Hot-Rolled, Heavy-Rail Image Recognition Based on Deep-Learning Network


  • Xie Changgui Chongqing Vocational Institute of Engineering, Chongqing, 402260, China
  • Xu Hao Chongqing Vocational Institute of Engineering, Chongqing, 402260, China
  • Liu Yuxi Chongqing Vocational Institute of Engineering, Chongqing, 402260, China
  • Chen Ping Chongqing University, Chongqing, 400044, China



heavy rail; deep learning; defect recognition; error recognition rate; network


A new method for image-defect recognition is proposed that is based on a convolution network with repeated stacking of small convolution kernels and a maximum pooling layer. By improving the speed and accuracy of image-defect recognition, this new method can be applied to image recognition such as heavy-rail images with high noise and many types of defects. The experimental results showed that the new algorithm effectively improved the accuracy of heavy-rail image-defect recognition. As evidenced by the simulation study, the proposed method has a lower error rate in heavy-rail image recognition than traditional algorithms, and the method may also be applied to defect recognition of nonlinear images under strong noise conditions. Its robustness and nonlinear processing ability are impressive, and the method is featured with high theoretical depth and important application value.


Download data is not yet available.

Author Biography

Xie Changgui, Chongqing Vocational Institute of Engineering, Chongqing, 402260, China

Xie Changgui was born in 1984 and obtained Ph.D. in school of mechanical engineering at Chongqing University in December 2012. He is now working as an associate professor in a famous Vocational College in Chongqing. His research area is about equipment diagnosis and signal processing, artificial intelligence etc. He has presided over many national and provincial projects.


XIE Zhi-jiang, CHEN TAO,CHU Hong-yu.The key Technology research of on-line surface inspection for hot heavy rail[J]. Journal of Chongqing University, . 2012,35(3):15-18.[2]

Shi Tian; Kong Jian-yi; Wang Xing-dong.Improved Sobel algorithm for defect detection of rail surfaces with enhanced efficiency and accuracy[J]. JOURNAL OF CENTRAL SOUTH UNIVERSITY, 2016,23(11): 2867-2875.

Ye Suru, Hu Zhimin, Ouyang Qi et al. Research on the Surface Defect Detection System of Heavy Rails Based on Machine Vision [J]. Modern Manufacturing Engineering, 2007, 8: 89-90.

Lu Tao, Wang Jiaming, Li Xiaolin et al. Face Super-resolution Reconstruction Based on Relay Cyclic Residual Network[J]. Journal of Huazhong University of Science and Technology(Natural Science), 2018, 46(12): 95-100.

Liu Yongxin, Duan Tiantian. Image Super-resolution Reconstruction Based on Deep Learning [J]. Technology and Innovation, 2018, 23: 40-43.

Yu Yongwei, Yin Guofu, Yin Ying et al. A Method for Radiation Image Defect Recognition Based on Deep Learning Network[J]. Chinese Journal of Scientific Instrument, 2014, 35(9): 2012-2017.

Chen Tao. Key Technologies for On-line Heavy Rail Detection System for Thermal Surface Defects[D].Chongqing: Chongqing University, 2011,:48-53.

JinYuan,XingxingHou,YaoqiangXiao etal. Multi-criteria active deep learning for image classification[J]. KNOWLEDGE-BASED SYSTEMS,2019,172:86-94.

Tiago Santos,Stefan Schrunner,Bernhard C.Geiger etal. Feature Extraction From Analog Wafermaps: A Comparison of Classical Image Processing and a Deep Generative Model[J]. IEEE TRANSACTIONS ON SEMICONDUCTOR MANUFACTURING ,2019,32(2):190-198.[10]Zhang, Chuan-Wei, Yang, Meng-Yue; Zeng, Hong-Jun.Pedestrian detection based on improved LeNet-5 convolution neural network[J].Journal of Algorithms and Computational Technology,2019,13:1-9.

Wang, Qibin; Zhao, Bo; Ma, Hongbo.A method for rapidly evaluating reliability and predicting remaining useful life using two-dimensional convolution neural network with signal conversion[J].JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY,2019,33(6):2561-2571.

Madec, Simon, Jin, Xiuliang, Lu, Hao etal. Ear density estimation from high resolution RGB imagery using deep learning technique[J]. AGRICULTURAL AND FOREST METEOROLOGY,2019,264:225-234.

YoshikoAriji,MotokiFukuda,YoshitakaKise. Contrast-enhanced computed tomography image assessment of cervical lymph node metastasis in patients with oral cancer by using a deep learning system of artificial intelligence[J]. ORAL SURGERY ORAL MEDICINE ORAL PATHOLOGY ORAL RADIOLOGY,2019,127(5):458-463.

