IMAGE SHARPENING WITH BLUR MAP ESTIMATION USING CONVOLUTIONAL NEURAL NETWORK
| Autor: | Andrey S. Krylov, D. A. Lyukov, Andrey Nasonov |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
lcsh:Applied optics. Photonics
Deblurring Pixel Computer science business.industry lcsh:T ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION lcsh:TA1501-1820 020206 networking & telecommunications 02 engineering and technology Sharpening Convolutional neural network lcsh:Technology Computer Science::Graphics Kernel (image processing) lcsh:TA1-2040 Computer Science::Computer Vision and Pattern Recognition 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Computer vision Artificial intelligence Image warping business lcsh:Engineering (General). Civil engineering (General) ComputingMethodologies_COMPUTERGRAPHICS |
| Zdroj: | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol XLII-2-W12, Pp 161-166 (2019) |
| ISSN: | 2194-9034 1682-1750 |
| Popis: | We propose a method for choosing optimal values of the parameters of image sharpening algorithm for out-of-focus blur based on grid warping approach. The idea of the considered sharpening algorithm is to move pixels from the edge neighborhood towards the edge centerlines. Compared to traditional deblurring algorithms, this approach requires only scalar blur level value rather than a blur kernel. We propose a convolutional neural network based algorithm for estimating the blur level value. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|