Skip to main content

Channel-Based Similarity Learning Using 2D Channel-Based Convolutional Neural Network

  • 13 Accesses

Part of the Lecture Notes in Computational Vision and Biomechanics book series (LNCVB,volume 37)

Abstract

Object identification is one of the major aspects of computer vision. In recent years, the development the computing as well as the storage capacity has increased drastically. These breakthroughs in the technology have blessed us with various data storage technologies and computational engines. Because of the breakthrough in recent years, we are generating humongous amounts of data of which 80% of data is unstructured data and only 20% of data is structured. Unstructured data are mainly composed of images, video and as well as the natural language, i.e. text. These 80% unstructured data consist of the enormous information, but it is difficult to unravel the information contained in these data. Convolution neural network (CNN) is backbone of computer vision and deals with extracting information from the image and video, before the invention of recurrent neural network (RNN), CNN was also employed for natural language processing (NLP) task such as classification and text generation, but the specialty of CNN lies where the dataset consists of sound signals, images or sequence of frames. On Internet, we can find 60% of the unstructured dataset consists of images or sequence of image or text. Basically, image consists of the features which is the orientation of the pixels in a well-defined pattern which can be extracted by using kernel’s known as the feature maps and Maxpooling layers to extract the underlying feature present in the image to train the neural network. CNN is one of the parts of supervised learning techniques which uses labelled data, but it is difficult to label huge number of images. The similarity-based learning enables us to control the similarity percentage as well as it has minimum labelling procedure, i.e. labelling of the dataset is to be labelled 0 or 1. Similarity learning is used to compute the percentage of the features which are similar in the target image with respect to the input image. Image consists of three channels, i.e. red, green and blue channels, which is basically a 2D vector with pixel values in range of 0–255. These individual channels contribute to the features present in the images, and if we can calculate the similarity between input image and the query image, then we can be able to present the unstructured images in relation to the similarity with respect to the input image by using the channels in channel-based CNN tower.

Keywords

  • Modified softmax
  • Distance learning
  • Similarity learning
  • Channel-based similarity

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-981-19-0151-5_28
  • Chapter length: 18 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   129.00
Price excludes VAT (USA)
  • ISBN: 978-981-19-0151-5
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Hardcover Book
USD   169.99
Price excludes VAT (USA)
Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

References

  1. Petrovic VMP (2018) Artificial intelligence and virtual worlds toward human-level AI agents. IEEE. https://doi.org/10.1109/ACCESS.2018.2855970

  2. Lpuridas P, Ebert (2016) Machine learning. IEEE software. https://doi.org/10.1109/MS.2016.114

  3. Angra S, Ahuja S, Machine learning and its application. IEEE. https://doi.org/10.1109/ICBDACI.2017.8070809

  4. Adadi A (2021) A survey on data-efficient algorithms in big data era. J Big Data 8:24. https://doi.org/10.1186/s40537-021-00419-9

    CrossRef  Google Scholar 

  5. Qi G, Luo J (2019) Small data challenges in big data era: a survey of recent progress on unsupervised and semi-supervised methods. arXiv preprint arXiv:1903.11260

  6. Ojha U, Adhikari U, Singh DK (2017) Image annotation using deep learning: a review. In: 2017 International conference on intelligent computing and control (I2C2), pp 1–5. https://doi.org/10.1109/I2C2.2017.8321819

  7. Aletti G, Micheletti A (2017) A clustering algorithm for multivariate data streams with correlated components. J Big Data 4:48. https://doi.org/10.1186/s40537-017-0109-0

    CrossRef  Google Scholar 

  8. Marginean S (2009) Advantages and disadvantages of clusters—a theoretical approach. Revista Econ 44:36–40

    Google Scholar 

  9. Koch G, Zemel R, Salakhutdinov R, Siamese neural networks for one-shot image recognition

    Google Scholar 

  10. Cano F, Cruz-Roa A (2020) An exploratory study of one-shot learning using Siamese convolutional neural network for histopathology image classification in breast cancer from few data examples. In: Proceedings of SPIE 11330, 15th international symposium on medical information processing and analysis, 113300A. https://doi.org/10.1117/12.2546488

