{"id":76,"date":"2021-02-08T23:36:18","date_gmt":"2021-02-08T23:36:18","guid":{"rendered":"http:\/\/adaptivecomputation.com\/?page_id=76"},"modified":"2021-02-13T02:48:55","modified_gmt":"2021-02-13T02:48:55","slug":"inspiration-vs-reality","status":"publish","type":"page","link":"https:\/\/adaptivecomputation.com\/index.php\/inspiration-vs-reality\/","title":{"rendered":"Inspiration vs Reality"},"content":{"rendered":"

<\/p>\n

E<\/strong>xtended Vi<\/strong>sual P<\/strong>athway (EViP.1)<\/h3>\n

<\/p>\n

<\/p>\n


<\/p>\n

ADC\u2019s image processing system is based on the mammalian Extended Visual Pathway, incorporating features like a saccadic eye movement emulator, a bio-inspired visual pathway filter array, and a linear visual cortex to enable the detection and recognition of objects in open and ambiguous environments.  This is the key to EViP\u2019s ability to effectively mimic human visual capabilities, particularly our ability to recognize an object or person in a single glance, even when only seeing a partial, low resolution, or sketch image.<\/p>\n


<\/p>\n

<\/p>\n

<\/p>\n

EV<\/strong>iP<\/strong> vs HV<\/strong>iS<\/strong> (H<\/strong>uman Vi<\/strong>sual S<\/strong>ystem)<\/h3>\n

<\/p>\n

<\/p>\n

For a single-sample database, detailed testing has shown that ADC\u2019s EViP system can match human visual system performance (75% correct) in a face recognition task involving a database with 1,000 distractors.  With 10,000 distractors, EViP outperforms <\/em>HViS<\/strong>, providing 66% versus 24% correct recognition in rank 1.<\/p>\n


<\/p>\n

<\/p>\n

<\/p>\n

Table I: HViS vs EViP comparison based on MegaFace Challenge of UoW<\/h4>\n

<\/p>\n

<\/p>\n\n\n\n\n\n
Distractors<\/strong> <\/td>\n 1K<\/strong> <\/td>\n10K<\/strong><\/td>\n<\/tr>\n
HV<\/strong>iS*<\/strong><\/td>\n75%<\/strong> Correct\/ Rank 1              <\/td>\n24%<\/strong> \/Rank 1   & 91.1%<\/strong> \/Rank 10<\/td>\n<\/tr>\n
EV<\/strong>iP<\/strong> <\/td>\n75%<\/strong> Correct\/ Rank 1<\/td>\n66%<\/strong> \/Rank 1   & 78.5%<\/strong> \/Rank 10<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

<\/p>\n

<\/p>\n

* This results are from   http:\/\/megaface.cs.washington.edu\/results\/humanstudy.html<\/a><\/pre>\n
<\/p>\n
<\/p>\n

<\/h4>
HViS vs EViP Comparison<\/h4>\n
<\/p>\n
<\/p>\n
\"\"Blue-HViS<\/strong>
Pink-EViP<\/strong><\/h6>\n
<\/p>\n
<\/p>\n
 <\/h3>\n
I<\/strong>ntelligent P<\/strong>erception and Co<\/strong>gnition (IPCO)<\/h3>\n
\n
<\/p>\n
<\/p>\n
EViP\u2019s real-time feature extraction engine-unsupervised learning technique provides sufficient object features for full\/partial, noisy and low resolution, incomplete and sketch detection, recognition, and identification and facilitates autonomous adaptive capability in short term memory (Retina block) while EViP’s non-competitive supervised learning technique enables autonomy, in situ, adaptation learning to provide cognitive capability in long term memory (Visual Cortex block) for intelligent perception. <\/p>\n

<\/p>\n
There is no human interference in the continuous recognition and cognition learning process. The system\u2019s autonomy and its capability for selective adaptation without human interference in real-time operation give it the capability for true machine-intelligence.<\/p>\n
<\/p>","protected":false},"excerpt":{"rendered":"
Extended Visual Pathway (EViP.1) ADC\u2019s image processing system is based on the mammalian Extended Visual Pathway, incorporating features like a saccadic eye movement emulator, a bio-inspired visual pathway filter array, and a linear visual cortex to enable the detection and recognition of objects in open and ambiguous environments.  This is the key to EViP\u2019s ability to effectively… Continue reading Inspiration vs Reality<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":99,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-76","page","type-page","status-publish","has-post-thumbnail","hentry","entry"],"_links":{"self":[{"href":"https:\/\/adaptivecomputation.com\/index.php\/wp-json\/wp\/v2\/pages\/76","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/adaptivecomputation.com\/index.php\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/adaptivecomputation.com\/index.php\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/adaptivecomputation.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/adaptivecomputation.com\/index.php\/wp-json\/wp\/v2\/comments?post=76"}],"version-history":[{"count":19,"href":"https:\/\/adaptivecomputation.com\/index.php\/wp-json\/wp\/v2\/pages\/76\/revisions"}],"predecessor-version":[{"id":237,"href":"https:\/\/adaptivecomputation.com\/index.php\/wp-json\/wp\/v2\/pages\/76\/revisions\/237"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/adaptivecomputation.com\/index.php\/wp-json\/wp\/v2\/media\/99"}],"wp:attachment":[{"href":"https:\/\/adaptivecomputation.com\/index.php\/wp-json\/wp\/v2\/media?parent=76"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}