[1]骆彦龙,毕晓君,吴立成,等.基于改进残差学习的东巴象形文字识别[J].智能系统学报,2022,17(1):79-87.[doi:10.11992/tis.202112009]
LUO Yanlong,BI Xiaojun,WU Licheng,et al.Dongba pictographs recognition based on improved residual learning[J].CAAI Transactions on Intelligent Systems,2022,17(1):79-87.[doi:10.11992/tis.202112009]
点击复制
LUO Yanlong,BI Xiaojun,WU Licheng,et al.Dongba pictographs recognition based on improved residual learning[J].CAAI Transactions on Intelligent Systems,2022,17(1):79-87.[doi:10.11992/tis.202112009]
基于改进残差学习的东巴象形文字识别
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
17
期数:
2022年第1期
页码:
79-87
栏目:
学术论文—智能系统
出版日期:
2022-01-05
- Title:
- Dongba pictographs recognition based on improved residual learning
- Keywords:
- deep learning; Dongba pictographs; image recognition; build dataset; ResNet model; residual shortcut connection; improved down-sampling; recognition accuracy
- 分类号:
- TP18
- 摘要:
-
基于深度学习模型的东巴象形文字识别效果明显优于传统算法，但目前仍存在识别字数少、识别准确率低等问题。为此本文建立了包含
1387 个东巴象形文字、图片总量达到22万余张的数据集，大幅度增加了可识别字数，并辅助提高了东巴象形文字的识别准确率。同时，本文根据东巴象形文字相似度高、手写随意性大的特点，选择ResNet模型作为改进的网络结构，设计了残差跳跃连接方式和卷积层的数量，并通过加入最大池化层实现了下采样的改进。实验结果表明，在本文建立的东巴象形文字数据集上，改进的ResNet模型实现了东巴象形文字识别字数多且识别准确率高的最好效果，识别准确率可达到98.65%。
- Abstract:
- Dongba pictographs recognition based on deep learning model has better recognition effect than that of traditional algorithms. However, these methods have disadvantages such as small number of recognizable Dongba pictographs and low recognition accuracy. Aiming at these problems, in this study, we build a novel dataset of Dongba pictographs that contains 1387 Dongba pictographs and more than 220 thousand images. Therefore, the number of recognizable Dongba pictographs is greatly increased and the Dongba pictographs recognition accuracy is improved. Since Dongba pictographs are characterized by high similarity and random writing, ResNet is adopted as an improved network structure. Moreover, we design a residual shortcut connection and the number of convolutional layers and introduce the max-pooling into the ResNet to improve down-sampling. The experimental results demonstrate that the improved ResNet model can recognize more Dongba characters, and has achieved the highest recognition accuracy 98.65% in our dataset.
- 参考文献/References:
-
[1] GUO Hai, ZHAO Jingying, LI Xiaoniu. Preprocessing method for NaXi pictographs character recognition using wavelet transform[J]. International journal of digital content technology and its applications, 2010, 4(3): 117–131.
[2] GUO Hai, ZHAO Jingying. Research on feature extraction for character recognition of NaXi pictograph[J]. Journal of computers, 2011, 6(5): 947–954.
[3] DA Mingjun, ZHAO Jingying, SUO Guojie, et al. Online handwritten Naxi pictograph digits recognition system using coarse grid[C]//Computer science for environmental engineering and EcoInformatics. Berlin, German: Springer, 2011: 390?396.
[4] HSU C W, LIN C J. A comparison of methods for multiclass support vector machines[J]. IEEE transactions on neural networks, 2002, 13(2): 415–425.
[5] BREIMAN L. Random forests[J]. Machine learning, 2001, 45(1): 5–32.
[6] 徐小力, 蒋章雷, 吴国新, 等. 基于拓扑特征和投影法的东巴象形文识别方法研究[J]. 电子测量与仪器学报, 2017, 31(1): 150–154
XU Xiaoli, JIANG Zhanglei, WU Guoxin, et al. Identification method of Dongba pictograph based on topological characteristic and projection method[J]. Journal of electronic measurement and instrumentation, 2017, 31(1): 150–154
[7] 杨玉婷, 康厚良. 东巴象形文字特征曲线提取算法研究[J]. 图学学报, 2019, 40(3): 591–599
YANG Yuting, KANG Houliang. Research on the extracting algorithm of dongba hieroglyphic feature curves[J]. Journal of graphics, 2019, 40(3): 591–599
[8] 张泽晖. 基于卷积神经网络的东巴文字分类与识别[D]. 昆明: 云南大学, 2019.
