Product and Shelf Recognizer Model

AI Data Capture SDK

Overview

Model Name: product-and-shelf-recognizer

Product recognition is used to detect and recognize products located on retail shelf images, as well as detect other classes including shelf labels, peg labels, and shelves. It is capable of recognizing the products using the previously prepared index. The index must be generated with the same model version from the set of cropped product images with their labels.​

This bundle comprises of product and shelf localizer and product recognizer.​


New in v3.4.2

  • Improves detection for the cosmetic product category.

Requirements

  • Operating System: Android 14 or higher. For specific OS versions, refer to AI Data Capture SDK Release Notes from the Zebra support portal.

  • Minimum SDK Version: AI Data Capture SDK v3.0.2 or later.

  • Supported Zebra Devices:

    Features Platform Device Model
    Products with DSP
    Fastest and most battery efficient
    QC6490 TC53, TC58, TC73, TC78, ET60, ET65
    QC5430 EM45
    Products without DSP
    Applies to still images
    QC4490 TC53e, TC58e, MC9400, MC9450

    For more information on devices based on platform, see Zebra Platform Devices.


Technical Details

  • Input Resolutions Recommended:
    • 640x640
    • 832x832
    • 1280x1280
    • 1600x1600​ (Localizer only)​

Note: Any other resolutions chosen will result in higher model load times.

Note: Exceeding these recommended input resolutions may result in increased model load times.​


Resources