/members-area/personalblogs/b/andy-clark-s-blog/posts/dragonboard-410c---opencvI&#39;ve put the code for the project on Github as it&#39;s now starting to get interesting. Testing on something simplerSo that I knew that OpenCV was working correctly I created a simple test script. import numpy as np import cv2 print cv...en-USTelligent Community 12https://community.element14.com/members-area/personalblogs/b/andy-clark-s-blog/posts/dragonboard-410c---opencvSat, 21 May 2016 19:59:40 GMT93d5dcb4-84c2-446f-b2cb-99731719e767:75d1146e-2cca-4064-affb-ccba58b30f36DAB0<p>Yes the &quot;self&quot; learning algorithms take a lot of time and options before they get reasonably reliable.</p><p>&nbsp;</p><p>I have seen a number of approaches where they use the geometry of eye placement and nose/mouth relationships to quickly narrow the search areas.</p><p>&nbsp;</p><p>DAB</p><img src="https://community.element14.com/aggbug?PostID=21675&AppID=312&AppType=Weblog&ContentType=0" width="1" height="1">