ZHANG Zehui. Classification and recognition of dongba characters based on convolutional neural network[D]. Kunming: Yunnan University, 2019.
[9] WU Guoxin, LIU Xiuli, JIANG Zhanglei, et al. Dongba classical ancient books image classification method based on ReN-Softplus convolution residual neural network[C]//2019 14th IEEE International Conference on Electronic Measurement & Instruments. New York, USA: IEEE, 2019: 398?404.
[10] 谢裕睿, 董建娥. 基于ResNet网络的东巴象形文字识别研究[J]. 计算机时代, 2021(1): 6–10
XIE Yurui, DONG Jian’e. Research on Dongba hieroglyph recognition using ResNet network[J]. Computer era, 2021(1): 6–10
[11] 李霖灿. 纳西族象形标音文字字典[M]. 昆明: 云南民族出版社, 2001.
LI Lincan. Naxi Pictographs and Transcription Characters Dictionary[M]. Kunming: Yunnan Nationalities Publishing House, 2001.
[12] 方国瑜, 和志武. 纳西象形文字谱[M]. 昆明: 云南人民出版社, 1981.
FANG Guoyu, HE Zhiwu. Naxi pictograph character chart[M]. Kunming: Yunnan People’s Publishing House, 1981.
[13] BUSLAEV A, PARINOV A, KHVEDCHENYA E, et al. Albumentations: fast and flexible image augmentations[EB/OL]. (2018-09-18) [2021-11-30].https://arxiv.org/abs/1809.06839.
[14] ZHANG Hongyi, MOUSTAPHA Cisseet, YANN N Dauphin, et al. Mixup: beyond empirical risk minimization[EB/OL]. (2017-10-25) [2021-11-30].https://arxiv.org/abs/1710.09412.
[15] DAN Hendrycks, NORMAN Mu, EKIN D Cubuk, et al. AugMix: A simple data processing method to improve robustness and uncertainty[EB/OL]. (2019-12-05) [2021-11-30].https://arxiv.org/abs/1912.02781.
[16] HE Tong, ZHANG Zhi, ZHANG Hang, et al. Bag of tricks for image classification with convolutional neural networks[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE, 2019: 558?567.
[17] KHAN A, SOHAIL A, ZAHOORA U, et al. A survey of the recent architectures of deep convolutional neural networks[J]. Artificial intelligence review, 2020, 53(8): 5455–5516.
[18] XIE Saining, GIRSHICK R, DOLLáR P, et al. Aggregated residual transformations for deep neural networks[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE, 2017: 5987?5995.
[19] TAN Mingxing, LE Quoc V. EfficientNet: rethinking model scaling for convolutional neural networks[EB/OL]. (2019-05-28) [2021-11-30].https://arxiv.org/abs/1905.11946.
[20] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE, 2016: 770?778.
[21] LIN Min, CHEN Qiang, YAN Shuicheng. Network in network[EB/OL]. (2013-12-16) [2021-11-30].https://arxiv.org/abs/1312.4400.
[22] HUANG Gao, LIU Shichen, MAATEN L V D, et al. CondenseNet: an efficient DenseNet using learned group convolutions[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE, 2018: 2752?2761.
[23] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[EB/OL]. (2014-09-04) [2021-11-30].https://arxiv.org/abs/1409.1556v3.
[24] IOFFE Sergey, SZEGEDY Christian. Batch normalization: accelerating deep network training by reducing internal covariate shift [C]//2015 International Conference on Machine Learning. New York, USA: ACM, 2015: 448?456.
[25] VINOD Nair, GEOFFREY E Hinton. Rectified Linear Units Improve Restricted Boltzmann Machines[C]//2010 International Conference on Machine Learning. New York, USA: ACM, 2010: 807?814.
