{"id":442,"date":"2020-10-24T01:02:56","date_gmt":"2020-10-24T01:02:56","guid":{"rendered":"https:\/\/machine-learning.webcloning.com\/2020\/10\/24\/arcanum-makes-hungarian-heritage-accessible-with-amazon-rekognition\/"},"modified":"2020-10-24T01:02:56","modified_gmt":"2020-10-24T01:02:56","slug":"arcanum-makes-hungarian-heritage-accessible-with-amazon-rekognition","status":"publish","type":"post","link":"https:\/\/salarydistribution.com\/machine-learning\/2020\/10\/24\/arcanum-makes-hungarian-heritage-accessible-with-amazon-rekognition\/","title":{"rendered":"Arcanum makes Hungarian heritage accessible with Amazon Rekognition"},"content":{"rendered":"
\n

Arcanum<\/a> specializes in digitizing Hungarian language content, including newspapers, books, maps, and art. With over 30 years of experience, Arcanum serves more than 30,000 global subscribers with access to Hungarian culture, history, and heritage.<\/p>\n

Amazon Rekognition Solutions Architects worked with Arcanum to add highly scalable image analysis to Hungaricana<\/a>, a free service provided by Arcanum, which enables you to search and explore Hungarian cultural heritage, including 600,000 faces over 500,000 images. For example, you can find historical works by author M\u00f3r J\u00f3kai<\/a> or photos on topics like weddings<\/a>. The Arcanum team chose Amazon Rekognition<\/a> to free valuable staff from time and cost-intensive manual labeling, and improved label accuracy to make 200,000 previously unsearchable images (approximately 40% of image inventory), available to users.<\/p>\n

Amazon Rekognition makes it easy to add image and video analysis to your applications using highly scalable machine learning (ML) technology that requires no previous ML expertise to use. Amazon Rekognition also provides highly accurate facial recognition<\/a> and facial search<\/a> capabilities to detect, analyze, and compare faces.<\/p>\n

Arcanum uses this facial recognition feature in their image database services to help you find particular people in Arcanum\u2019s articles. This post discusses their challenges and why they chose Amazon Rekognition as their solution.<\/p>\n

Automated image labeling challenges<\/h2>\n

Arcanum dedicated a team of three people to start tagging and labeling content for Hungaricana. The team quickly learned that they would need to invest more than 3 months of time-consuming and repetitive human labor to provide accurate search capabilities to their customers. Considering the size of the team and scope of the existing project, Arcanum needed a better solution that would automate image and object labelling at scale.<\/p>\n

Automated image labeling solutions<\/h2>\n

To speed up and automate image labeling, Arcanum turned to Amazon Rekognition to enable users to search photos by keywords (for example, type of historic event, place name, or a person relevant to Hungarian history).<\/p>\n

For the Hungaricana project, preprocessing all the images was challenging. Arcanum ran a TensorFlow face search across all 28 million pages on a machine with 8 GPUs in their own offices to extract only faces from images.<\/p>\n

The following screenshot shows what an extract looks like (image provided by Arcanum Database Ltd).<\/p>\n

\"\"<\/p>\n

The images containing only faces are sent to Amazon Rekognition, invoking the IndexFaces<\/a> operation to add a face to the collection<\/a>. For each face that is detected in the specified face collection, Amazon Rekognition extracts facial features into a feature vector and stores it in an Amazon Aurora<\/a> database. Amazon Rekognition uses feature vectors when it performs face match and search operations using the SearchFaces<\/a> and SearchFacesByImage<\/a> operations.<\/p>\n

The image preprocessing helped create a very efficient and cost-effective way to index faces. The following diagram summarizes the preprocessing workflow.<\/p>\n

\"\"<\/p>\n

As for the web application, the workflow starts with a Hungaricana user making a face search request. The following diagram illustrates the application workflow.<\/p>\n

\"\"<\/p>\n

The workflow includes the following steps:<\/p>\n

    \n
  1. The user requests a facial match by uploading the image. The web request is automatically distributed by the Elastic Load Balancer<\/a> to the webserver fleet.<\/li>\n
  2. \nAmazon Elastic Compute Cloud<\/a> (Amazon EC2) powers application servers that handle the user request.<\/li>\n
  3. The uploaded image is stored in Amazon Simple Storage Service<\/a> (Amazon S3).<\/li>\n
  4. Amazon Rekognition indexes the face and runs SearchFaces<\/a> to look for a face similar to the new face ID.<\/li>\n
  5. The output of the search face by image operation is stored in Amazon ElastiCache<\/a>, a fully managed in-memory data store.<\/li>\n
  6. The metadata of the indexed faces are stored in an Aurora relational database built for the cloud.<\/li>\n
  7. The resulting face thumbnails are served to the customer via the fast content-delivery network (CDN) service Amazon CloudFront<\/a>.<\/li>\n<\/ol>\n

    Experimenting and live testing Hungaricana<\/h2>\n

    During our test of Hungaricana, the application performed extremely well. The searches not only correctly identified people, but also provided links to all publications and sources in Arcanum\u2019s privately owned database where found faces are present. For example, the following screenshot shows the result of the famous composer and pianist Franz Liszt<\/a>.<\/p>\n

    \"\"<\/p>\n

    The application provided 42 pages of 6\u00d74 results. The results are capped to 1,000. The 100% scores are the confidence scores returned by Amazon Rekognition and are rounded up to whole numbers.<\/p>\n

    The application of Hungaricana has always promptly, and with a high degree of certainty, presented results and links to all corresponding publications.<\/p>\n

    Business results<\/h2>\n

    By introducing Amazon Rekognition into their workflow, Arcanum enabled a better customer experience, including building family trees, searching for historical figures, and researching historical places and events.<\/p>\n

    The concept of face searching using artificial intelligence certainly isn\u2019t new. But Hungaricana uses it in a very creative, unique way.<\/p>\n

    Amazon Rekognition allowed Arcanum to realize three distinct advantages:<\/p>\n