AICR (AI Character Recognition)

Automatically Extract Text and Data from Documents

AICR is a service that extracts data from images using deep learning-based image recognition technology. It employs OCR (Optical Character Recognition) technology and patented AI deep-learning technology for character conversion, document classification, and data detection, delivering top-tier accuracy. In addition, by integrating with object storage on the Samsung Cloud Platform, target images for analysis and findings are stored securely.

Overview

  • Highest Word Recognition Rate

    Samsung SDS image pre-processing technologies and text recognition algorithms help eliminate any distractions in images such as rotation, noise, and watermark, guaranteeing the highest text recognition accuracy in the industry. Accurate character recognition is available in 97 languages irrespective of the type and quality of documents.

  • Accurate Analysis of Document Structure

    A deep learning-based image analysis model with a digital image processing algorithm provides findings after identifying sentence structures such as sentences, tables, images, and non-character columns and distinguishing tables from key-value.

  • Invoice Analysis

    AICR provides analysis for not only general documents but also receipts and logistics documents (invoices, bills of landing, etc.). Clearly distinguishing sentences, tables, and key values from invoices and extracting data promote efficiency in financial tasks.

  • Easy Data Integration

    Data can easily be integrated with the application using the AICR-extracted data through API calls. Uploading target images for analysis and storing findings are done easily using Object Storage on the Samsung Cloud Platform.

01

04

Service Architecture

  • User → Apply for service & Issue OpenAPI key → AICR
  • AI Utilization System/ML Development Environment → API call/response using a previously-issued key → AICR
AICR
  • SCP Console: Manage Authentication Key, Apply for Service, Demo, View Usage, Object Storage
  • AICR Management: API Endpoint, Monitoring/Metering
  • AICR Engine: Word recognition, Document structure recognition, Document conversion, Keyword extraction

Key Features

  • Extract text by image type using the API call

    - Types of Image : Document, invoice
    - Types of extracted data
      · Text : Extract text and location
      · Table : Extract text and location of each cell by distinguishing table structure
      · Format : Extract data in key-value by distinguishing document format
    - Supported languages for character recognition : 7 language family, 97 languages (Korean, 56 in Latin, 11 in Cyrillic, 25 in Arabic, 2 in Chinese, Japanese, and Thai)

  • Provide demo

    - AICR functional/performance testing through Demo
    - Demo limitations : Use JPG, PNG, PDF format, no bigger than 10MB, one page

  • Limitations

    - Image format : JPEG, PNG, PDF
    - Maximum capacity and page limit
      · Console demo and synchronous API : 10MB, 1 page
      · Asynchronous API : Image file (JPEG, PNG) 10MB, PDF file 50MB/150 pages

  • View API call status

    - View call status by API and by day/week/month
    - View the number of calls by API (All/success/error)
    - View response time for successful API

Pricing

    • Billing
    • Billed by page depending on the type of image and extracted data
Let’s talk

Whether you’re looking for a specific business solution or just need some questions answered, we’re here to help

Get in Touch
Share