Fast, Accurate Barcode Detection in Ultra High-Resolution Images
University of California, Berkeley(加州大学伯克利分校)
Jerome Quenum, Kehan Wang, Avideh Zakhor
备注:
5 pages, 4 figures, 3 tables, GitHub Link added, Initial ArXiv Submission is 13 Feb 2021, Accepted at IEEE International Conference on Image Processing, September 2021, USA
发表信息:
2021 IEEE International Conference on Image Processing (ICIP)
超高分辨率(UHR)图像中的目标检测目标检测由于目标的尺度变化而长期以来一直是计算机视觉中具有挑战性的问题。当涉及到条形码检测时,将UHR输入图像缩小到更小的尺寸通常会导致相关信息的丢失,而直接处理它们是非常低效和计算昂贵的。在本文中,我们提出使用语义分割,以实现一个快速和准确的检测条码的各种尺度的超高频图像。我们的管道涉及修改后的区域建议网络(RPN)的图像大小大于10 k $\times$ 10 k和一个新提出的Y-Net分割网络,其次是后处理工作流程,以适应每个分割的条形码掩码周围的限界框。端到端系统的延迟为16毫秒,比YOLOv 4快$2.5\times$,比Mask R-CNN快$5.9\times$。在准确性方面,我们的方法在合成数据集上的$mAP$分别比YOLOv 4和Mask R-CNN高出5.5%和47.1%。我们已经在http://www.github.com/viplabB/SBD/上提供了生成的合成条形码数据集及其代码。
英文摘要:
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/.
Universal Barcode Detector via Semantic Segmentation
ABBYY Production LLC(ABBYY 产品有限责任公司);Moscow Institute of Physics and Technology (National Research University)(莫斯科物理技术学院(国立研究大学))
条形码用于许多商业应用中,因此快速和可靠的读取非常重要。有许多不同类型的条形码,其中一些看起来相似,而另一些则完全不同。本文介绍了一种基于语义分割方法的快速、鲁棒的深度学习检测器。它能够通过单个模型在文档扫描和野外同时检测任何类型的条形码。该检测器在ArTe-Lab 1D Medium Barcode Dataset上实现了最先进的结果,检测率为0.995。此外,开发的探测器可以处理更复杂的物体形状,如很长但很窄或很小的条形码。所提出的方法还可以识别检测到的条形码的类型,并在CPU环境下以比以前的最先进的方法快得多的实时速度执行。