{"id":25,"date":"2023-05-31T14:20:08","date_gmt":"2023-05-31T12:20:08","guid":{"rendered":"https:\/\/sites.unica.it\/livdet\/?page_id=25"},"modified":"2024-04-15T15:05:58","modified_gmt":"2024-04-15T13:05:58","slug":"challenge-2","status":"publish","type":"page","link":"https:\/\/sites.unica.it\/livdet\/challenge-2\/","title":{"rendered":"Challenge 2"},"content":{"rendered":"\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Fingerprint representation<\/h3>

This Challenge is available for either contact and contactless fingerprint or both.\u00a0<\/i><\/h4>

\u00a0Please indicate during registration.<\/i><\/h4>
\u00a0<\/div>

In modern biometric systems, the compactness and the discriminability of feature vectors are fundamental to guarantee high performance in terms of accuracy and speed. Competitors are invited to submit a liveness detection algorithm which returns in addition to the probability of liveness, the feature vector corresponding to the input image with a maximum size of 512 bytes<\/u><\/strong>.<\/p>

The algorithms will be assessed on the basis of system accuracy<\/strong>\u00a0and system speed<\/strong> on PC with these characteristics:<\/p>

  • Desktop-PC Linux 18.04.1 Ubuntu – Intel\u00ae Core\u2122 i9 9900K @ 3.60GHz; RAM 64 GB DDR4 2.933 MHz; Dual NVIDIA\u00ae GeForce\u00ae RTX 2080 Ti (11GB each)<\/li>
  • Desktop-PC Windows 10 Pro – Intel\u00ae Core\u2122 i9 9900K @ 3.60GHz; RAM 64 GB DDR4 2.933 MHz; Dual NVIDIA\u00ae GeForce\u00ae RTX 2080 Ti (11GB each)<\/li><\/ul>

    Each submitted algorithm must be a Windows<\/strong> or Linux<\/strong> console<\/strong> application<\/strong> with the following list of parameters:<\/p>

    Synopsis: [nameOfAlgorithm].exe [ndataset] [probeimagesfile][livenessoutputfile] [embeddingsfile]<\/strong><\/em><\/p>

    [nameOfAlgorithm].exe <\/strong><\/em>– It is the executable name. Format: Windows or Linux console application (es. .exe)<\/p>

    [ndataset]<\/strong> <\/em>–\u00a0It is the identification number of the dataset to analyse. Legend:\u00a0<\/p>

    1. GreenBit<\/li>
    2. Dermalog<\/li>
    3. Unknown1<\/li>
    4. Unknown2<\/li><\/ol>

      [probeimagesfile]<\/em><\/strong> –\u00a0A text file with the list of absolute paths of each image to analyse. Each image is in the same format of own train set. Example of a [probeimagesfile]<\/strong><\/em> called GreenBit_probe.txt<\/em>:<\/p>

      …<\/em>
      G:\\Works\\LivDet2025\\ProbeImages\\GreenBit\\0123.png<\/em>
      G:\\Works\\LivDet2025\\ProbeImages\\GreenBit\\1323.png<\/em>
      G:\\Works\\LivDet2025\\ProbeImages\\GreenBit\\0033.png<\/em>
      G:\\Works\\LivDet2025\\ProbeImages\\GreenBit\\0954.png<\/em>
      G:\\Works\\LivDet2025\\ProbeImages\\GreenBit\\2154.png<\/em>
      …<\/em><\/p>

      [livenessoutputfile]<\/strong> <\/em>-The text file with the liveness output of each processed image, in the same order of “probeimagesfile”. The output is a posterior probability of the live class given the image, or a degree of \u201cliveness\u201d normalized in the range 0 and 100 (100 is the maximum degree of liveness, 0 means that the image is fake). Scores [0, 50) classify fingerprint image as “fake” while scores [50,100] classify fingerprint image as “live”(in Fig.1 in blue “livenessoutput”). In the case that the algorithm has not been able to process the image, the correspondent output must be -1000 (failure to enroll). Example of a [livenessoutputfile]<\/strong><\/em> called GreenBit_liveness_results.txt<\/em>:<\/p>

      …<\/em>
      100<\/em>
      54<\/em>
      -1000<\/em>
      32<\/em>
      78<\/em>
      …<\/em><\/p>

      [embeddingsfile] <\/strong><\/em>– The .npy or .mat file\u00a0with the feature vector of each processed image (in the same order of probeimagesfile).<\/p>

      \u00a0<\/p>

      Each parameter related to the dataset configuration must be set before submission. Each competitor can configure his algorithm by the training-set available after the registration. Only Windows\u00a0 or Linux console applications with the above characteristics will be accepted for the competition.<\/p>

      Participants are recommended to send a description of their algorithm.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"

      Fingerprint representation This Challenge is available for either contact and contactless fingerprint or both.\u00a0 \u00a0Please indicate during registration. \u00a0 In modern biometric systems, the compactness and the discriminability of feature vectors are fundamental to guarantee high performance in terms of accuracy and speed. Competitors are invited to submit a liveness detection algorithm which returns in…<\/p>\n","protected":false},"author":9666,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-25","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/sites.unica.it\/livdet\/wp-json\/wp\/v2\/pages\/25","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/sites.unica.it\/livdet\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/sites.unica.it\/livdet\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/sites.unica.it\/livdet\/wp-json\/wp\/v2\/users\/9666"}],"replies":[{"embeddable":true,"href":"https:\/\/sites.unica.it\/livdet\/wp-json\/wp\/v2\/comments?post=25"}],"version-history":[{"count":10,"href":"https:\/\/sites.unica.it\/livdet\/wp-json\/wp\/v2\/pages\/25\/revisions"}],"predecessor-version":[{"id":11483,"href":"https:\/\/sites.unica.it\/livdet\/wp-json\/wp\/v2\/pages\/25\/revisions\/11483"}],"wp:attachment":[{"href":"https:\/\/sites.unica.it\/livdet\/wp-json\/wp\/v2\/media?parent=25"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}