Title :
A video stream processor for real-time detection and correction of specular reflections in endoscopic images
Author :
Tchoulack, Stéphane ; Langlois, J. M Pierre ; Cheriet, Farida
Author_Institution :
Dept. de genie Inf. et genie logiciel, Ecole Polytech. de Montreal, Montreal, QC
Abstract :
This paper presents the architecture and FPGA implementation of a video processor for detection and correction of specular reflections in endoscopic images by using an inpainting algorithm. Stream processing and parallelism are used to exceed real-time performance on NTSC format video without the need for an external memory. The system was implemented in a XC2VP30 FPGA and uses 91% of available slices. Image quality is significantly enhanced.
Keywords :
field programmable gate arrays; image enhancement; medical image processing; video signal processing; video streaming; FPGA implementation; NTSC format video; endoscopic images; image quality enhancement; inpainting algorithm; real-time detection; specular reflections correction; stream processing; video processor architecture; video stream processor; Augmented reality; Cardiology; Endoscopes; Field programmable gate arrays; Minimally invasive surgery; Neurosurgery; Optical reflection; Orthopedic surgery; Streaming media; Surges;
Conference_Titel :
Circuits and Systems and TAISA Conference, 2008. NEWCAS-TAISA 2008. 2008 Joint 6th International IEEE Northeast Workshop on
Conference_Location :
Montreal, QC
Print_ISBN :
978-1-4244-2331-6
Electronic_ISBN :
978-1-4244-2332-3
DOI :
10.1109/NEWCAS.2008.4606318
