{"id":2903,"date":"2017-01-08T15:45:49","date_gmt":"2017-01-08T23:45:49","guid":{"rendered":"http:\/\/briantroy.com\/?p=2903"},"modified":"2025-01-03T04:30:40","modified_gmt":"2025-01-03T04:30:40","slug":"aws-rekognition-graph-analysis-person-label-accuracy","status":"publish","type":"post","link":"https:\/\/blogarchive.briantroy.com\/index.php\/2017\/01\/08\/aws-rekognition-graph-analysis-person-label-accuracy\/","title":{"rendered":"AWS Rekognition Graph Analysis &#8211; Person Label Accuracy"},"content":{"rendered":"<p>Last week I wrote a <a href=\"http:\/\/briantroy.com\/2017\/01\/05\/analyzing-aws-rekognition-accuracy-with-neo4j\/\">post evaluating AWS Rekognition accuracy in finding people in images<\/a>. The analysis was performed using the Neo4j graph database.<\/p>\n<p>As I noted in the original post &#8211; Rekognition is either very confident it has identified a person or not confident at all. This leads to an enormous number of false negatives. Today I looked at the distribution of confidence for the Person label over the last 48 hours.<\/p>\n<p>You be the judge:<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone wp-image-2907 size-full\" src=\"https:\/\/blogarchive.briantroy.com\/wp-content\/uploads\/2017\/01\/rekognition-person-label-confidence-distribution-2.jpg\" alt=\"rekognition-person-label-confidence-distribution\" width=\"2310\" height=\"1187\" \/><\/p>\n<p>Check out <a href=\"http:\/\/briantroy.com\/2017\/01\/05\/analyzing-aws-rekognition-accuracy-with-neo4j\/\">original\u00a0post<\/a> to see how the graph is created and constantly updated as images are created in the <a href=\"http:\/\/briantroy.com\/2016\/10\/25\/serverless-architecture-practical-iot-implementation\/\">serverless IoT processing system<\/a>.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Last week I wrote a post evaluating AWS Rekognition accuracy in finding people in images. The analysis was performed using the Neo4j graph database. As I noted in the original post &#8211; Rekognition is either very confident it has identified a person or not confident at all. This leads to an enormous number of false&hellip; <a class=\"more-link\" href=\"https:\/\/blogarchive.briantroy.com\/index.php\/2017\/01\/08\/aws-rekognition-graph-analysis-person-label-accuracy\/\">Continue reading <span class=\"screen-reader-text\">AWS Rekognition Graph Analysis &#8211; Person Label Accuracy<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":2907,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[3,6,12,19,22,28],"tags":[54,81,146,155,233],"_links":{"self":[{"href":"https:\/\/blogarchive.briantroy.com\/index.php\/wp-json\/wp\/v2\/posts\/2903"}],"collection":[{"href":"https:\/\/blogarchive.briantroy.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blogarchive.briantroy.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blogarchive.briantroy.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/blogarchive.briantroy.com\/index.php\/wp-json\/wp\/v2\/comments?post=2903"}],"version-history":[{"count":1,"href":"https:\/\/blogarchive.briantroy.com\/index.php\/wp-json\/wp\/v2\/posts\/2903\/revisions"}],"predecessor-version":[{"id":3308,"href":"https:\/\/blogarchive.briantroy.com\/index.php\/wp-json\/wp\/v2\/posts\/2903\/revisions\/3308"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/blogarchive.briantroy.com\/index.php\/wp-json\/wp\/v2\/media\/2907"}],"wp:attachment":[{"href":"https:\/\/blogarchive.briantroy.com\/index.php\/wp-json\/wp\/v2\/media?parent=2903"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blogarchive.briantroy.com\/index.php\/wp-json\/wp\/v2\/categories?post=2903"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blogarchive.briantroy.com\/index.php\/wp-json\/wp\/v2\/tags?post=2903"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}