Search

To overcome the imprecise shortcomings of keeping low-level outline signal in denoise method based on fractional calculus filtering and losing high-level detail signal in BM3D (block-matching 3D) filtering, this paper proposed a fractional block-matching 3D filtering method. It discussed the basic mathmatic theory of fractional calculus to apply it to the image processing, constructured the fractional integral denoising templates, and discussed the impact of fractional order selection for de-noising results. And it used two standard methods to evaluate result: subjective visual perception and objective peak signal to noise ratio (PSNR). The experiment results show that this method gets better results in reservations high-level details compared with wavelet filtering and nonlocal mean filtering. Through numerical realizing the method and analysing it with some advanced denoise methods today, it proves the correctness and reasonability of the theory and it gets the conclution that this method is better. [ABSTRACT FROM AUTHOR]

As for the drivers' eye open degree changing due to fatigue, this paper proposed a finite state machine based on PERCLOS algorithm and applied to pre-warning system of fatigue driving according to the original PERCLOS standards. Firstly, it used infrared camera to capture drivers' face in real time and detected face by ASM algorithm. To avoid the influence of the distance between man and camera, it normalized eye open degree when it was calculated. Then it obtained PERCLOS value by the proposed finite state machine based method. Finally, the eye open degree based system pre-warns the fatigue according to the established pre-warning mechanism. The experiment results show that this method can monitor drivers' fatigue status in real time and it is insensitive to light and drivers' accessories. [ABSTRACT FROM AUTHOR]