Comparative Study of CNN and QCNN for Image Recognition in Heterogeneous Image Processing

Rashmita Routray*, Abhishek Ray**
*-** Department of Instrumentation and Electronics Engineering, College of Engineering and Technology, Bhubaneswar, Odisha, India.
Periodicity:January - March'2021
DOI : https://doi.org/10.26634/jip.8.1.18081

Abstract

Image recognition has many applications today, and is being done by using various methods and technologies. Neural networks are now popularly used for various image processing applications. QCNN (Quaternion Convolutional Neural Networks) and CNN (Convolutional Neural Networks) are two methods that can be used for image recognition. In this paper, we compare performance of QCNN and CNN in colour image recognition. It shows that QCNN can easily capture the inter pixel relations producing better RGB images whereas CNN produces worst gray scale images.

Keywords

QCNN, CNN, Image Recognition, Heterogeneous Image Processing.

How to Cite this Article?

Routray, R, and Ray, A. (2021). Comparative Study of CNN and QCNN for Image Recognition in Heterogeneous Image Processing. i-manager's Journal on Image Processing, 8(1), 25-35. https://doi.org/10.26634/jip.8.1.18081

References

[1]. Arena, P., Fortuna, L., Occhipinti, L., & Xibilia, M. G. (1994, May). Neural networks for quaternion-valued function approximation. In Proceedings of IEEE International Symposium on Circuits and Systems-ISCAS'94 (Vol. 6, pp. 307-310). IEEE. https://doi.org/10.1109/ISCAS.1994.409587
[2]. Collobert, R. (2004). Large scale machine learning (Thesis Library). Université de Paris VI, Paris.
[3]. Dataman. (2018, November 8). What is image recognition? Dataman in AI. Retrieved from https:// medium.com/dataman-in-ai/module-6-image-recognii on-for-insurance-claim-handling-part-i-a338 d16c9de
[4]. Ganesh, P. (2019, October 18). Types of convolution kernels: Simplified. Towards Data Science. https://towards datascience.com/types-of-convolution-kernels-simplifiedf040cb307c37
[5]. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 770-778).
[6]. Kingma, D. P., & Ba, J. (2015). Adam: A method for rd stochastic optimization. [Poster Presentation]. In 3 International Conference on Learning Representations, ICLR 2015, Retrieved from https://arxiv.org/pdf/1412. 6980.pdf
[7]. Madali, N. (2020, July 20). Quaternion convolutional neural networks. Retrieved from https://medium.com/@ nabil.madali/quaternion-convolutional-neural-networksd87faad6cc46
[8]. Nitta, T. (1995, November). A quaternary version of the back-propagation algorithm. In Proceedings of ICNN'95- International Conference on Neural Networks (Vol. 5, pp. 2753-2756). IEEE. https://doi.org/10.1109/ICNN.1995.4881 66
[9]. Parcollet, T., Morchid, M., & Linarès, G. (2019, May). Quaternion convolutional neural networks for heterogeneous image processing. In ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 8514-8518). IEEE. https://doi.org/10.1109/ICASSP.2019.8682495
[10]. Parcollet, T., Ravanelli, M., Morchid, M., Linarès, G., Trabelsi, C., De Mori, R., & Bengio, Y. (2018). Quaternion recurrent neural networks. In 7th International Conference on Learning Representations (ICLR 2019). Retrieved from https://openreview.net/pdf?id=ByMHvs0cFQ
[11]. Sangwine, S. J. (1996). Fourier transforms of colour images using quaternion or hypercomplex, numbers. Electronics Letters, 32(21), 1979-1980.
[12]. Socher, R., & Mundra, R. (2015). Deep learning for NLP [Lecture Notes]. https://cs224d.stanford.edu/lecture_ notes/LectureNotes4.pdf.
[13]. Zhu, X., Xu, Y., Xu, H., & Chen, C. (2018). Quaternion convolutional neural networks. In Proceedings of the European Conference on Computer Vision (ECCV) (pp. 631-647).
If you have access to this article please login to view the article or kindly login to purchase the article

Purchase Instant Access

Single Article

North Americas,UK,
Middle East,Europe
India Rest of world
USD EUR INR USD-ROW
Online 15 15

Options for accessing this content:
  • If you would like institutional access to this content, please recommend the title to your librarian.
    Library Recommendation Form
  • If you already have i-manager's user account: Login above and proceed to purchase the article.
  • New Users: Please register, then proceed to purchase the article.