Barcode Detection Reference Design

Implements Camera Barcode Detection Capabilities Based on Yolov5 NN Models

Barcode detection and reading is an application typically ran using an accelerated industrial PC running a mix of traditional and AI/ML based algorithms. As designers look to reduce the cost of deployment, cameras with built-in barcode reading capabilities enable simpler implementation of the application.

This reference design demonstrates the barcode detection using the CertusPro-NX Voice and Vision Machine Learning Board that implements camera barcode detection capabilities based on Yolov5 NN models.

Features

  • Detection, image quality improvement and reading in a single design
  • Low latency design based on the parallel compute capabilities of the CertusPro-NX FPGA
  • Image resolution input of 640 x 480, cropped and downscaled to 160 x 120 for processing
  • Detection results overlayed within the FPGA on top of the input image
  • Uses Yolov5 style network for improved accuracy in small footprint

Block Diagram

Machine Vision Barcode Detection Block Diagram

Documentation

Technical Resources
TITLE NUMBER VERSION DATE FORMAT SIZE
Select All
Barcode Detection Reference Design - Source Code
12/5/2023 ZIP 821 MB
Barcode Detection Reference Design - User Guide
FPGA-RD-02280 1.0 12/5/2023 PDF 5.4 MB

*By clicking on the "Notify Me of Changes" button, you agree to receive notifications on changes to the document(s) you selected.