  11. Melamud O, Goldberger J, Dagan I, Riezler S, Goldberg Y (2016) context2vec: learning generic context embedding with bidirectional LSTM. In: Proceedings of the 20th SIGNLL conference on computational natural language learning, association for computational linguistics (ACL), Berlin, Germany, 11–12 Aug 2016, pp 51–61

    Google Scholar 

  12. Gothwal R, Gupta S, Gupta D, Dahiya AK (2014) Color image segmentation algorithm based on RGB channels. In: Proceedings of 3rd international conference on reliability, infocom technologies and optimization, pp 1–5. https://doi.org/10.1109/ICRITO.2014.7014669

  13. He K, Zhang X, Ren S, Sun J, Deep residual learning for image recognition. arXiv:1512.03385

  14. Deng J, Dong W, Socher R, Li L, Li K, Li F-F (2009) ImageNet: a large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition, pp 248–255. https://doi.org/10.1109/CVPR.2009.5206848

  15. Adnan K, Akbar R (2019) An analytical study of information extraction from unstructured and multidimensional big data. J Big Data 6:91. https://doi.org/10.1186/s40537-019-0254-8

    CrossRef  Google Scholar 

  16. Verma S, Jain K, Prakash C (2020) An unstructured to structured data conversion using machine learning algorithm in internet of things (IoT. In: Proceedings of the international conference on innovative computing & communications (ICICC) 2020

    Google Scholar 

  17. Huang X, Li J, Liang Y et al (2017) Spatial hidden Markov chain models for estimation of petroleum reservoir categorical variables. J Petrol Explor Prod Technol 7:11–22. https://doi.org/10.1007/s13202-016-0251-9

    CrossRef  Google Scholar 

  18. Blake A, Kohli P, Rother C (2011) Markov random fields for vision and image processing. The MIT Press, Cambridge, pp 11–22

    CrossRef  Google Scholar 

  19. Bindra K, Mishra A (2017) A detailed study of clustering algorithms. In: 2017 6th international conference on reliability, infocom technologies and optimization (trends and future directions) (ICRITO), pp 371–376. https://doi.org/10.1109/ICRITO.2017.8342454

  20. Estivill-Castro V (2002) Why so many clustering algorithms: a position paper. ACM SIGKDD Explor Newsl 4:65–75

    CrossRef  Google Scholar 

  21. Xu D, Tian Y (2015) A comprehensive survey of clustering algorithms. Ann Data Sci 2:165–193. https://doi.org/10.1007/s40745-015-0040-1

    CrossRef  Google Scholar 

  22. Färber I, Günnemann S, Kriegel H, Kröger P, Müller E, Schubert E, Seidl T, Zimek A (2010) On using class-labels in evaluation of clusterings. In: MultiClust: 1st international workshop on discovering

    Google Scholar 

  23. Boley D, Gini M, Gross R, Han E, Hastings K, Karypis G, Kumar V, Mobasher B, Moore J (1999) Partitioning-based clustering for web document categorization. Decis Support Syst 27:329–341

    CrossRef  Google Scholar 

  24. Kleinberg J (2002) An impossibility theorem for clustering. In: Proceedings of 2002 conference advances in neural information processing systems, vol 15, pp 463–470

    Google Scholar 

  25. Shen C, Jin Z, Zhao Y, Fu Z (2017) Deep siamese network with multi-level simillarity perception for person re-identification. In: ACM conference. https://doi.org/10.1145/3123266.3123452

  26. Varior RR, Haloi M, Wang G (2016) Gated siamese convolutional neural network architecture for human re-identifcation. In: European conference on computer vision. Springer, pp 791–808

