Research on Overload Classification Method for Bus Images Based on Image Processing and SVM

  • Tingting Li
  • Yongxiong SunEmail author
  • Yanhua Liang
  • Yujia Zhai
  • Xuan Ji
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11336)


The speed and efficiency of overloaded artificial screening bus images are relatively low, which results in a large number of human resources waste problems. Therefore, an overload classification method for bus images based on image processing and support vector machine was proposed to intelligently identify the image overload or not. Based on the consideration we have done the following work. Firstly, the bus images were preprocessed, including image enhancement using histogram equalization method and image segmentation using improved Otsu algorithm; Secondly, the features of the segmented images was extracted by Kirsch edge detection operator to establish the image feature sample library; Finally, the appropriate kernel function and parameters were chosen to establish a classifier model based on support vector machine, which can train the sample library to classify the bus images. Theoretical analysis and experimental results show that the average classification accuracy of the polynomial kernel function is better than those of the Gaussian kernel function and the Sigmoid kernel function in the finite range of parameters selection. When the parameter d of the polynomial kernel function is 4, the classification accuracy is 93.68%, and its classification performance is stable and there is no significant increase or fall. And the conclusion was verified in the actual application.


Bus overload Image segmentation Image feature extraction Support vector machine Image classification 


  1. 1.
    Ding, C.: The effect of overloaded cars and the tire pressure on the stress distribution of the road. Int. J. Intell. Inf. Manag. Sci. 5(3), 264–267 (2016)Google Scholar
  2. 2.
    Wang, W.L., Lu, C.Z., Li, Y.R.: Basic economic measures in long-term effective mechanism for administering overload and oversize of motor vehicles. Int. J. Intell. Inf. Manag. Sci. 24(6), 148–152 (2007)Google Scholar
  3. 3.
    Zhang, Z., Cheng, W., Wu, L., et al.: Study on circular traffic signs recognition method based on invariant moments and SVM. J. Electron. Meas. Instrum. 31(5), 773–779 (2017)Google Scholar
  4. 4.
    Zhao, G.Q., Wang, F.J.: Car train overload signal monitoring system optimization modeling research. Comput. Simul. 33(11), 162–163 (2016)Google Scholar
  5. 5.
    Wu, Y.Q., Meng, T.L., Wu, S.H.: Research progress of image thresholding methods in recent 20 years (1994–2014). J. Data Acquis. Process. 30(1), 1–23 (2015)Google Scholar
  6. 6.
    Yan, J.Z., Lin, S., Sing, B.K.: Change-based image cropping with exclusion and compositional features. Int. J. Comput. Vis. 114(1), 74–87 (2015)CrossRefGoogle Scholar
  7. 7.
    A R Correspondng’s scientific contributions, Venmathi, Venmathi, A.R., et al.: Kirsch compass kernel edge detection algorithm for micro calcification clusters in mammogram. Middle East J. Sci. Res. 24(4), 1530–1535 (2016)Google Scholar
  8. 8.
    Liu, D.H., Zhang, Y.D., Li, X., et al.: Adaptive thresholding method under the dynamic environment. J. Comput. Appl. 36(S2), 152–156 (2016)Google Scholar
  9. 9.
    A R Correspondng’s scientific contributions, Venmathi, A.R., Venmathi, E.N., Ganesh, N.K.: Kirsch Compass kernel edge detection algorithm for micro calcification clusters in mammograms. Middle East J. Sci. Res. 24(4), 1530–1535 (2016)Google Scholar
  10. 10.
    Thang, P.Q., Thuy, N.T., Lam, H.T.: A modification of solution optimization in support vector machine simplification for classification. In: Bhateja, V., Nguyen, B.L., Nguyen, N.G., Satapathy, S.C., Le, D.-N. (eds.) Information Systems Design and Intelligent Applications. AISC, vol. 672, pp. 149–158. Springer, Singapore (2018). Scholar
  11. 11.
    Zhi, J., Sun, J., Wang, Z., Ding, W.: Support vector machine classifier for prediction of the metastasis of colorectal cancer. Int. J. Mol. Med. 41(3), 1419–1426 (2018)Google Scholar
  12. 12.
    Mcdonald, G., Macdonald, C., Ounis, I.: A study of SVM kernel functions for sensitivity classification ensembles with POS sequences. In: SIGIR 2017, pp. 1097–1100 (2017)Google Scholar
  13. 13.
    Yang, L., Wang, Y.: Survey for various cross-validation estimators of generalization error. Appl. Res. Comput. 32(5), 1287–1290 (2011)Google Scholar
  14. 14.
    Zhou, Z.H.: Machine Learning. 2nd edn. Tsinghua University Press, Beijing (2016)Google Scholar
  15. 15.
    Yu, Z., Wong, H.S., Wen, G.: A modified support vector machine and its application to image segmentation. Image Vis. 29(1), 29–40 (2016)CrossRefGoogle Scholar
  16. 16.
    Hsuan, T.L., Chih, J.L.: A study on Sigmoid Kernels for SVM and the training non-PSD kernels by SMO-type methods. Submitt. Neural Comput. 27(1), 15–23 (2003)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.College of SoftwareJilin UniversityChangchunChina
  2. 2.College of Computer Science and TechnologyJilin UniversityChangchunChina

Personalised recommendations