Adaptive real-time image smoothing using local binary patterns and Gaussian filters

Author

Teutsch, Michael ; Trantelle, Patrick ; Beyerer, Jurgen

Author_Institution

Fraunhofer Inst. of Optronics, Syst. Technol. & Image Exploitation (IOSB), Karlsruhe, Germany

fYear

2013

fDate

15-18 Sept. 2013

Firstpage

1120

Lastpage

1124

Abstract

Image smoothing is widely used for enhancing the quality of single images or videos. There is a large amount of application areas such as machine vision, entertainment industry with smart TVs or consumer cameras, or surveillance and reconnaissance with different imaging sensors. In many cases it is not easy to find the trade-off between high smoothing quality and fast processing time. However, this is necessary for the mentioned applications as they are dependent on real-time computing. In this paper, we aim to find a good trade-off. Local texture is analyzed with Local Binary Patterns (LBPs) which are used to adapt the size of a Gaussian smoothing kernel for each pixel. Real-time requirements are met by the implementation on a Graphical Processing Unit (GPU). An image of 512 × 512 pixels is processed in 2.6 ms.

Keywords

Gaussian processes; image denoising; image enhancement; image texture; smoothing methods; GPU; Gaussian filters; Gaussian smoothing kernel; LBP; adaptive real-time image smoothing; graphical processing unit; local binary patterns; local texture; real-time computing; time 2.6 ms; Graphics processing units; Image edge detection; Kernel; PSNR; Smoothing methods; Speckle; Image denoising; LBPs; image enhancement; locally adaptive; texture analysis; variable kernel size;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing (ICIP), 2013 20th IEEE International Conference on

Conference_Location

Melbourne, VIC

Type

conf

DOI

10.1109/ICIP.2013.6738231

Filename

6738231