Effect of Denoising on Vectorized Convolutional Neural Network for Hyperspectral Image Classification

Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 490)

Abstract

The remotely sensed high-dimensional hyperspectral imagery is a single capture of a scene at different spectral wavelengths. Since it contains an enormous amount of information, it has multiple areas of application in the field of remote sensing, forensic, biomedical, etc. Hyperspectral images are very prone to noise due to atmospheric effects and instrumental errors. In the past, the bands which were affected by noise were discarded before further processing such as classification. Therefore, along with the noise the relevant features present in the hyperspectral image are lost. To avoid this, researchers developed many denoising techniques. The goal of denoising technique is to remove the noise effectively while preserving the important features. Recently, the convolutional neural network (CNN) serves as a benchmark on vision-related task. Hence, hyperspectral images can be classified using CNN. The data is fed to the network as pixel vectors thus called Vectorized Convolutional Neural Network (VCNN). The objective of this work is to analyze the effect of denoising on VCNN. Here, VCNN functions as the classifier. For the purpose of comparison and to analyze the effect of denoising on VCNN, the network is trained with raw data (without denoising) and denoised data using techniques such as Total Variation (TV), Wavelet, and Least Square. The performance of the classifier is evaluated by analyzing its precision, recall, and F1-score. Also, comparison based on classwise accuracies and average accuracies for all the methods has been performed. From the comparative classification result, it is observed that Least Square denoising performs well on VCNN.

Keywords

Least square denoising Total variation-based denoising Wavelet denoising Vectorized convolutional neural network Hyperspectral image classification 

References

  1. 1.
    Zhao YQ, Yang J (2015) Hyperspectral image denoising via sparse representation and low-rank constraint. IEEE Trans Geosci Remote Sens 53(1)Google Scholar
  2. 2.
    Aswathy C, Sowmya V, Soman K (2015) Admm based hyperspectral image classification improved by denoising using legendrefenchel transformation. Indian J Sci Technol 8(24):1CrossRefGoogle Scholar
  3. 3.
    Hu W, Huang Y, Wei L, Zhang F, Li H (2015) Deep convolutional neural networks for hyperspectral image classification. J SensGoogle Scholar
  4. 4.
    Athira S, Mohan R, Poornachandran P, Soman KP (2016) Automatic modulation classification using convolutional neural network. International Science Press, IJCTA, pp 7733–7742Google Scholar
  5. 5.
    Ren JS, Xu L (2015) On vectorization of deep convolutional neural networks for vision tasks. arXiv preprint arXiv:1501.07338
  6. 6.
    Chen Y, Jiang H, Li C, Jia X, Ghamisi P (2016) Deep feature extraction and classification of hyperspectral images based on convolutional neural networks. IEEE Trans Geosci Remote Sens 54(10):6232–6251CrossRefGoogle Scholar
  7. 7.
    Slavkovikj V, Verstockt S, De Neve W, Van Hoecke S, Van de Walle R (2015) Hyperspectral image classification with convolutional neural networks. In: Proceedings conference. 23rd ACM international conference on Multimedia, 2015, pp 1159–1162 Google Scholar
  8. 8.
    Srivatsa S, Ajay A, Chandni C, Sowmya V, Soman K (2016) Application of least square denoising to improve admm based hyperspectral image classification. In: proceedings conference, 6th international conference on adavances in computing and communications, ICACC 2016, vol 93, pp 416–423Google Scholar
  9. 9.
    Rudin LI, Osher S, Fatemi E (1992) Nonlinear total var iation based noise removal algorithms. Physica D 60(1):259–268MathSciNetCrossRefMATHGoogle Scholar
  10. 10.
    Donoho DL, Johnstone JM (1994) Ideal spatial adaptat ion by wavelet shrinkage. Biometrika 81(3):425–455MathSciNetCrossRefMATHGoogle Scholar
  11. 11.
    Bhosale NP, Manza RR (2014) Image denoising based on wavelet for satellite imagery: a review. Int J Modern Eng Res 4(2014): 63–68Google Scholar
  12. 12.
    Abadi M et al (2015) TensorFlow: large-scale machine learning on heterogeneous systems. Software available from tensorflow.org. Available: http://tensorflow.org/
  13. 13.
    Fawcett T (2006) An introduction to ROC analysis. Pattern Recogn Lett 27(8):861–874Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  • K. Deepa Merlin Dixon
    • 1
  • V. Sowmya
    • 1
  • K. P. Soman
    • 1
  1. 1.Center for Computational Engineering and Networking (CEN), Amrita School of EngineeringAmrita Vishwa Vidyapeetham, Amrita UniversityCoimbatoreIndia

Personalised recommendations