Image interpolation based on 2D-DWT and HDP-HMM

This paper proposes a nonparametric approach with the purpose of estimating discrete wavelet transform (DWT) sub-band coefficients for high performance image interpolation. The number of clusters of defined statistical model that represents wavelet coefficients during the learning process is not fixed. The interpolating method is based on Hierarchical Dirichlet Process (HDP) where it uses the Blocked Gibbs Sampling method to obtain the optimum final values. The proposed HDP-HMM exploits statistical inter-scale, and intra-scale dependencies of image sub-bands of three-level decomposed 2D-DWT. It derives sub-bands of low resolution (LR) image, to obtain sub-bands of desired high resolution (HR) image. This research implements Hidden Markov model (HMM) to model the wavelet coefficients, and HDP to model the observations. It uses a very small size dataset that contains both LR and HR images of the dataset. The sophisticated statistical model introduced of the paper has excellent results in terms of Peak-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), Feature Similarity Index (FSIM), and Edge PSNR (EPSNR). It also has a great capability of repressing disturbing artifact, due to ability to model statistical dependencies of distant pixels. This method, and other compared state-of-the-art methods, have implemented on eighteen test-benches, with different statistical properties.

Automated summary

This paper proposes a nonparametric approach for estimating discrete wavelet transform (DWT) sub-band coefficients in order to achieve high performance image interpolation. The proposed method utilizes the Hierarchical Dirichlet Process (HDP) and Blocked Gibbs Sampling to obtain optimal values, and exploits statistical inter-scale and intra-scale dependencies to derive high-resolution image sub-bands. The sophisticated statistical model introduced in this research yields excellent results in various evaluation metrics and has the ability to suppress disturbing artifacts.