Image Recognition Model Based on Multivariate Feature Heterogeneous Ensemble Deep Learning With Its Application

TANG Jian; TIAN Hao; XIA Heng; WANG Zixuan; XU Zhe; HAN Honggui

doi:10.11936/bjutxb2022030011

Journal of Beijing University of Technology > 2024 > 50(1): 27-37. > DOI: 10.11936/bjutxb2022030011

TANG Jian, TIAN Hao, XIA Heng, WANG Zixuan, XU Zhe, HAN Honggui. Image Recognition Model Based on Multivariate Feature Heterogeneous Ensemble Deep Learning With Its Application[J]. Journal of Beijing University of Technology, 2024, 50(1): 27-37. DOI: 10.11936/bjutxb2022030011

Citation:

PDF (5962 KB)

Image Recognition Model Based on Multivariate Feature Heterogeneous Ensemble Deep Learning With Its Application

TANG Jian^{1, 2,},
TIAN Hao^{1, 2},
XIA Heng^{1, 2},
WANG Zixuan^{1, 2},
XU Zhe¹,
HAN Honggui^{1, 2}

1.
Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China
2.
Beijing Laboratory of Smart Environmental Protection, Beijing 100124, China

More Information

Received Date: March 20, 2022
Revised Date: July 05, 2022
Available Online: November 28, 2023

Graphical Abstract

Abstract

Abstract

With the continuous development of recycling technology for urban mineral resources, recycling of used mobile phones has become a hotspot for current research. Restricted by the relative lack of computing resources and data resources, the accuracy of used mobile phone recognition based on current off-line intelligent recycling equipment is difficult to meet the practical application. Therefore, an image identification method based on multivariate feature heterogeneous ensemble deep learning method was proposed. First, the character region on the back of the mobile phone was extracted by using character region awareness for text detection (CRAFT) algorithm, the VGG19 model pre-trained by ImageNet was used as the image feature embedding model, and the local character feature and global image feature were extracted by using the transfer learning mechanism. Then, the optical character recognition (OCR) character recognition model based on neural network (NN) mode was constructed by using the local feature, and the improved deep forest classification (DFC) model based on non-NN model was constructed by using the global and local features. Finally, the outputs of heterogeneous OCR and the DFC model were integrated and fed into the Softmax to ensemble, and the final recognition result was obtained based on the criterion of maximum category weight vector. The effectiveness of the proposed method was verified based on real images of used mobile phone from recycling equipment.
- used mobile phones,
- image recognition,
- transfer learning,
- multivariate feature,
- optical character recognition (OCR),
- deep forest,
- heterogeneous ensemble

FullText(HTML)

References (25)

