Volume : 5, Issue : 12, December - 2016

Performance Optimization of Distributed Face Recognition Based on Genetic Algorithm

Jie Shi

Abstract :

<p>&nbsp;<b style="text-align: justify;"><span style="font-size:10.0pt;line-height:115%;font-family:&quot;Times New Roman&quot;,serif;&#10;mso-fareast-language:ZH-CN">Due to the tasks </span></b><b style="text-align: justify;"><span style="font-size: 10pt; line-height: 115%; font-family: &quot;Times New Roman&quot;, serif;">partition into the agents unevenly will</span></b><b style="text-align: justify;"><span style="font-size: 10pt; line-height: 115%; font-family: &quot;Times New Roman&quot;, serif;"> cause </span></b><b style="text-align: justify;"><span style="font-size: 10pt; line-height: 115%; font-family: &quot;Times New Roman&quot;, serif;">the time of processing videos is too long and the CPU utilization of the agent which processes the most tasks will be explosion</span></b><b style="text-align: justify;"><span style="font-size: 10pt; line-height: 115%; font-family: &quot;Times New Roman&quot;, serif;">.</span></b><b style="text-align: justify;"><span style="font-size: 10pt; line-height: 115%; font-family: &quot;Times New Roman&quot;, serif;"> In order to solve the above problems, an improved genetic algorithm was proposed to balance the tasks of agents. Firstly, each agent counted the number of the videos and the number of pedestrians in each video. Secondly, the agents sen</span></b><b style="text-align: justify;"><span style="font-size: 10pt; line-height: 115%; font-family: &quot;Times New Roman&quot;, serif;">d</span></b><b style="text-align: justify;"><span style="font-size: 10pt; line-height: 115%; font-family: &quot;Times New Roman&quot;, serif;"> the statistical data to server by SOAP. Finally, server reallocated the videos to agents by using improved genetic algorithm. Experimental results show that the performance of distributed face recognition model has been effectively improved by using improved genetic algorithm to realize load balance.</span></b>< /> <b><span style="font-size: 10pt; line-height: 115%; font-family: &quot;Times New Roman&quot;, serif;">< clear="all" style="page-eak-before:auto;mso-eak-type:section-eak" /> </span></b></p> <div class="WordSection2"> <p class="MsoNormal" style="margin-bottom:0in;margin-bottom:.0001pt"><b><span style="font-size: 10pt; line-height: 115%; font-family: &quot;Times New Roman&quot;, serif;">&nbsp;</span></b></p> </div> <p><b><span style="font-size: 10pt; line-height: 115%; font-family: &quot;Times New Roman&quot;, serif;">< clear="all" style="page-eak-before:always;mso-eak-type:section-eak" /> </span></b></p>

Keywords :


Cite This Article:

Jie Shi, Performance Optimization of Distributed Face Recognition Based on Genetic Algorithm, Global Journal For Research Analysis,Volume : 5 | Issue : 12 | December 2016


Article No. : 1


Number of Downloads : 1


References :