http://samediff.kr/wiki/index.php?action=history&feed=atom&title=CMC 2026-04-28T04:09:44Z 이 문서의 편집 역사 MediaWiki 1.34.0 http://samediff.kr/wiki/index.php?title=CMC&diff=13210&oldid=prev 2017-07-31T09:13:26Z

<p></p> <table class="diff diff-contentalign-left" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="ko"> <td colspan="2" style="background-color: #fff; color: #222; text-align: center;">← 이전 판</td> <td colspan="2" style="background-color: #fff; color: #222; text-align: center;">2017년 7월 31일 (월) 09:13 판</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l5" >5번째 줄:</td> <td colspan="2" class="diff-lineno">5번째 줄:</td></tr> <tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>rank=1부터 시작이므로 rank=0~1구간은 비어있거나 축에서 아예 제외되고, 데이터 그대로 그리자면 부드러운(differentiable) 커브가 아니다.  </div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>rank=1부터 시작이므로 rank=0~1구간은 비어있거나 축에서 아예 제외되고, 데이터 그대로 그리자면 부드러운(differentiable) 커브가 아니다.  </div></td></tr> <tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr> <tr><td class='diff-marker'>−</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>말로 된 설명은 [https://www.researchgate.net/post/How_is_CMC_produced_recognition_rate_vs_Rank_for_unknown_faces How is CMC produced (recognition rate vs Rank) for unknown faces?]가 가장 쉬운 것 같고, 예제그림은 [<del class="diffchange diffchange-inline">https</del>://www.<del class="diffchange diffchange-inline">nist</del>.<del class="diffchange diffchange-inline">gov/sites/default</del>/<del class="diffchange diffchange-inline">files</del>/<del class="diffchange diffchange-inline">documents</del>/<del class="diffchange diffchange-inline">2016</del>/<del class="diffchange diffchange-inline">12/06/12_ross_cmc-roc_ibpc2016</del>.pdf <del class="diffchange diffchange-inline">이 pdf</del>]<del class="diffchange diffchange-inline">의 6페이지에 </del>있다. Formal한 설명은 논문&lt;ref&gt;Grother, Patrick, Ross J. Micheals, and P. Jonathon Phillips. &quot;Face recognition vendor test 2002 performance metrics.&quot; Audio-and Video-Based Biometric Person Authentication. Springer Berlin Heidelberg, 2003. &lt;/ref&gt;을 참고한다.</div></td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>말로 된 설명은 [https://www.researchgate.net/post/How_is_CMC_produced_recognition_rate_vs_Rank_for_unknown_faces How is CMC produced (recognition rate vs Rank) for unknown faces?]가 가장 쉬운 것 같고, 예제그림은 <ins class="diffchange diffchange-inline">논문(</ins>[<ins class="diffchange diffchange-inline">http</ins>://www.<ins class="diffchange diffchange-inline">cv-foundation</ins>.<ins class="diffchange diffchange-inline">org</ins>/<ins class="diffchange diffchange-inline">openaccess</ins>/<ins class="diffchange diffchange-inline">content_cvpr_2015</ins>/<ins class="diffchange diffchange-inline">papers</ins>/<ins class="diffchange diffchange-inline">Ahmed_An_Improved_Deep_2015_CVPR_paper</ins>.pdf <ins class="diffchange diffchange-inline">example</ins>]<ins class="diffchange diffchange-inline">) 여기저기서 많이 볼 수 </ins>있다. Formal한 설명은 논문&lt;ref&gt;Grother, Patrick, Ross J. Micheals, and P. Jonathon Phillips. &quot;Face recognition vendor test 2002 performance metrics.&quot; Audio-and Video-Based Biometric Person Authentication. Springer Berlin Heidelberg, 2003. &lt;/ref&gt;을 참고한다.</div></td></tr> <tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr> <tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>참고: [[Mean Average Precision|mAP]]</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>참고: [[Mean Average Precision|mAP]]</div></td></tr> </table>

