Evaluation of Digital Inpainting Quality in the Context of Artwork Restoration

Improved digital image inpainting algorithms could provide substantial support for future artwork restoration. However, currently, there is an acknowledged lack of quantitative metrics for image inpainting evaluation. In this paper the performance of eight inpainting algorithms is first evaluated by means of a psychophysical experiment. The ranking of the algorithms thus obtained confirms that exemplar based methods generally outperform PDE based methods. Two novel inpainting quality metrics, proposed in this paper, eight general image quality metrics and four inpainting-specific metrics are then evaluated by validation against the perceptual data. Results show that no metric can adequately predict inpainting quality over the entire image database, and that the performance of the metrics is image-dependent.

[1]  Jon Y. Hardeberg,et al.  An adaptive Bilateral Filter for Predicting Color Image Difference , 2009, CIC.

[2]  Patrick Pérez,et al.  Region filling and object removal by exemplar-based image inpainting , 2004, IEEE Transactions on Image Processing.

[3]  Jun Zhou,et al.  Image Inpainting Based on Local Optimisation , 2010, 2010 20th International Conference on Pattern Recognition.

[4]  Alain Trémeau,et al.  Computational Color Imaging, Second International Workshop, CCIW 2009, Saint-Etienne, France, March 26-27, 2009. Revised Selected Papers , 2009, CCIW.

[5]  Adam Finkelstein,et al.  PatchMatch: a randomized correspondence algorithm for structural image editing , 2009, SIGGRAPH 2009.

[6]  Rachid Deriche,et al.  Vector-valued image regularization with PDEs: a common framework for different applications , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Manuel Menezes de Oliveira Neto,et al.  Fast Digital Image Inpainting , 2001, VIIP.

[8]  Alexandru Telea,et al.  An Image Inpainting Technique Based on the Fast Marching Method , 2004, J. Graphics, GPU, & Game Tools.

[9]  Dirk Walther,et al.  Interactions of visual attention and object recognition : computational modeling, algorithms, and psychophysics. , 2006 .

[10]  Jon Yngve Hardeberg,et al.  Evaluating colour image difference metrics for gamut‐mapped images , 2008 .

[11]  Hans Brettel,et al.  Evaluation of Spatial Gamut Mapping Algorithms , 2006, Color Imaging Conference.

[12]  Folkmar Bornemann,et al.  Fast Image Inpainting Based on Coherence Transport , 2007, Journal of Mathematical Imaging and Vision.

[13]  Sheila S. Hemami,et al.  VSNR: A Wavelet-Based Visual Signal-to-Noise Ratio for Natural Images , 2007, IEEE Transactions on Image Processing.

[14]  S. Cheung,et al.  Digital inpainting algorithms and evaluation , 2010 .

[15]  Jon Y. Hardeberg,et al.  A New Spatial Hue Angle Metric for Perceptual Image Difference , 2009, CCIW.

[16]  Mark D. Fairchild,et al.  Darwinism of Color Image Difference Models , 2001, CIC.

[17]  Brian A. Wandell,et al.  A spatial extension of CIELAB for digital color‐image reproduction , 1997 .

[18]  M R Luo,et al.  New algorithm for calculating perceived colour difference of images , 2006 .

[19]  Paul A. Ardis,et al.  Visual salience metrics for image inpainting , 2009, Electronic Imaging.