ALWT based Regularizer for Improvement of Low Intensity Visual Data

Main Article Content

Jyothula Sunil Kumar, et. al.


Image Completion is the process of recovering corrupted image with very limited observations. It is a challenging task to achieve accurate recovery in image with minimum observations. Many researchers are proposed various methods to recover the corrupted image. Here a new Adaptive Lifting Wavelet Transform (ALWT) based Alternating Direction Method of Multipliers (ADMM) optimization technique is proposed. A spiffing image recovery is observed at 90% of missing ratio. The non-linear filters are used in ALWT to obtain the lost observations. The Image Quality Assessment (IQA) metrics are considered to evaluate the performance of proposed approach. The IQA metrics namely Mean Square Error (MSE), Peak Signal to Noise Ratio (PSNR) and Structural Similarity (SSIM) are achieved 32.32, 33.04dB and 0.8666 respectively. Here, the Additive White Gaussian Noise (AWGN) with standard deviation 150 is considered. The Mean Absolute Reconstruction Error (MARE), MSE and PSNR values are obtained as 3.176, 12.11 and 37.31dB respectively.


Download data is not yet available.


Metrics Loading ...

Article Details

How to Cite
et. al., J. S. K. . (2021). ALWT based Regularizer for Improvement of Low Intensity Visual Data. Turkish Journal of Computer and Mathematics Education (TURCOMAT), 12(10), 2847–2855. Retrieved from