首页|Text Recognition of Barcode Images under Harsh Lighting Conditions

Text Recognition of Barcode Images under Harsh Lighting Conditions

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
  • 维普
The inventory counting of silver ingots plays a key role in silver futures.However,the manual inventory counting is time-consuming and labor-intensive.Furthermore,the silver ingots are stored in warehouses with harsh lighting conditions,which makes the automatic inventory counting difficult.To meet the challenge,we propose an automatic inventory counting method integrating object detection and text recognition under harsh lighting conditions.With the help of our own dataset,the barcode on each silver ingot is detected and cropped by the feature pyra-mid network(FPN).The cropped image is normalized and cor-rected for text recognition.We use the PSENet+CRNN(Progres-sive Scale Expansion Network,Convolutional Recurrent Neural Network)for text detection and recognition to obtain the serial number of the silver ingot image.Experimental results show that the proposed automatic inventory counting method achieves good results since the accuracy of the proposed object detection and text recognition under harsh lighting conditions is near 99％.

barcodeobject detectiontext recognitiondeep learning

WU Xing、GE Yuxi、ZHANG Qingfeng、CHEN Liming

展开 >

School of Computer Engineering and Science,Shanghai University,Shanghai 200444,China

Shanghai Institute for Advanced Communication and Data Science,Shanghai University,Shanghai 200444,China

CAC Supply Chain Management Company,Beijing 100016,China

Supported by the National Key R&D Program of ChinaState Key Program of National Nature Science Foundation of Chinaand the Natural Science Foundation of Shanghai

2019YFE01905006193600120ZR1420400

2020

10.19823/j.cnki.1007-1202.2020.0068

武汉大学自然科学学报(英文版)
武汉大学

武汉大学自然科学学报(英文版)

CSTPCDCSCD
影响因子：0.066
ISSN：1007-1202
年,卷(期)：2020.25(6)
  • 1
  • 22