{"id":29016,"date":"2018-11-24T01:06:43","date_gmt":"2018-11-23T23:06:43","guid":{"rendered":"https:\/\/mamchenkov.net\/wordpress\/?p=29016"},"modified":"2019-02-25T12:00:09","modified_gmt":"2019-02-25T10:00:09","slug":"amazon-rekognition-enhanced-capabilities","status":"publish","type":"post","link":"https:\/\/mamchenkov.net\/wordpress\/2018\/11\/24\/amazon-rekognition-enhanced-capabilities\/","title":{"rendered":"Amazon Rekognition enhanced capabilities"},"content":{"rendered":"\n

\"\"<\/a>Amazon Machine Learning Blog<\/a> announces some very significant improvements<\/a> to the Amazon Rekognition<\/a> – their service for image and video analysis.  These particular changes are improving the face recognition technology.<\/p>\n

\u201cFace detection\u201d tries to answer the question: Is there a face in this picture? In real-world images, various aspects can have an impact on a system\u2019s ability to detect faces with high accuracy. These aspects might include pose variations caused by head movement and\/or camera movements, occlusion due to foreground or background objects (such as faces covered by hats, hair, or hands of another person in the foreground), illumination variations (such as low contrast and shadows), bright lighting that leads to washed out faces, low quality and resolution that leads to noisy and blurry faces, and distortion from cameras and lenses themselves. These issues manifest as missed detections (a face not detected) or false detections (an image region detected as a face even when there is no face). For example, on social media different poses, camera filters, lighting, and occlusions (such as a photo bomb) are common. For financial services customers, verification of customer identity as a part of multi-factor authentication and fraud prevention workflows involves matching a high resolution selfie (a face image) with a lower resolution, small, and often blurry image of face on a photo identity document (such as a passport or driving license). Also, many customers have to detect and recognize faces of low contrast from images where the camera is pointing at a bright light.<\/p>\n

With the latest updates, Amazon Rekognition can now detect 40 percent more faces \u2013 that would have been previously missed \u2013 in images that have some of the most challenging conditions described earlier. At the same time, the rate of false detections is reduced by 50 percent. This means that customers such as social media apps can get consistent and reliable detections (fewer misses, fewer false detections) with higher confidence, allowing them to deliver better customer experiences in use cases like automated profile photo review. In addition, face recognition now returns 30 percent more correct \u2018best\u2019 matches (the most similar face) compared to our previous model when searching against a large collection of faces. This enables customers to obtain better search results in applications like fraud prevention. Face matches now also have more consistent similarity scores across varying lighting, pose, and appearance, allowing customers to use higher confidence thresholds, avoid false matches, and reduce human review in applications such as identity verification. As always, for use cases involving civil liberties or customer sentiments, where the veracity of the match is critical, we recommend that customers use best practices, higher confidence level (at least 99%), and always include human review.<\/p><\/blockquote>\n

Have a look at their blog post<\/a> for some examples of what the machine can recognize as a face.  Some of these are difficult enough to treat many humans, I think.<\/p>\n\n","protected":false},"excerpt":{"rendered":"\n

