A Novel Technique for Target Recognition Using Multiresolution Technique

  • Tamanna Sahoo
  • Bibhuprasad MohantyEmail author
Conference paper
Part of the Lecture Notes in Networks and Systems book series (LNNS, volume 109)


Identification of targets in different circumstances is one of the challenging tasks in the computer vision area. This paper presents an algorithm that is capable of identifying specified targets embedded in visual image by means of 2D-Discrete Wavelet Transform and Wavelet Coefficient Features (WCFs). The computation of WCF via Gray Level Co-Occurrence Matrix (GLCM) of transformed sub-block image to obtain the seed block is one of the major tasks of this paper which uses two approaches: Firstly, GLCM of each detail subband and their summation provide the total GLCM of sub-block image. Second approach is the calculation of GLCM by creating the dynamics of sub-block image. From the seed block, the target object is obtained using region growing process where a seed point from seed block is extracted and processed to obtain the desired result. The results of second approach of the proposed method are very efficient through visual inspection.


Target Wavelet coefficient features Gray level co-occurrence matrix and region growing 


  1. 1.
    Arivazhagan S, Ganesan L (2004) Automatic target detection using wavelet transform. EURASIP J Appl Sig Process 17:2663–2674zbMATHGoogle Scholar
  2. 2.
    Pulla Rao C, Guruva Reddy A., Rama Rao CB (2016) Target detection using multi resolution analysis for camouflaged images. Int J Cybern Inf 5(4)CrossRefGoogle Scholar
  3. 3.
    Espinal F, Huntsberger TL, Jawerth BD, Kubota T (1998) Wavelet-based fractal signature analysis for automatic target recognition. Opt Eng 37(1):166–174CrossRefGoogle Scholar
  4. 4.
    Mahmoodabadi SZ, Ahmadian A, Abolhasani MD, Eslami M, Bidgoli JH (2005) Feature Extraction based on multiresolution wavelet transform. In: IEEE Proceedings, pp 3902–3905Google Scholar
  5. 5.
    Sahoo T, Mohanty B (2018, September) Moving object detection using background subtraction in wavelet domain. In: 2nd International Conference on Data Science and Business Analytics (ICDSBA)Google Scholar
  6. 6.
    Gomes JPP, Brancalion JFB, Fernandes D (2008) Automatic target recognition in synthetic aperture radar image using multiresolution analysis and classifiers combination. IEEEGoogle Scholar
  7. 7.
    Arivazhagan S, Ganesan L (2003) Texture classification using wavelet transform. Pattern Recogn Lett 24(9–10):1513–1521CrossRefGoogle Scholar
  8. 8.
    Hazra D (2011) Texture recognition with combined GLCM, wavelet and rotated wavelet features. Int J Comput Electr Eng 3(1):17938163Google Scholar
  9. 9.
    Shan Z, Aviyente S (2005) Image denoising based on the wavelet co-occurrence matrix. ICASSP2005, IEEE, pp 645–648Google Scholar
  10. 10.
    Pan Y, Chen Y, Fu Q, Zhang P, Xu X (2011) Study on the Camouflaged target detection method based on 3D convexity. Proc Modern Appl Sci 5:152–157Google Scholar
  11. 11.
    Singh SK, Dhawale CA, Misra S (2013) Survey of object detection methods in camouflaged image. In: Proceedings of IERI, Elsevier, pp 1–6CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.Department of Electronics and Communication EngineeringITER, Siksha ‘O’ Anusandhan University (Deemed to be University)BhubaneswarIndia

Personalised recommendations