Admin http://samediff.kr/wiki/index.php?title=CMC&diff=13208&oldid=prev 2017-07-31T07:16:02Z

<p></p> <table class="diff diff-contentalign-left" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="ko"> <td colspan="2" style="background-color: #fff; color: #222; text-align: center;">← 이전 판</td> <td colspan="2" style="background-color: #fff; color: #222; text-align: center;">2017년 7월 31일 (월) 07:16 판</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l6" >6번째 줄:</td> <td colspan="2" class="diff-lineno">6번째 줄:</td></tr> <tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr> <tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>말로 된 설명은 [https://www.researchgate.net/post/How_is_CMC_produced_recognition_rate_vs_Rank_for_unknown_faces How is CMC produced (recognition rate vs Rank) for unknown faces?]가 가장 쉬운 것 같고, 예제그림은 [https://www.nist.gov/sites/default/files/documents/2016/12/06/12_ross_cmc-roc_ibpc2016.pdf 이 pdf]의 6페이지에 있다. Formal한 설명은 논문&lt;ref&gt;Grother, Patrick, Ross J. Micheals, and P. Jonathon Phillips. &quot;Face recognition vendor test 2002 performance metrics.&quot; Audio-and Video-Based Biometric Person Authentication. Springer Berlin Heidelberg, 2003. &lt;/ref&gt;을 참고한다.</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>말로 된 설명은 [https://www.researchgate.net/post/How_is_CMC_produced_recognition_rate_vs_Rank_for_unknown_faces How is CMC produced (recognition rate vs Rank) for unknown faces?]가 가장 쉬운 것 같고, 예제그림은 [https://www.nist.gov/sites/default/files/documents/2016/12/06/12_ross_cmc-roc_ibpc2016.pdf 이 pdf]의 6페이지에 있다. Formal한 설명은 논문&lt;ref&gt;Grother, Patrick, Ross J. Micheals, and P. Jonathon Phillips. &quot;Face recognition vendor test 2002 performance metrics.&quot; Audio-and Video-Based Biometric Person Authentication. Springer Berlin Heidelberg, 2003. &lt;/ref&gt;을 참고한다.</div></td></tr> <tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;"></ins></div></td></tr> <tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">참고: [[Mean Average Precision|mAP]]</ins></div></td></tr> </table>

Admin http://samediff.kr/wiki/index.php?title=CMC&diff=13206&oldid=prev 2017-07-31T07:13:02Z

<p>새 문서: cumulative matching curve x축이 rank, y축이 identification accuracy(0~1)이 된다.&lt;br /&gt; rank1에 다 맞추면 rank=1지점부터 y=1로 직선이 그어지겠지만, 보통은...</p> <p><b>새 문서</b></p><div>cumulative matching curve<br /> <br /> x축이 rank, y축이 identification accuracy(0~1)이 된다.&lt;br /&gt;<br /> rank1에 다 맞추면 rank=1지점부터 y=1로 직선이 그어지겠지만, 보통은 ROC와 비슷한 모양의 커브를 이룬다.&lt;br /&gt;<br /> rank=1부터 시작이므로 rank=0~1구간은 비어있거나 축에서 아예 제외되고, 데이터 그대로 그리자면 부드러운(differentiable) 커브가 아니다. <br /> <br /> 말로 된 설명은 [https://www.researchgate.net/post/How_is_CMC_produced_recognition_rate_vs_Rank_for_unknown_faces How is CMC produced (recognition rate vs Rank) for unknown faces?]가 가장 쉬운 것 같고, 예제그림은 [https://www.nist.gov/sites/default/files/documents/2016/12/06/12_ross_cmc-roc_ibpc2016.pdf 이 pdf]의 6페이지에 있다. Formal한 설명은 논문&lt;ref&gt;Grother, Patrick, Ross J. Micheals, and P. Jonathon Phillips. &quot;Face recognition vendor test 2002 performance metrics.&quot; Audio-and Video-Based Biometric Person Authentication. Springer Berlin Heidelberg, 2003. &lt;/ref&gt;을 참고한다.</div>

Admin