Chandrasekaran Raja and Narayanan Gangatharan. Appropriate Sub-band Selection in Wavelet Packet Decomposition for Automated Glaucoma Diagnoses. International Journal of Automation and Computing, vol. 12, no. 4, pp. 393-401, 2015. DOI: 10.1007/s11633-014-0858-6
Citation: Chandrasekaran Raja and Narayanan Gangatharan. Appropriate Sub-band Selection in Wavelet Packet Decomposition for Automated Glaucoma Diagnoses. International Journal of Automation and Computing, vol. 12, no. 4, pp. 393-401, 2015. DOI: 10.1007/s11633-014-0858-6

Appropriate Sub-band Selection in Wavelet Packet Decomposition for Automated Glaucoma Diagnoses

  • The most common reason for blindness among human beings is Glaucoma. The increase of fluid pressure damages the optic nerve which gradually leads to irreversible loss of vision. A technique for automated screening of Glaucoma from the fundal retinal images is presented in this paper. This paper intends to explore the significance of both the approximate and detail coefficients through wavelet packet decomposition (WPD). Decomposition is done with “db3” wavelet function and the images are decomposed up to level-3 producing 84 sub-bands. Two features, the energy and the entropy are calculated for each sub-band producing two feature matrices (158 images × 84 features). The above step is purely a statistical measure based on WPD. To enhance the diagnostic accuracy, the second phase considers the structural (biological) region of interest (ROI) in the image and then extracts the same features. It is worthy to note that direct biological features are not extracted to eliminate the drawbacks of segmentation whereas the biologically significant region is taken as biological-ROI. Interestingly, the detailed coefficient sub-bands (prominent edges) show more significance in the biological-ROI phase. Apart from enhancing the diagnostic accuracy by feature reduction, the paper intends to mark the significance indices, uniqueness and discrimination capability of the significant features (sub-bands) in both the phases. Then, the crisp inputs are fed to the classifier ANN. Finally, from the significant features of the biological-ROI feature matrices, the accuracy is raised to 85% which is notable than the accuracy of 79% achieved without considering the ROI.
  • loading

Catalog

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return