Veterinary Image Enhancement using DWTDCT and Singular Value Decomposition

Abstract

As imaging technology advances, one of the unavoidable part of image processing is the image enhancement. Image enhancement is to improve the visual quality for specific applications. The proposed algorithm enhances the visual quality of the vaginoscopic images of bitches using Discrete Wavelet Transform (DWT), Discrete Cosine Transform (DCT) and Singular Value Decomposition (SVD). The input image is decomposed into four frequency bands by using DWT. The low frequency band of the transformed image is again transformed by DCT into low frequency DCT coefficients and higher DCT coefficients. New low frequency band is formed by SVD. Inverse Discrete Cosine Transform (IDCT) is applied to produce the equalized image. Inverse Discrete Wavelet Transform (IDWT) of new low frequency band and the other three frequency band are combined to give the enhanced image. Different quality measures such as Root Mean Square Error (RMSE), Peak to Signal Noise Ratio (PSNR), Entropy, mean and Standard deviation are used to evaluate the performance of the model. The proposed model is implemented using MATLAB 2017a and obtained an average RMSE of 1.645. PSNR, Entropy, mean and standard deviation values for the proposed model are 44.12dB, 6.57, 103.35, 0.11 respectively. This qualitative analysis shows that proposed method seems to be useful for enhancing veterinary images for further processing.