基于NVIDIA TX2的喷码字符检测算法

doi:10.3778/j.issn.1002-8331.2107-0317

摘要/Abstract

摘要： 针对复杂商品背景下喷码字符漏喷、重叠、缺失等现象，提出一种基于YOLOv5+CRNN的喷码字符检测算法。喷码字符定位算法以YOLOv5为基础网络，结合注意力机制提高其检测精度，再通过稀疏训练和通道剪枝降低模型参数量与复杂度，最终检测精度提高了3.4个百分点，模型参数量降低了6.7?MB。对定位后的字符区域进行背景擦除和透视变换处理后送入CRNN网络实现喷码字符识别，最终将改进后的算法部署至NVIDIA TX2嵌入式平台。通过在食品包装工厂生产流水线实测，检测速度达到28?frame/s，字符定位精度99.4%，识别率95%，且具有很好的鲁棒性。

关键词: YOLOv5算法, CRNN网络, 目标检测, 字符识别, 嵌入式, 模型量化

Abstract: Aiming at the phenomenon of spray leakage, re-spray, deficiency of inkjet characters under the background of complex commodities, an inkjet character detection algorithm based on YOLOv5+CRNN is proposed. The inkjet character positioning algorithm is based on YOLOv5, combined with the attention mechanism to improve its detection accuracy. Then, the number and complexity of model parameters are reduced through sparse training and channel pruning, so that the final detection accuracy is increased by 3.4?percentage points, and the amount of model parameters is reduced by 6.7?MB. After erasing background and perspective transformation, the positioned character area is send to the CRNN network to complete the recognition of inkjet character. Finally, the improved algorithm is deployed to the NVIDIA TX2 embedded platform. Through the actual measurement in the production lines of the food packaging factory, the testing speed of the model reaches 28?frame/s, the accuracy of character-localization is 99.4%, and the recognition rate is 95% with good robustness.

Key words: YOLOv5 algorithm, convolutional recurrent neual network（CRNN）, target detection, character recognition, embedded, model quantization

李帆, 胡维平, 刘北北, 刘雨戈. 基于NVIDIA TX2的喷码字符检测算法[J]. 计算机工程与应用, 2022, 58(13): 210-216.

LI Fan, HU Weiping, LIU Beibei, LIU Yuge. NVIDIA TX2-Based Inkjet Character Detection Algorithm[J]. Computer Engineering and Applications, 2022, 58(13): 210-216.

参考文献

[1] 袁先珍.食品包装日期喷码检测系统设计[J].包装工程，2020，41（5）：109-113.
YUAN X Z.Design of date printing detection system for food packaging[J].Packaging Engineering，2020，41（5）：109-113.
[2] 马玲，罗晓曙，蒋品群.基于模板匹配和支持向量机的点阵字符识别研究[J].计算机工程与应用，2020，56（4）：134-139.
MA L，LUO X S，JIANG P Q.Research on dot matrix character recognition based on template matching and support vector machine[J].Computer Engineering and Applications，2020，56（4）：134-139.
[3] 张成，戴俊峰，熊闻心.融合LeNet-5改进的扫描文档手写日期识别[J].计算机工程与应用，2021，57（9）：207-211.
ZHANG C，DAI J F，XIONG W X.Improved handwritten date recognition in scanned documents combined with LeNet-5[J].Computer Engineering and Applications，2021，57（9）：207-211.
[4] TIAN Z，HUANG W，HE T，et al.Detecting text in natural i-mage with connectionist text proposal network[C]//Proceedings of the European Conference on Computer Vision，2016：56-72.
[5] REDMON J，DIVVALA S，GIRSHICK R，et al.You only look once：Unified，real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2016：779-788.
[6] 唐博，史仪凯，王萑，等.啤酒瓶字符的圆周投影特征提取与识别[J].计算机工程与应用，2010，46（13）：229-232.
TANG B，SHI Y K，WANG H，et al.Beer bottle characters extraction and recognition method based on circular projection[J].Computer Engineering and Applications，2010，46（13）：229-232.
[7] SRIRAM A，JUN H，SATHEESH S，et al.Cold fusion：Training seq2seq models together with language models[J].arXiv：1708.06426，2017.
[8] ZHAO H，JIA J，KOLTUN V.Exploring self-attention for image recognition[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2020：10076-10085.
[9] HE P，HUANG W，QIAO Y，et al.Reading scene text in deep convolutional sequences[C]//Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence，2016.
[10] SHI B，BAI X，YAO C.An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2016，39（11）：2298-2304.
[11] HU J，SHEN L，SUN G.Squeeze-and-excitation networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：7132-7141.
[12] LI H，KADAV A，DURDANOVIC I，et al.Pruning filters for efficient convnets[J].arXiv：1608.08710，2016.
[13] LIU Z，LI J，SHEN Z，et al.Learning efficient convolutional networks through network slimming[C]//Proceedings of the IEEE International Conference on Computer Vision，2017：2736-2744.
[14] WANG Q，WU B，ZHU P，et al.ECA-Net：Efficient channel attention for deep convolutional neural networks[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR），2020.
[15] ZHENG Z，WANG P，LIU W，et al.Distance-IoU loss：Faster and better learning for bounding box regression[C]//Proceedings of the AAAI Conference on Artificial Intelligence，2020：12993-13000.
[16] LIU S，MOCANU D C，MATAVALAM A R R，et al.Sparse evolutionary deep learning with over one million artificial neurons on commodity hardware[J].Neural Computing and Applications，2021，33（7）：2589-2604.
[17] GRAVES A，FERNáNDEZ S，GOMEZ F，et al.Connectionist temporal classification：labelling unsegmented sequence data with recurrent neural networks[C]//Proceedings of the 23rd International Conference on Machine Learning，2006：369-376.
[18] LIU Y，CHEN H，SHEN C，et al.Abcnet：Real-time scene text spotting with adaptive bezier-curve network[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2020：9809-9818.
[19] LIU X，LIANG D，YAN S，et al.Fots：Fast oriented text spotting with a unified network[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：5676-5685.
[20] YAN H，HE Q，XIE W.CRNN-CTC based mandarin keywords spotting[C]//Proceedings of the IEEE International Conference on Acoustics，Speech and Signal Processing（ICASSP），2020：7489-7493.