About AI Data Capture SDK

AI Data Capture SDK 2.22

Overview

The Zebra AI Data Capture SDK enables Java developers to create and deploy computer vision applications on Zebra mobile computing devices. Designed for both seasoned AI professionals and beginners, the SDK offers the tools and resources to leverage the AI capabilities offered on Zebra devices.

SDK capabilities:

  • Localizer - Detects objects in images:
    • Barcode Localizer - Locates the barcodes within an image for decode.
    • Shelf and Product Localizer - Finds products, shelves, price labels, and shelf labels within an image.
  • Product Recognition - Utilizes Feature Extractor, Feature Storage and Recognizer components to build and store detailed visual data about retail products, enhancing inventory management. This process typically follows the use of Shelf Localizer, which detects products in images, crops them and submits them for recognition.
  • Barcode Decoder - Decodes single and multiple barcodes within images, generally after the Barcode Localizer detects and crops them for recognition.
  • Text OCR - Detects and recognizes text characters in images, capturing them as words or paragraphs.

New in v2.22.10

Localizer

Localizer detects objects in images using supported models and outputs the location of the detected objects.

  • Barcode Localizer - Detects 1D and 2D barcodes in images, suitable for various use cases such as identifying barcodes on product boxes, shelves and shipping labels.

    image

    Sample of detected barcodes

  • Shelf and Product Localizer Detects and identifies objects on retail shelves, aiding inventory management, optimizing space and ensuring accurate labeling. The types of objects detected include:

    • Products - Identifies individual products on the shelf, facilitating inventory tracking and automating stock checks.
    • Shelf Labels - Detects and reads shelf labels, ensuring that products are accurately priced and labeled.
    • Peg Labels - Recognizes peg labels used for hanging products, aiding in efficient product organization.
    • Shelves - Detects the presence and structure of shelves themselves, helping in understanding shelf layouts and optimizing space usage.

    image

    Sample of objects detected on a retail shelf

Product Recognition

Product Recognition builds a database to facilitate inventory tracking and automated checkouts. The Feature Extractor isolates key features from images, generating descriptors - vectors of float values that capture an item's characteristics - and stores them in Feature Storage to enable product recognition. After a database of recognizable products is established, the Product Recognizer performs semantic searches to locate matching descriptors, predicting the identities of products on the shelf.

image        image
         Sample of extracted item                 Sample of items recognized in the image and displayed with their corresponding data


Barcode Decoder

The Barcode Decoder decodes various types of barcodes detected within images, using the Barcode Localizer to first identify barcode locations, and then decoding from entire images or specific regions, handling both single and multiple barcodes per image.

Text OCR

The Text OCR model detects and decodes text characters in images, offering suggestions for recognized characters or words. It adapts to various fonts and input sizes, allowing for effective text recognition at different distances. Detected words can be grouped into 'lines' or 'paragraphs.'

image

            Sample of OCR detection

Sample App

Refer to the AISuite Sample Application, which showcases all the features of the AI Data Capture SDK within a single app.