Mateo Sanguino, Tomas de J.; Castilla Webber, Pedro A. Making image and vision effortless: Learning methodology through the quick and easy design of short case studies[J]. COMPUTER APPLICATIONS IN ENGINEERING EDUCATION,2018,26(6):2102-2115.

Al-Kofahi Yousef, Zaltsman Alla, Graves Robert. A deep learning-based algorithm for 2-D cell segmentation in microscopy images[J]. BMC BIOINFORMATICS, 2018,19:1-11.

Amato G , Falchi F, Vadicamo L. Visual Recognition of Ancient Inscriptions Using convolution Neural Network and Fisher Vector[J]. ACM JOURNAL ON COMPUTING AND CULTURAL HERITAGE,2016,9(4):1-21.

Shibata Naoto, Tanito Masaki, Mitsuhashi Keita. Development of a deep residual learning algorithm to screen for glaucoma from fundus photography[J]. SCIENTIFIC REPORTS,2018,8:1-9.

Srivastava Arunima, Kulkarni Chaitanya, Huang Kun. Imitating Pathologist Based Assessment With Interpretable and Context Based Neural Network Modeling of Histology Images[J]. BIOMEDICAL INFORMATICS INSIGHTS,2018,10:1-7.

Park Sang Jun, Shin Joo Young, Kim Sangkeun. A Novel Fundus Image Reading Tool for Efficient Generation of a Multi-dimensional Categorical age Database for Machine Learning Algorithm Training[J]. JOURNAL OF KOREAN MEDICAL SCIENCE,2018,33(43):1-12.

Faust Kevin, Xie Quin, Han Dominick. Visualizing histopathologic deep learning classification and anomaly detection using nonlinear feature space dimensionality reduction[J].BMC BIOINFORMATICS,2018,19:1-15.

Gopalakrishnan Kasthurirangan, Khaitan, Siddhartha K, Choudhary Aloketal. Deep convolution Neural Networks with transfer learning for computer vision-based data-driven pavement distress detection[J]. CONSTRUCTION AND BUILDING MATERIALS,2017,157:322-330.

Okamura Rintaro, Iwabuchi Hironobu, Schmidt K. Sebastian. Feasibility study of multi-pixel retrieval of optical thickness and droplet effective radius of inhomogeneous clouds using deep learning[J]. ATMOSPHERIC MEASUREMENT TECHNIQUES,2017,10(12):4747-4759.

Metcalf SJ (Metcalf, Shari J.), Reilly JM (Reilly, Joseph M.), Kamarainen AM (Kamarainen, Amy M.). Supports for deeper learning of inquiry-based ecosystem science in virtual environments - Comparing virtual and physical concept mapping[J]. COMPUTERS IN HUMAN BEHAVIOR,2018,87:459-469.

Yan SY (Yan, Shiyang), Smith JS (Smith, Jeremy S.),Zhang BL (Zhang, Bailing). Action Recognition from Still Images Based on Deep VLAD Spatial Pyramids[J].SIGNAL PROCESSING-IMAGE COMMUNICATION,2017,54:118-129.

Kim, TaeGuen, Kang, BooJoong, Rho, M (Rho, Mina etal. A Multimodal Deep Learning Method for Android Malware Detection Using Various Features[J]. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,2019,14(3):773-788.

Brachmann, A , Redies, C. Using convolution Neural Network Filters to Measure Left-Right Mirror Symmetry in Images[J]. SYMMETRY-BASEL,2016,8(12):1-10.

Tan Wenxue, Zhao, Chunjiang, Wu, Huarui. Intelligent alerting for fruit-melon lesion image basedonmomentum deep learning[J]. MULTIMEDIA TOOLS AND APPLICATIONS,2016,75(24):16741-16761.

Noda, Kuniaki, Arie, Hiroaki), Suga, Yuki. Multimodal integration learning of robot behavior using deep neural networks[J]. ROBOTICS AND AUTONOMOUS SYSTEMS,2014,62(6):721-736.

Bansal, Raghav; Raj, Gaurav; Choudhury, Tanupriya.Blur Image Detection using Laplacian Operator and Open-CV[J]. 5th International Conference System Modeling and Advancement in Research Trends (SMART),2016:63-67.

Farahani, Behzad, V; Barros, Francisco; Sousa, Pedro J.A coupled 3D laser scanning and digital image correlation system for geometry acquisition and deformation monitoring of a railway tunnel[J].TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY,2019,91:1-12.





Advanced Practice in Web Engineering