Product and Shelf Recognizer Model

AI Data Capture SDK 4.0

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.​

Note: Zebra strongly recommends updating to the latest models.

Version History

New in v3.4.4

  • Updated configurations for compatibility with the latest SDK version.

New in v3.4.3

  • Added support for Q-6690 device platform.

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 v4.0.0 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
    Q-6690 ET401, TC501, TC701
    Products without DSP
    Applies to still images     		QC4490 TC53e, TC58e, MC9400, MC9450

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

  • Memory Requirements: Since running multiple on-device models concurrently is highly resource-intensive, using multiple models within the AI Data Capture SDK is recommended for high-memory devices only.

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