Application of EARLYBREAK for Line Segment Hausdorff Distance for Face Recognition

Chau Dang-Nguyen
<span title="">2020</span> <i title="ASTES Journal"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/5z5fhzfgard2vod5er2hdyuq54" style="color: black;">Advances in Science, Technology and Engineering Systems</a> </i> &nbsp;
The Hausdorff distance (HD) is defined as MAX-MIN distance between two geometric objects for measuring the dissimilarity between two objects. Because MAX-MIN distance is sensitive with the outliers, in face recognition field, average Hausdorff distance is used for measuring the dissimilarity between two sets of features. The computational complexity of HD, and also average HD, is high. Various methods have been proposed in recent decades for reducing the computational complexity of HD
more &raquo; ... However, these methods could not be used for reducing the computational complexity of average HD. Line Hausdorff distance (LHD) is a face recognition method, which uses weighted average HD for measuring the distance between two line edge maps of face images. In this paper, the Least Trimmed Square Line Hausdorff Distance method, LTS-LHD, is proposed for face recognition. The LTS-LHD, which is a modification of the weighted average HD, is used for measuring the distance between two line edge maps. The state -of -art algorithm, the EARLYBREAK method, is used for reducing the computational complexity of the LTS-LHD. The experimental results show that the accuracy of proposed method and LHD method are equivalent while the runtime of proposed method is 68% lower than LHD method.
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.25046/aj050466">doi:10.25046/aj050466</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ooxryp2opvfxrjrj2n67wpse7i">fatcat:ooxryp2opvfxrjrj2n67wpse7i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201106202253/http://www.astesj.com/publications/ASTESJ_050466.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/f2/df/f2df915ff1a58c54e5fa33e70c03aa863a93dd8b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.25046/aj050466"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>