Image sharpening by grid warping

We develop a post-processing algorithm which enhances the results of the existing image deblurring methods. It performs additional edge sharpening using grid warping. The idea of the proposed algorithm is to transform the neighborhood of the edge so that the neighboring pixels move closer to the edge, and then resample the image from the warped grid to the original uniform grid. The proposed technique preserves image textures while making the edges sharper. The effectiveness of the method is shown for basic deblurring methods on LIVE database images with added blur and noise.

The proposed algorithm is not posed as a global image deblurring method. It enhances only image edges neighborhood and practically does not affect image textures.

The proposed algorithm has the following advantages and features:

• 1. The best results are achieved when grid warping is used as a post-processing method after global image deblurring methods. Traditional image deblurring methods improve overall image quality while grid warping pays special attention to image edges.
• 2. No artifacts like ringing effect or noise amplification are introduced because pixel values are not changed.
• 3. Unlike morphological methods and shock filters, the resulting images look natural and do not inevitably become piecewise constant.
• 4. It can be used as a standalone method of image sharpening. It is a good choice in the presence of strong noise and complex and non-uniform blur kernel.

You can try this method using our program.

Grid warping idea:
Traditional sharpening approach: pixel values are modified	Grid warping approach: pixels are shifted

Results:
Blurred and noisy image	Wiener filter deblurring
Wiener + warping	SSIM improvement after warping

Average PSNR values for images from LIVE database with added blur and noise.
Grid warping is applied and a post-processing algorithm:

Publications

2015

A. Nasonova, A. Krylov. “Deblurred images post-processing by Poisson warping” // IEEE Signal Processing Letters, Vol. 22, No. 4, 2015, pp. 417−420. PDF.

A. S. Krylov, A. V. Nasonov. “3D image sharpening by grid warping” // Lecture Notes in Computer Science (IScIDE2015), Vol. 9242, 2015, pp. 441−450. PDF.

A. S. Krylov, A. A. Nasonova, A. V. Nasonov. “Image warping as an image enhancement post-processing tool” // In: Proceedings of 9th Open German-Russian Workshop on Pattern Recognition and Image Understanding (OGRW 2014). Koblenz, Germany, 2015, pp. 132−135. PDF.

2014

A. Nasonova, A. Nasonov, A. Krylov, I. Pechenko, A. Umnov, N. Makhneva. “Image warping in dermatological image hair removal” // Lecture Notes in Computer Science, Vol. 8815, ICIAR 2014, Vilamoura, Algarve, Portugal, 2014, pp. 159−166. PDF.

A. Krylov, A. Nasonova, A. Nasonov. “Grid warping for image sharpening using one-dimensional approach” // In: Proceedings of International Conference on Signal Processing (ICSP2014). IEEE, Hangzhou, China, 2014, pp. 672−677. PDF.

À. À. Íàñîíîâà. «Äåôîðìàöèîííûé ìåòîä ïîâûøåíèÿ ðàçðåøåíèÿ èçîáðàæåíèé ñ ñîõðàíåíèåì ðåçêîñòè ãðàíèö» // â: Òðóäû 16-é ìåæäóíàðîäíîé êîíôåðåíöèè «Öèôðîâàÿ îáðàáîòêà ñèãíàëîâ è åå ïðèìåíåíèå» (DSPA'2014), ò. 2. Ìîñêâà, 2014, ñ. 452−455. PDF.

À. À. Íàñîíîâà, À. Ñ. Êðûëîâ. «Ïîâûøåíèå ðåçêîñòè èçîáðàæåíèé íà îñíîâå äåôîðìàöèè ïèêñåëüíîé ñåòêè» // â: Òåçèñû êîíôåðåíöèè «Ëîìîíîñîâñêèå ÷òåíèÿ 2014». ÂÌÊ ÌÃÓ, 2014, ñ. 40−41.

A. Nasonov, A. Krylov. “Grid warping in total variation image enhancement methods” // In: Proceedings of International Conference on Image Processing (ICIP2014). IEEE, Paris, France, 2014, pp. 4517−4521. PDF.