{"id":74362,"date":"2026-03-02T11:33:15","date_gmt":"2026-03-02T11:33:15","guid":{"rendered":"https:\/\/www.cloudthat.com\/resources\/?post_type=resources&#038;p=74362"},"modified":"2026-03-02T11:33:15","modified_gmt":"2026-03-02T11:33:15","slug":"building-a-scalable-smart-cart-system-with-90-95-ocr-accuracy-using-aws-and-amazon-bedrock-for-an-it-consulting-firm","status":"publish","type":"resources","link":"https:\/\/www.cloudthat.com\/resources\/case-study\/building-a-scalable-smart-cart-system-with-90-95-ocr-accuracy-using-aws-and-amazon-bedrock-for-an-it-consulting-firm","title":{"rendered":"Building a Scalable Smart Cart System with 90-95% OCR Accuracy Using AWS and Amazon Bedrock for an IT Consulting Firm"},"content":{"rendered":"<p>The client is a software company established in 2017 that solves supply-chain and retail operation challenges using AI and mobile edge computing solutions. Recognized under DPIIT&#8217;s Startup India program, their platform supports inventory, payments, operations, and reporting, serving over 5 lakh businesses to streamline operations and reduce manual effort.<\/p>\n","protected":false},"author":325,"featured_media":74363,"parent":0,"template":"","cat_resources":[6],"technology":[32],"published_by":"325","primary-authors":["9638","633","292"],"secondary-authors":["325"],"acf":{"banner_image":74364,"resources_label":"","download_url":"https:\/\/content.cloudthat.com\/resources\/wp-content\/uploads\/2026\/03\/Smaket_Short_Form_Case_Study.pdf","client_logo":"","highlights":{"first_part":{"icon":336,"title":"98%","subtitle":"Product Identification Accuracy"},"second_part":{"icon":335,"title":"90-95%","subtitle":"OCR Accuracy "},"third_part":{"icon":334,"title":"Enhanced Accuracy ","subtitle":"Rule-Based Billing Validation"}},"the_challenge":"The client needed highly accurate product recognition for smart carts despite inconsistent camera angles, lighting conditions, and packaging variations. The system required multi-image validation, real-time OCR and weight verification with \u00b110g tolerance, duplicate prevention to avoid race conditions, low-latency billing updates during shopping, and scalable data ingestion from field devices without disrupting the shopping experience.","client_testimonial":{"image":"","description":"","author":""},"solutions":"\u2022 Field devices upload images to S3 and weight\/session data to IoT Core (MQTT)\r\n\u2022 Amazon S3 triggers Amazon SQS, which invokes Lambda for controlled parallel processing\r\n\u2022 Lambda preprocesses images and uses Bedrock Claude 3.5 Sonnet for OCR and label extraction\r\n\u2022 OCR results sent to Amazon EC2 FastAPI, which uses Claude 3 Haiku + Bedrock Knowledge Base + Titan Embeddings for product identification and SQL generation\r\n\u2022 Product validated using cart weight from Amazon DynamoDB; bill updated in Amazon DynamoDB\r\n\u2022 Mismatches trigger IoT drop alerts back to the device","the_results":"Delivered a GenAI smart cart pipeline achieving 98% product identification, 90-95% OCR accuracy, and enhanced billing precision through rule-based validation.","about_client_left_side":[{"field_63315a4dc06e1":"15085","field_63315a5bc06e2":"Industry\u00a0","field_63315a61c06e3":"IT Services and IT Consulting "},{"field_63315a4dc06e1":"15083","field_63315a5bc06e2":"Expertise\u00a0","field_63315a61c06e3":"AWS Lambda, AWS IoT Core, Amazon API Gateway, Amazon SQS, Amazon S3, Amazon DynamoDB, Amazon Bedrock"},{"field_63315a4dc06e1":"15084","field_63315a5bc06e2":"Offerings\/solutions\u00a0","field_63315a61c06e3":"Built a GenAI smart cart pipeline achieving 98% product identification and 90-95% OCR accuracy on AWS"}]},"_links":{"self":[{"href":"https:\/\/www.cloudthat.com\/resources\/wp-json\/wp\/v2\/resources\/74362"}],"collection":[{"href":"https:\/\/www.cloudthat.com\/resources\/wp-json\/wp\/v2\/resources"}],"about":[{"href":"https:\/\/www.cloudthat.com\/resources\/wp-json\/wp\/v2\/types\/resources"}],"author":[{"embeddable":true,"href":"https:\/\/www.cloudthat.com\/resources\/wp-json\/wp\/v2\/users\/325"}],"version-history":[{"count":2,"href":"https:\/\/www.cloudthat.com\/resources\/wp-json\/wp\/v2\/resources\/74362\/revisions"}],"predecessor-version":[{"id":74367,"href":"https:\/\/www.cloudthat.com\/resources\/wp-json\/wp\/v2\/resources\/74362\/revisions\/74367"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.cloudthat.com\/resources\/wp-json\/wp\/v2\/media\/74363"}],"wp:attachment":[{"href":"https:\/\/www.cloudthat.com\/resources\/wp-json\/wp\/v2\/media?parent=74362"}],"wp:term":[{"taxonomy":"cat_resources","embeddable":true,"href":"https:\/\/www.cloudthat.com\/resources\/wp-json\/wp\/v2\/cat_resources?post=74362"},{"taxonomy":"technology","embeddable":true,"href":"https:\/\/www.cloudthat.com\/resources\/wp-json\/wp\/v2\/technology?post=74362"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}