{
  "_schema": "https://data.nist.gov/od/dm/nerdm-schema/v0.7#",
  "@context": [
    "https://data.nist.gov/od/dm/nerdm-pub-context.jsonld",
    {
      "@base": "ark:/88434/mds2-2155"
    }
  ],
  "@type": [
    "nrdp:PublicDataResource"
  ],
  "_extensionSchemas": [
    "https://data.nist.gov/od/dm/nerdm-schema/pub/v0.7#/definitions/PublicDataResource"
  ],
  "@id": "ark:/88434/mds2-2155",
  "doi": "doi:10.18434/M32155",
  "title": "2D Segmentation of Concrete Samples for Training AI Models",
  "contactPoint": {
    "fn": "Peter Bajcsy",
    "hasEmail": "mailto:peter.bajcsy@nist.gov"
  },
  "modified": "2019-11-18 00:00:00",
  "ediid": "ark:/88434/mds2-2155",
  "landingPage": "https://data.nist.gov/od/id/mds2-2155",
  "description": [
    "This web-based validation system has been designed to perform visual validation of automated multi-class segmentation of concrete samples from scanning electron microscopy (SEM) images. The goal is to segment automatically SEM images into no-damage and damage sub-classes, where the damage sub-classes consist of paste damage, aggregate damage, and air voids. While the no-damage sub-classes are not included in the goal, they provide context for assigning damage sub-classes. The motivation behind this web validation system is to prepare a large number of pixel-level multi-class annotated microscopy images for training artificial intelligence (AI) based segmentation models (U-Net and SegNet models). While the purpose of the AI models is to predict accurately four damage labels, such as, paste damage, aggregate damage, air voids, and no-damage, our goal is to assert trust in such predictions (a) by using contextual labels and (b) by enabling visual validations of predicted damage labels."
  ],
  "keyword": [
    "CS-MET computational metrology"
  ],
  "theme": [
    "Information Technology:Computational science"
  ],
  "topic": [],
  "accessLevel": "public",
  "license": "https://www.nist.gov/open/license",
  "components": [
    {
      "accessURL": "https://isg.nist.gov/deepzoomweb/data/concreteScoring",
      "format": {
        "description": "TIFF file format"
      },
      "description": "his web-based validation system has been designed to perform visual validation of automated multi-class segmentation of concrete samples from scanning electron microscopy (SEM) images. The goal is to segment automatically SEM images into no-damage and damage sub-classes, where the damage sub-classes consist of paste damage, aggregate damage, and air voids. While the no-damage sub-classes are not included in the goal, they provide context for assigning damage sub-classes.",
      "title": "2D Segmentation of Concrete Samples for Training AI Models",
      "@type": [
        "nrdp:AccessPage",
        "dcat:Distribution"
      ],
      "@id": "#deepzoomweb/data/concreteScoring",
      "_extensionSchemas": [
        "https://data.nist.gov/od/dm/nerdm-schema/pub/v0.7#/definitions/AccessPage"
      ]
    },
    {
      "accessURL": "https://github.com/usnistgov/WIPP-unet-train-plugin",
      "title": "UNet CNN Semantic-Segmentation Training plugin",
      "@type": [
        "nrdp:AccessPage",
        "dcat:Distribution"
      ],
      "@id": "#usnistgov/WIPP-unet-train-plugin",
      "_extensionSchemas": [
        "https://data.nist.gov/od/dm/nerdm-schema/pub/v0.7#/definitions/AccessPage"
      ]
    },
    {
      "accessURL": "https://github.com/usnistgov/WIPP-unet-inference-plugin",
      "title": "UNet CNN Semantic-Segmentation Inference plugin",
      "@type": [
        "nrdp:AccessPage",
        "dcat:Distribution"
      ],
      "@id": "#usnistgov/WIPP-unet-inference-plugin",
      "_extensionSchemas": [
        "https://data.nist.gov/od/dm/nerdm-schema/pub/v0.7#/definitions/AccessPage"
      ]
    },
    {
      "accessURL": "https://doi.org/10.18434/M32155",
      "title": "DOI Access for 2D Segmentation of Concrete Samples for Training AI Models",
      "@type": [
        "nrd:Hidden",
        "dcat:Distribution"
      ],
      "@id": "#doi:10.18434/M32155"
    }
  ],
  "publisher": {
    "name": "National Institute of Standards and Technology",
    "@type": "org:Organization"
  },
  "language": [
    "en"
  ],
  "bureauCode": [
    "006:55"
  ],
  "programCode": [
    "006:045"
  ],
  "references": [],
  "version": "1.0.0"
}