An Adaptive Image Inpainting Method Based on the Weighted Mean

Imaging inpainting is the process of digitally filling-in missing pixel values in images and requires carefully crafted image analysis tools. In this work, we propose an adaptive image inpainting method based on the weighted mean. The weighted mean is assessed to be better than the median because, for the case of the weighted mean, we can exclude the values of the corrupted pixels from evaluating values to fill those corrupted pixels. In the experiments, we implement the algorithm on an open dataset with various corrupted masks and we also compare the inpainting result by the proposed method to other similar inpainting methods – the harmonic inpainting method and the inpainting by directional median filters – to prove its own effectiveness to restore small, medium as well as fairly large corrupted regions. This comparison will be handled based on two of the most popular image quality assessment error metrics, such as the peak signal to noise ratio, and structural similarity. Further, since the proposed inpainting method is non-iterative, it is suitable for implementations to process big imagery that traditionally require higher computational costs, such as the large, high-resolution images or video sequences.

[1]  Dang N. H. Thanh,et al.  An adaptive image inpainting method based on euler's elastica with adaptive parameters estimation and the discrete gradient method , 2021, Signal Process..

[2]  Dang N. H. Thanh,et al.  A Denoising Method Based on Total Variation , 2015, SoICT.

[3]  Dang N. H. Thanh,et al.  An adaptive method for image restoration based on high-order total variation and inverse gradient , 2020, Signal Image Video Process..

[4]  Le Minh Hieu,et al.  An Iterative Mean Filter for Image Denoising , 2019, IEEE Access.

[5]  Dang N. H. Thanh,et al.  Image Inpainting Method Based on Mixed Median , 2019, 2019 Joint 8th International Conference on Informatics, Electronics & Vision (ICIEV) and 2019 3rd International Conference on Imaging, Vision & Pattern Recognition (icIVPR).

[6]  Dang N. H. Thanh,et al.  Adaptive total variation L1 regularization for salt and pepper image denoising , 2020 .

[7]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[8]  Dang N. H. Thanh,et al.  Distorted Image Reconstruction Method with Trimmed Median , 2019, 2019 3rd International Conference on Recent Advances in Signal Processing, Telecommunications & Computing (SigTelCom).

[9]  Jidesh Pacheeripadikkal,et al.  Non-local total variation regularization models for image restoration , 2018, Comput. Electr. Eng..

[10]  Xuehui Bi,et al.  Exemplar-Based Image Inpainting With Multi-Resolution Information and the Graph Cut Technique , 2019, IEEE Access.

[11]  Fang Li,et al.  A New Adaptive Weighted Mean Filter for Removing Salt-and-Pepper Noise , 2014, IEEE Signal Processing Letters.

[12]  Chin-Chen Chang,et al.  Analyzing and removing SureSign watermark , 2013, Signal Process..

[13]  S. D. Dvoenko,et al.  A method of total variation to remove the mixed Poisson-Gaussian noise , 2016, Pattern Recognition and Image Analysis.

[14]  Saeid Saryazdi,et al.  Image Inpainting Using Directional Median Filters , 2010, 2010 International Conference on Computational Intelligence and Communication Networks.

[15]  V. B. Surya Prasath,et al.  On Selecting the Appropriate Scale in Image Selective Smoothing by Nonlinear Diffusion , 2018, 2018 IEEE Seventh International Conference on Communications and Electronics (ICCE).

[16]  Tony F. Chan,et al.  Mathematical Models for Local Nontexture Inpaintings , 2002, SIAM J. Appl. Math..

[17]  S. D. Dvoenko,et al.  Image noise removal based on total variation , 2015 .

[18]  Jean-Michel Morel,et al.  Level lines based disocclusion , 1998, Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269).

[19]  Le Minh Hieu,et al.  Melanoma Skin Cancer Detection Method Based on Adaptive Principal Curvature, Colour Normalisation and Feature Extraction with the ABCD Rule , 2019, Journal of Digital Imaging.

[20]  Ze-Nian Li,et al.  Review and Preview: Disocclusion by Inpainting for Image-Based Rendering , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[21]  Jeffrey J. Rodríguez,et al.  Image Inpainting Using Nonlocal Texture Matching and Nonlinear Filtering , 2019, IEEE Transactions on Image Processing.

[22]  Jixiang Cheng,et al.  Markov random field-based image inpainting with direction structure distribution analysis for maintaining structure coherence , 2019, Signal Process..

[23]  Surya Prasath,et al.  Structure tensor adaptive total variation for image restoration , 2019, TURKISH JOURNAL OF ELECTRICAL ENGINEERING & COMPUTER SCIENCES.

[24]  Dang N. H. Thanh,et al.  An adaptive image inpainting method based on the modified mumford-shah model and multiscale parameter estimation , 2019, Computer Optics.

[25]  Serdar Enginoglu,et al.  An Iterative Image Inpainting Method Based on Similarity of Pixels Values , 2019, 2019 6th International Conference on Electrical and Electronics Engineering (ICEEE).