多分支轻量级残差网络的手写字符识别方法

doi:10.3778/j.issn.1002-8331.2109-0237

摘要/Abstract

摘要： 由于手写数字容易出现粘连现象，影响了此类字符的分割和识别精度；另一方面，深度学习模型通常计算复杂度较高，导致其无法在资源受限的设备上高效运行。针对上述问题，提出一种多分支轻量级残差网络的手写字符识别方法。针对字符粘连问题制作了90类复合数字，将其与MNIST和7种算术符号混合作为实验数据集。将ResNet残差结构和注意力机制融合，借用Inception思想，采用多分支结构，提高网络的特征学习能力，并将网络通过知识蒸馏来学习深度神经网络ResNet。在对107类手写字符数据集上的实验证明，该方法能达到深度网络的高精度，同时模型复杂度大大降低，实现在树莓派等低配置终端上的高精度识别效果。

关键词: 手写字符识别, 残差结构, 注意力机制, ResNet, 知识蒸馏

Abstract: Handwritten numerals are prone to adhesion, which affects the precision of segmentation and recognition. On the other hand, deep learning models usually have high computational complexity, which makes them unable to run efficiently on resource constrained devices. For the above problems, a handwritten character identification method of a multi-branch lightweight residual network is proposed. A 90-class composite number is made for character adhesion, and it is mixed with MNIST and 7 arithmetic symbols as experimental data sets. It fuses ResNet residual structure and attention mechanism, borrows Inception thinking, uses multi-branch structure, which improves the network’s characteristic learning capabilities, and learns the deep neural network ResNet through knowledge distillation. Experiments on 107 types of handwritten character data sets prove that this method can achieve the high precision of deep networks, and the model complexity is greatly reduced, and the high precision recognition effect on the low configuration terminal of the Raspberry Pi.

Key words: handwritten character recognition, residual structure, attention mechanism, ResNet, knowledge distillation

黎光艳, 王修晖. 多分支轻量级残差网络的手写字符识别方法[J]. 计算机工程与应用, 2023, 59(5): 115-121.

LI Guangyan, WANG Xiuhui. Handwritten Character Recognition Method Based on Multi-Branch Lightweight Residual Network[J]. Computer Engineering and Applications, 2023, 59(5): 115-121.

参考文献

[1] LI Q，CAO H，YAN H，et al.High speed homework data collecting system under K-12 education circumstance[C]//International Symposium on System & Software Relia-bility，2017.
[2] 姚红革，董泽浩，喻钧，等.深度EM胶囊网络全重叠手写数字识别与分离[J].自动化学报，2022，48（12）：2996-3005.
YAO Hongge，DONG Zehao，YU Jun，et al.Fully overlapped handwritten number recognition and separation based on deep EM capsule network[J].Acta Automatica Sinica，2022，48（12）：2996-3005.
[3] GOODFELLOW I J，WARDE-FARLEY D，MIRZA M，et al.Maxout networks[C]//The 30th International Conference on Machine Learning，2013：1319-1327.
[4] HE K，ZHANG X，REN S，et al.Delving deep into rectifiers：surpassing human-level performance on imagenet classification[C]//Proceedings of the IEEE International Conference on Computer Vision，2015：1026-1034.
[5] MA C，HONG Z.Effective handwritten digit recognition based on multi-feature extraction and deep analysis[C]//International Conference on Fuzzy Systems & Knowledge Discovery，2016.
[6] IGNAT A，ACIOBANITEI B.Handwritten digit recognition using rotations[C]//2016 18th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing（SYNASC），2016.
[7] SRIVASTAVA S，YADAV S，AGRAWALLA K，et al.Recognition of handwritten digits using computer vision preprocessor based combined architecture of self-organizing map and backpropagation on MNIST dataset[C]//2018 International Conference on Recent Innovations in Electrical，Electronics & Communication Engineering（ICRIEECE），2018.
[8] NYIDE O，GWERU M V.Handwritten digit classification using Iterative haar-like operators and neural networks[C]//2019 International Conference on Advances in Big Data，Computing and Data Communication Systems（icABCD），2019.
[9] URAZOE K，KUROKI N，HIROSE T，et al.Combination of convolutional neural network architecture and its learning method for rotation‐invariant handwritten digit recognition[J].IEEJ Transactions on Electrical and Electronic Engineering，2020，16（1）：161-163.
[10] BUCILUA C，CARUANA R，NICULESCU-MIZIL A.Model compression[C]//Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining，New York，USA，2006：535-541.
[11] ZOPH B，VASUDEVAN V，SHLENS J，et al.Learning transferable architectures for scalable image recognition[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR），2018.
[12] HOWARD A G，ZHU M，CHEN B，et al.MobileNets：efficient convolutional neural networks for mobile vision applications[J].arXiv：1704.04861，2017.
[13] ROMERO A，BALLAS N，KAHOU S E，et al.FitNets：hints for thin deep nets[J].arXiv：1412.6550，2014.
[14] REN S Q，HE K M，GIRSHICK R，et al.Faster R-CNN：towards real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis & Machine Intelligence，2015，39（6）：1137-1149.
[15] HE K M，ZHANG X Y，REN S Q，et al.Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition（CVPR），Las Vegas，USA，2016：770-778.
[16] 周飞燕，金林鹏，董军.卷积神经网络研究综述[J].计算机学报，2017，40（6）：1229-1251.
ZHOU F Y，JIN L P，DONG J.Review of convolutional neural network[J].Chinese Journal of Computers，2017，40（6）：1229-1251.
[17] 张顺，龚怡宏，王进军.深度卷积神经网络的发展及其在计算机视觉领域的应用[J].计算机学报，2019，42（3）：3-32.
ZHANG S，GONG Y H，WANG J J.The development of deep convolution neural network and its applications on computer vision [J].Chinese Journal of Computers，2019，42（3）：3-32.
[18] GIRSHICK R，DONAHUE J，DARRELL T，et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，Columbus，USA，2014：580-587.
[19] GIRSHICK R.Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision，Santiago，Chile，2015：1440-1448.
[20] 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，Las Vegas，USA，2016：779-788.
[21] LIU W，ANGUELOV D，ERHAN D，et al.SSD：single shot multibox detector[C]//European Conference on Computer Vision，Amsterdam，Holland，2016：21-37.
[22] SIMONYAN K，ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[J].arXiv：1409.1556，2014.
[23] 赖轩，曲延云，谢源，等.基于拓扑一致性对抗互学习的知识蒸馏[J].自动化学报，2023，49（1）：102-110.
LAI Xuan，QU Yanyun，XIE Yuan，et al.Topology-guided adversarial deep mutual learning for knowledge distillation[J].Acta Automatica Sinica，2023，49（1）：102-110.
[24] URBAN G，GERAS K J，KAHOU S E，et al.Do deep convolutional nets really need to be deep and convolutional?[J].arXiv：1603.05691，2016.
[25] HINTON G，VINYALS O，DEAN J.Distilling the knowledge in a neural network[J].arXiv：1503.02531，2015.
[26] SZEGEDY C，VANHOUCKE V，IOFFE S，et al.Rethinking the inception architecture for computer vision[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition（CVPR），2016：2818-2826.
[27] HE K，ZHANG X，REN S，et al.Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition（CVPR），2016.