Skip to main content

Advertisement

Springer Nature Link
Log in

Candidate region acquisition optimization algorithm based on multi-granularity data enhancement

  • Original Article
  • Published:
International Journal of Machine Learning and Cybernetics Aims and scope Submit manuscript

Abstract

Given the deepening network hierarchy of deep learning, improving the accuracy of the candidate region acquisition algorithm can help save time and improve operational efficiency in subsequent work. Since the traditional methods overly rely on single-grain size, color and texture features of images, which can easily lead to candidate frames cutting off the foreground object when acquiring candidate regions, this paper proposes a multi-granularity selective search algorithm (MGSS) for candidate region acquisition by extracting the main features such as outline, texture and color of images with multiple grain sizes and improving the subgraph similarity calculation method.This paper mainly compares the performance of previous common algorithms on Pascal VOC 2012 and 2007 datasets, and the experiments show that the method used in this paper maintains the Mean Average Best Overlap (MABO) values of 0.909 and 0.890, which is 9.55\(\%\) and 2.05\(\%\) better than the Selective Search (SS)“Fast” and SS “Quality” results, respectively. The experiments show that both R-CNN and Fast R-CNN algorithms improve mAP (mean Average Precision) values by 1.5, 0.8 and 0.6 \(\%\) with MGSS respectively, over with the traditional SS algorithm and RPN algorithm.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 580–587

  2. Zhang N, Donahue J, Girshick R, Darrell T (2014) Part-based r-cnns for fine-grained category detection. In: European conference on computer vision. Springer, pp 834–849

  3. He K, Zhang X, Ren S, Sun J (2015) Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Intell 37(9):1904–1916

    Article  Google Scholar 

  4. He K, Sun J, Zhang X, Ren S (2016) Spatial pyramid pooling networks for image processing

  5. Girshick R (2015) Fast r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 1440–1448

  6. Li J, Liang X, Shen S, Xu T, Feng J, Yan S (2017) Scale-aware fast r-cnn for pedestrian detection. IEEE Trans Multimed 20(4):985–996

    Google Scholar 

  7. Zhao ZQ, Bian H, Hu D, Cheng W, Glotin H (2017) Pedestrian detection based on fast r-cnn and batch normalization. In: International conference on intelligent computing. Springer, pp 735–746

  8. Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: Towards real-time object detection with region proposal networks. arXiv preprint arXiv:1506.01497

  9. Dai J, Li Y, He K, Sun J (2016) R-fcn: Object detection via region-based fully convolutional networks. arXiv preprint arXiv:1605.06409

  10. Hosang J, Benenson R, Dollár P, Schiele B (2015) What makes for effective detection proposals? IEEE Trans Pattern Anal Mach Intell 38(4):814–830

    Article  Google Scholar 

  11. Pang Y, Cao J, Li X (2016) Learning sampling distributions for efficient object detection. IEEE Trans Cybernet 47(1):117–129

    Article  Google Scholar 

  12. Wang X, Liang C, Chen J (2016) Multi-pedestrian detection from effective proposal in crowd scene. In: Proceedings of the international conference on internet multimedia computing and service, pp 156–159

  13. Uijlings JR, Van De Sande KE, Gevers T, Smeulders AW (2013) Selective search for object recognition. Int J Comput Visi 104(2):154–171

    Article  Google Scholar 

  14. Felzenszwalb PF, Huttenlocher DP (2004) Efficient graph-based image segmentation. Int J Comput Vis 59(2):167–181

    Article  Google Scholar 

  15. Lin T-Y, Dollár P, Girshick R, He K, Hariharan B, Belongie S (2017) Feature pyramid networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2117–2125

  16. Yao Y (2013) Granular computing and sequential three-way decisions. In: International conference on rough sets and knowledge technology. Springer, pp 16–27

  17. Xiaodong Y, Duoqian M, Caiming Z (2010) Color image segmentation method based on roughness metric. Automa J 36(6):807–816

    Google Scholar 

  18. Chahine C, Vachier-Lagorre C, Chenoune Y, El Berbari R, El Fawal Z, Petit E (2017) Information fusion for unsupervised image segmentation using stochastic watershed and hessian matrix. IET Image Process 12(4):525–531

    Article  Google Scholar 

  19. Noyel G, Angulo J, Jeulin D (2007) Random germs and stochastic watershed for unsupervised multispectral image segmentation. In: International conference on knowledge-based and intelligent information and engineering systems. Springer, pp 17–24

  20. Chahine C, El Berbari R, Lagorre C, Nakib A, Petit E (2015) Evidence theory for image segmentation using information from stochastic watershed and hessian filtering. In: 2015 International conference on systems, signals and image processing (IWSSIP).1em plus 0.5em minus 0.4emIEEE, pp 141–144

  21. Nouri M, Khezeli A, Ramezani A, Ebrahimi A (2012) A dynamic chaotic hash function based upon circle chord methods. In: 6th International symposium on telecommunications (IST). IEEE, pp 1044–1049