- 相似文献/References:
-
[1]张媛媛,霍静,杨婉琪,等.深度信念网络的二代身份证异构人脸核实算法[J].智能系统学报,2015,10(2):193.[doi:10.3969/j.issn.1673-4785.201405060]
ZHANG Yuanyuan,HUO Jing,YANG Wanqi,et al.A deep belief network-based heterogeneous face verification method for the second-generation identity card[J].CAAI Transactions on Intelligent Systems,2015,10():193.[doi:10.3969/j.issn.1673-4785.201405060]
[2]丁科,谭营.GPU通用计算及其在计算智能领域的应用[J].智能系统学报,2015,10(1):1.[doi:10.3969/j.issn.1673-4785.201403072]
DING Ke,TAN Ying.A review on general purpose computing on GPUs and its applications in computational intelligence[J].CAAI Transactions on Intelligent Systems,2015,10():1.[doi:10.3969/j.issn.1673-4785.201403072]
[3]马晓,张番栋,封举富.基于深度学习特征的稀疏表示的人脸识别方法[J].智能系统学报,2016,11(3):279.[doi:10.11992/tis.201603026]
MA Xiao,ZHANG Fandong,FENG Jufu.Sparse representation via deep learning features based face recognition method[J].CAAI Transactions on Intelligent Systems,2016,11():279.[doi:10.11992/tis.201603026]
[4]刘帅师,程曦,郭文燕,等.深度学习方法研究新进展[J].智能系统学报,2016,11(5):567.[doi:10.11992/tis.201511028]
LIU Shuaishi,CHENG Xi,GUO Wenyan,et al.Progress report on new research in deep learning[J].CAAI Transactions on Intelligent Systems,2016,11():567.[doi:10.11992/tis.201511028]
[5]马世龙,乌尼日其其格,李小平.大数据与深度学习综述[J].智能系统学报,2016,11(6):728.[doi:10.11992/tis.201611021]
MA Shilong,WUNIRI Qiqige,LI Xiaoping.Deep learning with big data: state of the art and development[J].CAAI Transactions on Intelligent Systems,2016,11():728.[doi:10.11992/tis.201611021]
[6]王亚杰,邱虹坤,吴燕燕,等.计算机博弈的研究与发展[J].智能系统学报,2016,11(6):788.[doi:10.11992/tis.201609006]
WANG Yajie,QIU Hongkun,WU Yanyan,et al.Research and development of computer games[J].CAAI Transactions on Intelligent Systems,2016,11():788.[doi:10.11992/tis.201609006]
[7]黄心汉.A3I:21世纪科技之光[J].智能系统学报,2016,11(6):835.[doi:10.11992/tis.201605022]
HUANG Xinhan.A3I: the star of science and technology for the 21st century[J].CAAI Transactions on Intelligent Systems,2016,11():835.[doi:10.11992/tis.201605022]
[8]宋婉茹,赵晴晴,陈昌红,等.行人重识别研究综述[J].智能系统学报,2017,12(6):770.[doi:10.11992/tis.201706084]
SONG Wanru,ZHAO Qingqing,CHEN Changhong,et al.Survey on pedestrian re-identification research[J].CAAI Transactions on Intelligent Systems,2017,12():770.[doi:10.11992/tis.201706084]
[9]杨梦铎,栾咏红,刘文军,等.基于自编码器的特征迁移算法[J].智能系统学报,2017,12(6):894.[doi:10.11992/tis.201706037]
YANG Mengduo,LUAN Yonghong,LIU Wenjun,et al.Feature transfer algorithm based on an auto-encoder[J].CAAI Transactions on Intelligent Systems,2017,12():894.[doi:10.11992/tis.201706037]
[10]王科俊,赵彦东,邢向磊.深度学习在无人驾驶汽车领域应用的研究进展[J].智能系统学报,2018,13(1):55.[doi:10.11992/tis.201609029]
WANG Kejun,ZHAO Yandong,XING Xianglei.Deep learning in driverless vehicles[J].CAAI Transactions on Intelligent Systems,2018,13():55.[doi:10.11992/tis.201609029]
备注/Memo
收稿日期:2021-12-05。
基金项目:国家社科基金重大项目(20&ZD279).
作者简介:骆彦龙，博士研究生，主要研究方向为图像识别、深度学习；毕晓君, 教授，博士生导师，主要研究方向为智能信息处理技术、数字图像处理、机器学习。主持国家重点研发计划项目、国家社科基金重大项目等国家级、省部级项目6项。获得高等学校科学技术进步一等奖1项、省部级科学技术奖7项。发表学术论 文170余篇；吴立成，教授，博士生导师，主要研究方向为智能机器人、人工智能。主持国家自然科学基金、863项目等国家级、省部级项目十余项。获教育部科技进步奖、江苏省科技进步奖各1项。发表学术论文80余篇。
通讯作者:毕晓君. E-mail：bixiaojun@hrbeu.edu.cn
更新日期/Last Update:
1900-01-01