf3e10284485ddffa69d5da493e1be5b3c1ad8c",
                "sha256": "846bad80c76f7c9078e719fece390fc9e84e75ac11b9dc60f4ebbf8740077533"
            },
            "filename": "archive.zip",
            "length": 355152,
            "url": "https://deposit.softwareheritage.org/1/private/1308/raw/"
        }
    ]
}