A generalized approach of convolutional and pooling layer in image processing using wavelet CNN
Keywords:
CNNs, pooling layer, image processing, using waveletAbstract
Spatial and spectral approaches area unit two major approaches for image processing tasks like and beholding. Among several such algorithms, convolutional neural networks (CNNs) have recently achieved significant performance improvement in several difficult tasks. CNNs enable the nation to utilize spectral data that is usually lost in typical CNNs however helpful in most image processing tasks. We tend to evaluate the sensitivity performance of Wavelet CNNs on texture classification and image annotation. The experiments show that Wavelet CNNs can do higher accuracy in each task than existing models, whereas having significantly fewer parameters than typical CNNs.
Downloads
References
Cimpoi, S. Maji, and A. Vedaldi. "Deep filter banks for texture recognition and segmentation." In IEEE Conference on Computer Vision and Pattern Recognition , 2015. DOI: https://doi.org/10.1109/CVPR.2015.7299007
Gao, O. Beijbom, N. Zhang, and T. Darrell. " Compact bilinear pooling." In IEEE Conference on Computer Vision and Pattern Recognition , 2016: 317-326. DOI: https://doi.org/10.1109/CVPR.2016.41
Lin, A. RoyChowdhury, and S. Maji. "Bilinear cnns for fine-grained visual recognition." In Transactions of Pattern Analysis and Machine Intelligence, 2017.
Whelan, Andrearczyk and P. F. "Using filter banks in convolutional neural networks for texture classification." Pattern Recognition Letters, 2016: 63-69. DOI: https://doi.org/10.1016/j.patrec.2016.08.016
S.Arivazhagan,T.G.SubashKumar,andL.Ganesan. Texture classification using curvelet transform. International Journal of Wavelets, Multiresolution and Information Processing, 05(03):451–464, 2007. DOI: https://doi.org/10.1142/S0219691307001847
Y. Boureau, J. Ponce, and Y. Lecun. A theoretical analysis of feature pooling in visual recognition. In International ConferenceonMachineLearning(ICML-10),pages111–118. Omnipress, 2010.
K. Chatfield, K. Simonyan, A. Vedaldi, and A. Zisserman. Return of the devil in the details: Delving deep into convolutional nets. In British Machine Vision Conference, 2014. DOI: https://doi.org/10.5244/C.28.6
M. Cimpoi, S. Maji, I. Kokkinos, S. Mohamed, and A. Vedaldi. Describing textures in the wild. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014. DOI: https://doi.org/10.1109/CVPR.2014.461
G. Huang, Y. Sun, Z. Liu, D. Sedra, and K. Q. Weinberger. DeepNetworkswithStochasticDepth,pages646–661. Springer International Publishing, 2016. DOI: https://doi.org/10.1007/978-3-319-46493-0_39
S. Ioffe and C. Szegedy. Batch normalization: Accelerating deep network training by reducing internal covariate shift. CoRR, abs/1502.03167, 2015.
T. B. J. T. Springenberg, A. Dosovitskiy and M. Riedmiller. Striving for simplicity: The all convolutional net. In International Conference on Learning Representations Workshop Track, 2015.
J.JinandH.Nakayama. Annotationordermatters: Recurrent image annotator for arbitrary length image tagging. In International Conference on Pattern Recognition (ICPR), pages 2452–2457, 2016.
Published
How to Cite
Issue
Section
Copyright (c) 2022 International journal of health sciences
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Articles published in the International Journal of Health Sciences (IJHS) are available under Creative Commons Attribution Non-Commercial No Derivatives Licence (CC BY-NC-ND 4.0). Authors retain copyright in their work and grant IJHS right of first publication under CC BY-NC-ND 4.0. Users have the right to read, download, copy, distribute, print, search, or link to the full texts of articles in this journal, and to use them for any other lawful purpose.
Articles published in IJHS can be copied, communicated and shared in their published form for non-commercial purposes provided full attribution is given to the author and the journal. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
This copyright notice applies to articles published in IJHS volumes 4 onwards. Please read about the copyright notices for previous volumes under Journal History.
