Multimedia Tools and Applications

, Volume 76, Issue 6, pp 8449–8469 | Cite as

Performance analysis of Gabor wavelet for extracting most informative and efficient features

Article
  • 151 Downloads

Abstract

Gabor wavelet can extract most informative and efficient texture features for different computer vision and multimedia applications. Features extracted by Gabor wavelet have similar information as visualized by the receptive field of simple cells in the visual cortex of the mammalian brains. This motivates researchers to use Gabor wavelet for feature extraction. Gabor wavelet features are used for many multimedia applications such as stereo matching, face and facial expression recognition (FER), texture representation for segmentation. This motivates us to analyze Gabor features to evaluate their effectiveness in representing an image. In this paper, three major characteristics of Gabor features are established viz., (i) Real coefficients of Gabor wavelet alone is sufficient enough to represent an image; (ii) Local Gabor wavelet features with overlapping regions represent an image more accurately as compared to the global Gabor features and the local features extracted for the non-overlapping regions; and (iii) Real coefficients of overlapping regions are more robust to radiometric changes as compared to the features extracted from both global and local (non-overlapping regions) by using real, imaginary and magnitude information of a Gabor wavelet. The efficacy and effectiveness of these findings are evaluated by reconstructing the original image using the extracted features, and subsequently the reconstructed image is compared with the original image. Experimental results show that the local Gabor wavelet features extracted from overlapping regions represent an image more efficiently than the global and non-overlapping region-based features. Experimental results also show that the real coefficients alone is sufficient enough to represent an image more accurately as compared to the imaginary and magnitude informations.

Keywords

Feature extraction Gabor wavelet Mean square error and Correlation coefficients. 