References

[1]	韩红桂, 甄琪, 任柯燕, 等. 基于孪生卷积神经网络的手机型号识别方法[J]. 北京工业大学学报, 2021, 47(2): 112-119. doi: 10.11936/bjutxb2019100016 HAN H G, ZHEN Q, REN K Y, et al. Mobile phone model recognition method based on Siamese convolutional neural network[J]. Journal of Beijing University of Technology, 2021, 47(2): 112-119. (in Chinese) doi: 10.11936/bjutxb2019100016
[2]	LINDA S. Global handset/smartphone/feature phone sales forecast for countries: 2007 to 2026[EB/OL]. [2021-03-01]. https://www.strategyanalytics.com/access-services/devices/mobile-phones/smartphone/smartphones/market-data/report-detail/global-handset-smartphone-feature-phone-sales-forecast-for-88-countries-2007-to-2026?Related.
[3]	郭学益, 张婧熙, 黄国勇, 等. 典型电子废弃物中金属资源开采潜力分析[J]. 中国有色金属学报, 2018, 28(2): 365-376 GUO X Y, ZHANG J X, HUANG G Y, et al. Exploitation potentiality analysis of metal resources in typical electronic waste[J]. Chinese Journal of Nonferrous Metals, 2018, 28(2): 365-376. (in Chinese)
[4]	王子轩, 汤健, 夏恒, 等. 基于并行差分进化-梯度特征深度森林的废旧手机识别方法[J]. 控制理论与应用, 2022, 39(11): 2137-2148. WANG Z X, TANG J, XIA H, et al. Used mobile phone recognition method based on parallel differential evolution and gradient feature deep forest[J]. Control Theory & Applications, 2022, 39(11): 2137-2148. (in Chinese)
[5]	WANG Z, TANG J, CUI C, et al. Review of used mobile phone recognition method for recycling equipment[C]//2020 39th Chinese Control Conference (CCC). Piscataway: IEEE, 2020: 1105-1110.
[6]	林琳, 吕彦诚, 郭昊, 等. 基于边缘检测的生产线手机膜缺陷识别方法[J]. 控制与决策, 2021, 36(4): 1017-1024. LIN L, LÜ Y C, GUO H, et al. Mobile phone protective film defect recognition method based on edge detection[J]. Control and Decision, 2021, 36(4): 1017-1024. (in Chinese)
[7]	王睿男, 武穆清, 陈铁英, 等. 基于形态学的红外图像边缘检测[J]. 北京邮电大学学报, 2021, 44(1): 66-71. WANG R N, WU M Q, CHEN T Y, et al. Edge detection of infrared image based on morphology[J]. Journal of Beijing University of Posts and Telecommunications, 2021, 44(1): 66-71. (in Chinese)
[8]	刘晓军, 类成玉, 张晓玲, 等. 基于卷积神经网络的人脸检测综述[J]. 兵工自动化, 2021, 40(6): 58-63. LIU X J, LEI C Y, ZHANG X L, et al. Face detection survey based on convolutional neural network[J]. Ordnance Automation, 2021, 40(6): 58-63. (in Chinese)
[9]	刘芳, 浦昭辉, 张帅超. 基于注意力特征融合的无人机多目标跟踪算法[J]. 控制与决策, 2023, 38(2): 345-353. LIU F, PU Z H, ZHANG S C. UAV multi-target tracking algorithm based on attention feature fusion[J]. Control and Decision, 2023, 38(2): 345-353. (in Chinese)
[10]	宋建辉, 孙晓南, 刘晓阳, 等. 融合HOG特征和注意力模型的孪生目标跟踪算法[J]. 控制与决策, 2023, 38(2): 327-334. SONG J H, SUN X N, LIU X Y, et al. Twin target tracking network combining HOG features and attention mode[J]. Control and Decision, 2023, 38(2): 327-334. (in Chinese)
[11]	AZIZI S, IMANI F, GHAVIDEL S, et al. Detection of prostate cancer using temporal sequences of ultrasound data: a large clinical feasibility study[J]. International Journal of Computer Assisted Radiology and Surgery, 2016, 11(6): 947-956. doi: 10.1007/s11548-016-1395-2
[12]	ZHOU Z H, FENG J. Deep forest[J]. National Science Review, 2019, 6(1): 74-86. doi: 10.1093/nsr/nwy108
[13]	夏恒, 汤健, 乔俊飞. 深度森林研究综述[J]. 北京工业大学学报, 2022, 48(2): 182-196. doi: 10.11936/bjutxb2020120017 XIA H, TANG J, QIAO J F. Review of deep forest[J]. Journal of Beijing University of Technology, 2022, 48(2): 182-196. (in Chinese) doi: 10.11936/bjutxb2020120017
[14]	程月华, 江文建, 杨浩, 等. 基于深度森林的卫星ACS执行机构与传感器故障识别[J]. 航空学报, 2020, 41(增刊1): 195-205. CHENG Y H, JIANG W J, YANG H, et al. Fault identification of actuators and sensors of satellite attitude control systems based on deep forest algorithm[J]. Journal of Aeronautics and Astronautics, 2020, 41(Suppl 1): 195-205. (in Chinese)
[15]	LI H, ZHAO H, YU E, et al. A clothes classification method based on the gcForest[C]//2018 3rd IEEE International Conference on Image, Vision and Computing(ICIVC). Piscataway: IEEE, 2018: 429-432.
[16]	李璐, 杜兰, 何浩男, 等. 基于深度森林的多级特征融合SAR目标识别[J]. 电子与信息学报, 2021, 43(3): 606-614. LI L, DU L, HE H N, et al. Multi-level feature fusion SAR automatic target recognition based on deep forest[J]. Journal of Electronics and Information, 2021, 43(3): 606-614. (in Chinese)
[17]	SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[C]//2015 The Eleventh International Conference on Learning Representations(ICLR). Ithaca: Cornell University Library, arXiv. org. 2015: 1-14.
[18]	赵凯琳, 靳小龙, 王元卓. 小样本学习研究综述[J]. 软件学报, 2021, 32(2): 349-369. ZHAO K L, JIN X L, WANG Y Z. Survey on few-shot learning[J]. Journal of Software, 2021, 32(2): 349-369. (in Chinese)
[19]	LI T, MA Y, ENDOH T. A systematic study of tiny YOLO₃ inference: toward compact brainware processor with less memory and logic gate[J]. IEEE Access, 2020, 8: 142931-142955. doi: 10.1109/ACCESS.2020.3013934
[20]	CHOWDARY V S, TEJA G P S, MOUNESH D, et al. Sign board recognition based on convolutional neural network using Yolo-3[J]. Journal of Computational and Theoretical Nanoscience, 2020, 17(8): 3478-3483. doi: 10.1166/jctn.2020.9214
[21]	SUN X, WU P, HOI S. Face detection using deep learning: an improved faster RCNN approach[J]. Neurocomputing, 2018, 299: 42-50. doi: 10.1016/j.neucom.2018.03.030
[22]	汤健, 乔俊飞, 郭子豪. 基于潜在特征选择性集成建模的二噁英排放浓度软测量[J]. 自动化学报, 2022, 48(1): 223-238. TANG J, QIAO J F, GUO Z H. Dioxin emission concentration soft measurement based on multi-source latent feature selective ensemble modeling for municipal solid waste incineration process[J]. Acta Automatica Sinica, 2022, 48(1): 223-238. (in Chinese)
[23]	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, 2017, 39(11): 2298-2304. doi: 10.1109/TPAMI.2016.2646371
[24]	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). Piscataway: IEEE, 2016: 770-778.
[25]	CHOPRA S, HADSELL R, LECUN Y. Learning a similarity metric discriminatively, with application to face verification[C]//2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05). Piscataway: IEEE, 2005: 539-546.

