Fast, Accurate Barcode Detection in Ultra High-Resolution Images

TL;DR

This paper introduces a semantic segmentation approach for fast and accurate barcode detection in ultra high-resolution images, significantly outperforming existing methods in speed and accuracy.

Contribution

The paper presents a novel pipeline combining a modified RPN and a new Y-Net segmentation network for efficient barcode detection in UHR images.

Findings

End-to-end system latency of 16 ms, 2.5x faster than YOLOv4.

Outperforms YOLOv4 and Mask R-CNN in accuracy on synthetic dataset.

Provides synthetic barcode dataset and code for research use.

Abstract

Object detection in Ultra High-Resolution (UHR) images has long been a challenging problem in computer vision due to the varying scales of the targeted objects. When it comes to barcode detection, resizing UHR input images to smaller sizes often leads to the loss of pertinent information, while processing them directly is highly inefficient and computationally expensive. In this paper, we propose using semantic segmentation to achieve a fast and accurate detection of barcodes of various scales in UHR images. Our pipeline involves a modified Region Proposal Network (RPN) on images of size greater than 10k$\times$10k and a newly proposed Y-Net segmentation network, followed by a post-processing workflow for fitting a bounding box around each segmented barcode mask. The end-to-end system has a latency of 16 milliseconds, which is $2.5\times$ faster than YOLOv4 and $5.9\times$ faster than Mask R-CNN. In terms of accuracy, our method outperforms YOLOv4 and Mask R-CNN by a $mAP$ of 5.5% and 47.1% respectively, on a synthetic dataset. We have made available the generated synthetic barcode dataset and its code at http://www.github.com/viplabB/SBD/.