References

  1. 1.
    Ali AM (2014) A 3D-based pose invariant face recognition at a distance framework. IEEE Trans Inf Forensic Secur 9(12):2158–2169CrossRefGoogle Scholar
  2. 2.
    Bhagavathy S, Tesic J, Manjunath BS (2003) On the Rayleigh nature of Gabor filter outputs. In: Proceedings IEEE International Conference Image Processing, pp 745–748Google Scholar
  3. 3.
    Daugman J (1980) Two-dimensional spectral analysis of cortical receptive field profiles. Vis Res 20(10):847–856CrossRefGoogle Scholar
  4. 4.
    Daugman JG (1985) Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. J Opt Soc A Opt Image Sci Vis 2(7):1160–1169CrossRefGoogle Scholar
  5. 5.
    Daugman JG (1988) Complete discrete 2-D Gabor transforms by neural networks for image analysis and compression. IEEE Trans Acoust Speech Signal Process 36 (7):1169–1179CrossRefMATHGoogle Scholar
  6. 6.
    Hirschmller H, Scharstein D (2007) Evaluation of cost functions for stereo matching. In: Proceeding International Conference Computer Vision and Pattern Recognition, pp 1–8Google Scholar
  7. 7.
    Hirschmuller H, Scharstein D (2009) Evaluation of stereo matching costs on images with radiometric differences. IEEE Trans Pattern Anal Mach Intell 31(9):1582–1599CrossRefGoogle Scholar
  8. 8.
    Jahanbin S, Choi H, Bovik AC (2011) Passive multimodal 2-D+3-D face recognition using Gabor features and landmark distances. IEEE Trans Inf Forensic Secur 6(4):1287–1304CrossRefGoogle Scholar
  9. 9.
    Jiang W, Lam KM, Shen TZ (2009) Efficient edge detection using simplified Gabor wavelets. IEEE Trans Syst Man Cyber 39(4):1036–1047CrossRefGoogle Scholar
  10. 10.
    Jones JP, Palmer LA (1987) An evaluation of the 2-D Gabor filter model of simple receptive fields in cat striate cortex. J Neurophysiol 58(6):1233–1258Google Scholar
  11. 11.
    Kosov S, Scherbaum K, Faber K, Thormahlen T, Seidel H-P (2009) Rapid stereo-vision enhanced face detection. In: Proceedings IEEE International Conference Image Processing, pp 1221–1224Google Scholar
  12. 12.
    Kumar A, Pang G (2000) Fabric defect segmentation using multichannel blob detectors. Opt Eng 39(12):3176–3190CrossRefGoogle Scholar
  13. 13.
    Lin L, Luo P, Chen X, Zeng K (2012) Representing and recognizing objects with massive local image patches. Pattern Recogn 45:231–240CrossRefMATHGoogle Scholar
  14. 14.
    Liebelt J, Xiao J, Yang J (2006) Robust AAM fitting by fusion of images and disparity data. In: Proceedings IEEE International Conference Computer Vision and Pattern Recognition, pp 2483–2490Google Scholar
  15. 15.
    Lee TS (1996) Image representation using 2D Gabor wavelets. IEEE Trans Pattern Anal Mach Intell 18(10):959–971CrossRefGoogle Scholar
  16. 16.
    Loizou CP, Pattischis CS, Istepanian RSH, Pantziaris M, Tyllis T, Nicolaides A (2004) Quality evaluation of ultrasound imaging in the carotid artery. In: Proceeding Mediterranean Electrotechnical Conference, pp 395–398Google Scholar
  17. 17.
    Moghaddam HA, Dehaji MN (2013) Enhanced Gabor wavelet correlogram feature for image indexing and retrieval. Pattern Anal Appl 16:163–177MathSciNetCrossRefGoogle Scholar
  18. 18.
    Mohamed MA, Rashwan HA, Mertsching B, Garcia MA, Puig D (2014) Illumination-robust optical flow approach using local directional pattern. IEEE Trans Circ Syst Video Technol 24(9):1499–1508CrossRefGoogle Scholar
  19. 19.
    Malathi T, Bhuyan MK (2015) Estimation of disparity map of stereo image pairs using spatial domain local Gabor wavelet. IET Comput Vis 9(4):595–602CrossRefGoogle Scholar
  20. 20.
    Ojala T, Pietikainen M, Maenpaa T (2002) Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans Pattern Anal Mach Intell 24(7):971–987CrossRefMATHGoogle Scholar
  21. 21.
    Peng Z, Li Y, Cai Z, Lin L (2015) Deep boosting: Joint feature selection and analysis dictionary learning in hierarchy. Neurocomputing:1–20Google Scholar
  22. 22.
    Panetta RL, Liu C, Yang P (2013) A pseudo-spectral time domain method for light scattering computation. In: Kokhanovsky AA (ed) Light Scattering Reviews 8: Radiative transfer and light scattering. Springer, London, p 151Google Scholar
  23. 23.
    Rajadell O, Garca-Sevilla P, Pla F (2009) Scale analysis of several filter banks for color texture classification. In: Proceedings International Symposium Advances in Visual Computing: Part II, pp 509?-518Google Scholar
  24. 24.
    Shen L, Jia S (2011) Three-dimensional Gabor wavelets for pixel-based hyperspectral imagery classification. IEEE Trans Trans Geosci Remote Sens 49 (12):5039–5046CrossRefGoogle Scholar
  25. 25.
    Soares JVB, Leandro JJG, Cesar Jr. RM, Jelinek HF, Cree MJ (2006) Retinal vessel segmentation using the 2-D Gabor wavelet and supervised classification. IEEE Trans Med Imag 25(9):1214–1222CrossRefGoogle Scholar
  26. 26.
    Scharstein D, Szeliski R (2002) A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. Int J Comput Vis 47(1):7–42CrossRefMATHGoogle Scholar
  27. 27.
    Scharstein D, Szeliski R (2003) High-accuracy stereo depth maps using structured light. In: Proceeding International Conference Computer Vision and Pattern Recognition, pp 195–202Google Scholar
  28. 28.
    Scharstein D, Pal C (2007) Learning conditional random fields for stereo. In: Proceeding International Conference Computer Vision and Pattern Recognition, pp 1–8Google Scholar
  29. 29.
    Scharstein D, Hirschmller H, Kitajima Y, Krathwohl G, Nesic N, Wang X, Westling P (2014) High-resolution stereo datasets with subpixel-accurate ground truth. In: Proceeding German Conference Pattern Recognition, pp 31–42Google Scholar
  30. 30.
    Tou JY, Tay YH, Lau PY (2007) Gabor filters and grey-level co-occurrence matrices in texture classification. In: MMU International Symposium Information and Communications Technologies, pp 197–202Google Scholar
  31. 31.
    Tou JY, Tay YH, Lau PY (2009) Gabor filters as feature images for covariance matrix on texture classification Problem. Advances in neuro-information processing. Lect Notes Comput Sci 5507:745–751CrossRefGoogle Scholar
  32. 32.
    Xu C, Li S, Tan T, Quan L (2009) Automatic 3D face recognition from depth and intensity Gabor features. Pattern Recogn 42(9):1895–1905CrossRefMATHGoogle Scholar
  33. 33.
    Xie X, Lam KM (2009) Facial expression recognition based on shape and texture. Pattern Recogn 42(5):1003–1011CrossRefGoogle Scholar
  34. 34.
    Yang M, Zhang L, Shiu SCK, Zhang D (2013) Gabor feature based robust representation and classification for face recognition with Gabor occlusion dictionary. Pattern Recogn 46:1865–1878CrossRefGoogle Scholar
  35. 35.
    Zuiga AG, Florindo JB, Bruno OM (2014) Gabor wavelets combined with volumetric fractal dimension applied to texture analysis. Pattern Recogn Lett 36:135–143CrossRefGoogle Scholar
  36. 36.
    Zhang B, Shan S, Chen X, Gao W (2007) Histogram of Gabor phase patterns (HGPP): A novel object representation approach for face recognition. IEEE Trans Image Process 16(1):57–68MathSciNetCrossRefGoogle Scholar
  37. 37.
    Zhang L, Tjondronegoro D, Chandran V (2014) Random Gabor based templates for facial expression recognition in images with facial occlusion. Neurocomputing 145:451–464CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2016

Authors and Affiliations

  1. 1.Indian Institute of Technology GuwahatiGuwahatiIndia

Personalised recommendations