[1]	GAO Tiaokang, JIN Xiaoning, LAI Yingxu. Model Heterogeneous Federated Learning for Intrusion Detection[J]. Journal of Beijing University of Technology, 2024, 50(5): 543-557. DOI: 10.11936/bjutxb2022060002
[2]	XIA Heng, TANG Jian, QIAO Junfei. Review of Deep Forest[J]. Journal of Beijing University of Technology, 2022, 48(2): 182-196. DOI: 10.11936/bjutxb2020120017
[3]	TANG Jian, XIA Heng, QIAO Junfei, GUO Zihao. Modeling Method of Deep Ensemble Forest Regression With Its Application[J]. Journal of Beijing University of Technology, 2021, 47(11): 1219-1229. DOI: 10.11936/bjutxb2020050002
[4]	WANG Dan, WANG Meng, WANG Xiaoxi, YANG Ping. Ensemble of Incremental Learning Algorithm for Flight Delay Prediction[J]. Journal of Beijing University of Technology, 2020, 46(11): 1239-1245. DOI: 10.11936/bjutxb2019030009
[5]	FANG Juan, ZHANG Xibei, LIU Shijian. LLC Buffer Management Strategy Based on Heterogeneous Multi-core[J]. Journal of Beijing University of Technology, 2019, 45(5): 421-427. DOI: 10.11936/bjutxb2017090031
[6]	JIANG Feng, ZHANG Youqiang, DU Junwei, LIU Guozhu, SUI Yuefei. Approximate Reducts-based Ensemble Learning Algorithm and Its Application in Intrusion Detection[J]. Journal of Beijing University of Technology, 2016, 42(6): 877-885. DOI: 10.11936/bjutxb2015100008
[7]	FANG Juan, WANG Xiao-cui. Improved Heterogeneous Prefetching Coordination Algorithm[J]. Journal of Beijing University of Technology, 2012, 38(3): 401-405.
[8]	YAN Jian-zhuo, FANG Li-ying, SHI Bin, CHENG Bo-yuan, YAN Bei. Detection and Resolution of Data Confliction in the Integration of Heterogeneous Information Sources[J]. Journal of Beijing University of Technology, 2008, 34(1): 37-42.
[9]	YAN Jian-zhuo, WANG Pu, FANG Li-ying, LÜ Xiao. The Design and Realization of Digital Campuses Heterogeneous Information Integrate System[J]. Journal of Beijing University of Technology, 2005, 31(z1): 20-23.
[10]	LIN Tong, SHU Zhen-cai. Web Services Based Integration of Remote Heterogeneous Databases[J]. Journal of Beijing University of Technology, 2005, 31(2): 210-213.

Cited By

Cited by

Periodical cited type(2)

1.	彭桂喜，袁思遥，高梓寒，吴玉龙，孙昊. 基于深度学习低图像要求的继电保护压板状态自动识别方法. 电力科学与技术学报. 2024(02): 134-142 .
2.	李荣基. 基于注意力机制的图像识别与目标检测方法. 电脑编程技巧与维护. 2024(06): 149-151 .

Other cited types(2)

Get Citation

PDF

XML

Article views (145) PDF downloads (46) Cited by(4)

Turn off MathJax

Article Contents

Abstract

References

Image Recognition Model Based on Multivariate Feature Heterogeneous Ensemble Deep Learning With Its Application