Amazon Machine Learning Blog announces some very significant improvements to the Amazon Rekognition – their service for image and video analysis.  These particular changes are improving the face recognition technology. \u201cFace detection\u201d tries to answer the question: Is there a face in this picture? In real-world images, various aspects can have an impact on a system\u2019s … Continue reading Amazon Rekognition enhanced capabilities<\/span><\/a><\/p>\n\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_publicize_message":"Amazon Rekognition enhanced capabilities #WebDev #AWS #AI #MachineLearning #ImageRecognition","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":true,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2},"_links_to":"","_links_to_target":""},"categories":[1,18,62,1334],"tags":[3270,3464,1462,2366,1460,3493,1330],"keyring_services":[],"class_list":["post-29016","post","type-post","status-publish","format-standard","hentry","category-general","category-programming","category-technology","category-web-work","tag-amazon-aws","tag-amazon-rekognition","tag-artificial-intelligence","tag-cloud-computing","tag-image-recognition","tag-machine-learning","tag-web-development"],"aioseo_notices":[],"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack-related-posts":[{"id":27060,"url":"https:\/\/mamchenkov.net\/wordpress\/2016\/12\/05\/amazon-rekognition-image-detection-and-recognition-powered-by-deep-learning\/","url_meta":{"origin":29016,"position":0},"title":"Amazon Rekognition \u2013 Image Detection and Recognition Powered by Deep Learning","author":"Leonid Mamchenkov","date":"December 5, 2016","format":false,"excerpt":"I know, I know, this blog is turning into an Amazon marketing blow-horn, but what can I do? Amazon re:Invent 2016 conference turned into an exciting stream of news for the regular Joe, like yours truly. This time, Amazon Rekognition is announced, which is an image detection and recognition service,\u2026","rel":"","context":"In "All"","block_context":{"text":"All","link":"https:\/\/mamchenkov.net\/wordpress\/category\/general\/"},"img":{"alt_text":"rekognition-burger","src":"https:\/\/i0.wp.com\/mamchenkov.net\/wordpress\/wp-content\/uploads\/2016\/12\/rekognition-burger-500x243.png?resize=350%2C200&ssl=1","width":350,"height":200},"classes":[]},{"id":24717,"url":"https:\/\/mamchenkov.net\/wordpress\/2015\/09\/10\/free-data-science-books\/","url_meta":{"origin":29016,"position":1},"title":"Free Data Science Books","author":"Leonid Mamchenkov","date":"September 10, 2015","format":false,"excerpt":"I came across\u00a0a collection of free data science books: Pulled from the web, here is a great collection of eBooks (most of which have a physical version that you can purchase on Amazon) written on the topics of Data Science, Business Analytics, Data Mining, Big Data, Machine Learning, Algorithms, Data\u2026","rel":"","context":"In "All"","block_context":{"text":"All","link":"https:\/\/mamchenkov.net\/wordpress\/category\/general\/"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":25061,"url":"https:\/\/mamchenkov.net\/wordpress\/2015\/12\/17\/amazon-ec2-t2-nano-instances\/","url_meta":{"origin":29016,"position":2},"title":"Amazon EC2 t2.nano instances","author":"Leonid Mamchenkov","date":"December 17, 2015","format":false,"excerpt":"If you thought t2.micro was a tiny machine, I have news for you - Amazon announced t2.nano instance type. \u00a0It features 512 MB of RAM, 1 vCPU, and up to two Elastic network interfaces. \u00a0Price for on-demand instance - $0.0065 per hour. This instance type is perfect for small websites,\u2026","rel":"","context":"In "All"","block_context":{"text":"All","link":"https:\/\/mamchenkov.net\/wordpress\/category\/general\/"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":28928,"url":"https:\/\/mamchenkov.net\/wordpress\/2018\/11\/12\/awsome-day-athens-2018\/","url_meta":{"origin":29016,"position":3},"title":"AWSome Day Athens 2018","author":"Leonid Mamchenkov","date":"November 12, 2018","format":false,"excerpt":"Last week I've attended the AWSome Day Athens 2018\u00a0(huge thanks to Qobo for the opportunity).\u00a0 There aren't that many technology events in Cyprus, so I'm constantly on the lookout for events in Europe. AWSome Day Athens is part of the Amazon's AWSome Day Global Series, which are one day events\u2026","rel":"","context":"In "All"","block_context":{"text":"All","link":"https:\/\/mamchenkov.net\/wordpress\/category\/general\/"},"img":{"alt_text":"","src":"https:\/\/i0.wp.com\/mamchenkov.net\/wordpress\/wp-content\/uploads\/2018\/11\/AWSome-Day-Athens-430x500.png?resize=350%2C200&ssl=1","width":350,"height":200},"classes":[]},{"id":26860,"url":"https:\/\/mamchenkov.net\/wordpress\/2016\/11\/08\/install-ansible-2-0-on-amazon-ami\/","url_meta":{"origin":29016,"position":4},"title":"Install Ansible 2.0+ on Amazon AMI","author":"Leonid Mamchenkov","date":"November 8, 2016","format":false,"excerpt":"Today, while upgrading some of my Ansible roles I've hit the problem. \u00a0Some of the newer roles require Ansible 2.0. \u00a0My Amazon AMI machine that runs the playbooks was still on version 1.9. \u00a0EPEL repository doesn't seem to have the newer Ansible version yet. \u00a0Gladly, Google brough in this StackOverflow\u2026","rel":"","context":"In "All"","block_context":{"text":"All","link":"https:\/\/mamchenkov.net\/wordpress\/category\/general\/"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":34997,"url":"https:\/\/mamchenkov.net\/wordpress\/2019\/02\/18\/aws-cloudformation-sample-templates\/","url_meta":{"origin":29016,"position":5},"title":"AWS CloudFormation Sample Templates","author":"Leonid Mamchenkov","date":"February 18, 2019","format":false,"excerpt":"awslabs\/aws-cloudformation-templates is an extensive collection of Amazon AWS CloudFormation templates for a wide range of resources and services. Some of these can be used as is for deploying production infrastructure, others are good starting points for those of us who are still learning.","rel":"","context":"In "All"","block_context":{"text":"All","link":"https:\/\/mamchenkov.net\/wordpress\/category\/general\/"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]}],"jetpack_sharing_enabled":true,"amp_enabled":true,"_links":{"self":[{"href":"https:\/\/mamchenkov.net\/wordpress\/wp-json\/wp\/v2\/posts\/29016","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mamchenkov.net\/wordpress\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/mamchenkov.net\/wordpress\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/mamchenkov.net\/wordpress\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/mamchenkov.net\/wordpress\/wp-json\/wp\/v2\/comments?post=29016"}],"version-history":[{"count":0,"href":"https:\/\/mamchenkov.net\/wordpress\/wp-json\/wp\/v2\/posts\/29016\/revisions"}],"wp:attachment":[{"href":"https:\/\/mamchenkov.net\/wordpress\/wp-json\/wp\/v2\/media?parent=29016"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/mamchenkov.net\/wordpress\/wp-json\/wp\/v2\/categories?post=29016"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/mamchenkov.net\/wordpress\/wp-json\/wp\/v2\/tags?post=29016"},{"taxonomy":"keyring_services","embeddable":true,"href":"https:\/\/mamchenkov.net\/wordpress\/wp-json\/wp\/v2\/keyring_services?post=29016"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}