    Google Scholar 

  27. Subramaniam A, Chatterjee M, Mittal A (2016) Deep neural networks with inexact matching for person re-identifcation. In: Advances in neural information processing systems, pp 2667–2675

    Google Scholar 

  28. Chen W, Chen X, Zhang J, Huang K (2016) A multitask deep network for person re-identifcation. arXiv preprint arXiv:1607.05369

  29. Ahmed E, Jones M, Marks TK (2015) An improved deep learning architecture for person re-identifcation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3908–3916

    Google Scholar 

  30. Li W, Zhao R, Xiao T, Wang X (2014) Deepreid: deep filter pairing neural network for person re-identifcation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 152–159

    Google Scholar 

  31. Liu J, Zha ZJ, Tian QI, Liu D, Yao T, Ling Q, Mei T (2016) Multi-scale triplet CNN for person re-identifcation. In: Proceedings of the 2016 ACM on multimedia conference. ACM, pp 192–196

    Google Scholar 

  32. Schroff F, Kalenichenko D, Philbin J (2015) Facenet: a unied embedding for face recognition and clustering. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 815–823

    Google Scholar 

  33. Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. In: NIPS 2012: neural information processing systems, Lake Tahoe, Nevada

    Google Scholar 

  34. Song H, Kim M, Lee J (2019) SELFIE: refurbishing unclean samples for robust deep learning. In: Proceedings of 36th international conference on machine learning (ICML), Long Beach California

    Google Scholar 

  35. Wach HB, Dowski ER, Cathey WT (2000) Channel reduction and applications to image processing. Appl Opt 39(11):1794–1798

    Google Scholar 

  36. Ramírez Paulino I, Hounie I (2021) Image inpainting using patch consensus and DCT priors. In: Image processing on line, vol 11, pp 1–17. https://doi.org/10.5201/ipol.2021.286

  37. Lisani JL, Petro AB (2021) Automatic 1D histogram segmentation and application to the computation of color palettes. In: Image processing on line, vol 11, pp 76–104. https://doi.org/10.5201/ipol.2021.344

  38. Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1–9

    Google Scholar 

  39. Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097–1105

    Google Scholar 

  40. Marra S, Iachino MA, Morabito FC (2006) Tanh-like activation function implementation for high-performance digital neural systems. In: 2006 Ph.D. research in microelectronics and electronics, pp 237–240. https://doi.org/10.1109/RME.2006.1689940

  41. Cong J, Xiao B (2014) Minimizing computation in convolutional neural networks. In: International conference on artificial neural networks. Springer, pp 281–290

    Google Scholar 

  42. Ruder S (2017) Insight centre for data analytics, NUI Galway Aylien Ltd., Dublin An overview of gradient descent optimisation algorithms arXiv:1609.04747v2 [cs.LG]. 15 Jun 2017

Download references

Acknowledgements

I would like to thank Dr. P. Supraja and Mrs. A. Helen Victoria, who has helped in all the stages of my educational life. Without their help and guidance, it would have been a very difficult task for me. I would also like to thank Corrado Alessio for giving access to the Animal-10 dataset and Alex Krizhevsky for giving me access to the Cifar-10 dataset.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Ravi Shekhar Tiwari .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

About this paper

Verify currency and authenticity via CrossMark

Cite this paper

Tiwari, R.S. (2023). Channel-Based Similarity Learning Using 2D Channel-Based Convolutional Neural Network. In: Gupta, M., Ghatak, S., Gupta, A., Mukherjee, A.L. (eds) Artificial Intelligence on Medical Data. Lecture Notes in Computational Vision and Biomechanics, vol 37. Springer, Singapore. https://doi.org/10.1007/978-981-19-0151-5_28

Download citation

  • DOI: https://doi.org/10.1007/978-981-19-0151-5_28

  • Published:

  • Publisher Name: Springer, Singapore

  • Print ISBN: 978-981-19-0150-8

  • Online ISBN: 978-981-19-0151-5

  • eBook Packages: EngineeringEngineering (R0)