  22. Liu Y, Yan P, Xia R et al (2016) Fp-cnnh: a fast image hashing algorithm based on deep convolutional neural network. Comput Sci 43(9):39–51

    Google Scholar 

  23. Qu W, Wang D, Feng S, Zhang Y, Yu G (2017) A novel cross-modal hashing algorithm based on multimodal deep learning. Sci China Inf Sci 60(9):092104

    Article  Google Scholar 

  24. Liu X, Zhang Q, Luan R, Yu F, (2013) Applications of perceptual hash algorithm in agriculture images. In: 2013 6th International congress on image and signal processing (CISP), vol 2.1. IEEE, pp 698–702

  25. Ruchay A, Kober V, Yavtushenko E (2017) Fast perceptual image hash based on cascade algorithm. In: Applications of digital image processing XL, vol 10396. International Society for Optics and Photonics, p 1039625

  26. Yuan J, Xu D, Xiong H-C, Li Z-Y (2016) A novel object tracking algorithm based on enhanced perception hash and online template matching. In: 2016 12th International conference on natural computation, fuzzy systems and knowledge discovery (ICNC-FSKD). IEEE, pp 494–499

  27. Imasaki K, Dandamudi S (2002) An adaptive hash join algorithm on a network of workstations. In: Proceedings 16th international parallel and distributed processing symposium. IEEE, p 8

  28. Raposo CA, Ribeiro J, Cattai A (2018) Global solution for a thermoelastic system with p-laplacian. Appl Math Lett 86:119–125

    Article  MathSciNet  Google Scholar 

  29. Alzaid A, Kim JS, Proschan F (1991) Laplace ordering and its applications. J Appl Prob 28:116–130

    Article  MathSciNet  Google Scholar 

  30. Alves CO, de Lima RN, Nóbrega AB (2018) Bifurcation properties for a class of fractional laplacian equations in. Math Nachr 291(14–15):2125–2144

    Article  MathSciNet  Google Scholar 

  31. Merris R (1994) Laplacian matrices of graphs: a survey. Linear Algebra Its Appl 197:143–176

    Article  MathSciNet  Google Scholar 

  32. Zhang X-D (2011) The laplacian eigenvalues of graphs: a survey. arXiv preprint arXiv:1111.2897

  33. Li J-S, Zhang X-D (1998) On the laplacian eigenvalues of a graph. Linear Algebra Its Appl 285(1–3):305–307

    Article  MathSciNet  Google Scholar 

  34. Pirzada S, Ganie HA (2015) On the laplacian eigenvalues of a graph and laplacian energy. Linear Algebra Its Appl 486:454–468

    Article  MathSciNet  Google Scholar 

  35. Gutman I, Zhou B (2006) Laplacian energy of a graph. Linear Algebra Its Appl 414(1):29–37

    Article  MathSciNet  Google Scholar 

  36. Liu Y, Wu B (2010) Some results on the laplace energy of graphs (English). J East China Normal Univ (Natural Sciences Edition) 1:161–171

    Google Scholar 

  37. Bandeira AS (2018) Random laplacian matrices and convex relaxations. Found Comput Math 18(2):345–379

    Article  MathSciNet  Google Scholar 

  38. Pan H, Wang B, Jiang H (2015) “Deep learning for object saliency detection and image segmentation,” arXiv preprint arXiv:1505.01173

  39. Alexe B, Deselaers T, Ferrari V (2012) Measuring the objectness of image windows. IEEE Trans Pattern Anal Mach Intell 34(11):2189–2202

    Article  Google Scholar 

  40. Endres I, Hoiem D (2010) Category independent object proposals. In European conference on computer vision. Springer, pp 575–588

  41. Felzenszwalb PF, Girshick RB, McAllester D, Ramanan D (2009) Object detection with discriminatively trained part-based models. IEEE Trans Pattern Anal Mach Intell 32(9):1627–1645

    Article  Google Scholar 

  42. Liu Y, Zhang Q, Zhang D, Han J (2019) Employing deep part-object relationships for salient object detection. In: Proceedings of the IEEE/CVF international conference on computer vision, pp 1232–1241

Download references

Acknowledgements

This research was supported in part by the National Natural Science Foundation of China Grant Nos. 61976158 and 62006172.

Author information

Authors and Affiliations

  1. Tongji University, Zhixin Hall, Jiading Campus, 4800 Cao’an Road, Shanghai, China

    Chen Dong, Miao Duoqian & Cairong Zhao

  2. Information Technology Center, Shanghai Institute of Technology, Shanghai, China

    Hailong Zhou

Authors
  1. Chen Dong
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Miao Duoqian
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Cairong Zhao
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Hailong Zhou
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Miao Duoqian.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Chen, D., Miao, D., Zhao, C. et al. Candidate region acquisition optimization algorithm based on multi-granularity data enhancement. Int. J. Mach. Learn. & Cyber. 13, 1847–1860 (2022). https://doi.org/10.1007/s13042-021-01492-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13042-021-01492-5

Keywords